GEOMATICS AND ENVIRONMENTAL ENGINEERING • Volume 17 • Number 6 • 2023

[Link]

Gitisree Biswas1, Tusar Kanti Roy2

Measuring Objective Walkability

from Pedestrian-Level Visual Perception
Using Machine Learning and GSV
in Khulna, Bangladesh

Abstract: Walkability entails measuring the degree of walking activity, a non-motorized

mode of active transportation crucial in fast-developing urban settings and
combating sedentary lifestyles. While there has been extensive objective re-
search focusing on factors related to the physical environment that influence
walkability, there has been a comparatively limited exploration into objectively
evaluating a pedestrian’s visual perception. This study in Khulna, Bangladesh,
aimed to develop a novel method for objectively measuring walkability based
on pedestrian-level visual perception using machine learning. In this research,
ResNet, a computer vision model, analyzed 127 panoramic Google Street
View images taken at 200-meter intervals from seven major roads. The model,
trained with the “deeplabv3plusResnet18CamVid” algorithm, quantified five
selected visual features. The results, including walkability rankings, correlation
analysis, and spatial mapping, highlighted that greenery and visual enclosures
significantly influenced the walkability index. However, the impact of other
visual features was less distinctive due to an overall poor streetscape condition.
This study bridged the gap between human perception and scientific intelli-
gence, allowing for the evaluation of previously “unmeasurable” streetscape
designs. It provides valuable insights for more human-centered planning and
transportation strategies, addressing the challenges of modern urbanization
and sedentary behavior.

Keywords: walkability, streetscapes features, visual perception, machine learning, Google

Street View (GSV)

Received: 21 March 2023; accepted: 17 July 2023

© 2023 Author(s). This is an open access publication, which can be used, distributed and re-
produced in any medium according to the Creative Commons CC-BY 4.0 License.

1
Khulna University of Engineering & Technology (KUET), Department of Urban and Regional
Planning, Khulna, Bangladesh, email: giti181biswas@[Link] (corresponding author),
[Link]
2
Khulna University of Engineering & Technology (KUET), Department of Urban and Regional
Planning, Khulna, Bangladesh, email: tusarkroy@[Link],
[Link]

5
6 G. Biswas, T.K. Roy

1. Introduction
According to [1], 27.5% of the Earth’s population is not efficiently physically
active. Rapid urbanization and vehicular dependency tend to result in sedentary
lifestyles, which increases the risk of cardiovascular disease, stroke, Type-2 diabetes,
and other non-communicable diseases [2–4]. Walking is considered to be an active
mode of non-motorized transportation, as it requires greater physical exertion, pro-
motes walking behavior as a mode of transportation for short trips or errands, and
highlights human-oriented transportation. However, walkability is a measurable
quality that is distinct from simple walking [5]. Walkability refers to the degree of
friendliness to which an area is designed and accessible for walking [6]. Research on
walkability (a widely studied topic) has shown a two-fold connection between walk-
ability and the built environment: a well-designed environment promotes walking
as a mode of transportation and contributes to health benefits from the mutual con-
venience of an economic aspect [7].
Walkability is variably influenced by walking environments that consist of
physical and non-physical elements. Physical components like street connectivity,
accessibility, block size, land use, street amenities, retail floor area ratio, vegetation,
and horizontal-vertical road elements are generally measured at a macro-scale using
GIS or Point of Interest data [8]. Non-physical elements constitute the perceptual
judgment of the feeling of attractiveness, comfort, pleasurability, place proximity,
safety from crime, and social cohesion. Human-oriented walkability refers to the
perspective of pedestrians, which deals with the non-physical qualitative design and
functionality of a built environment. According to [9, 10], walkability components
can be categorically measured into direct and indirect approaches of objective and
subjective measures. Also, [11, 12] explored that physical elements alone might not
be attributed to the walking experience. Arguably, walking behavior may be implic-
itly impacted by the subjective dimension of perceptual opinions, visual intuitions,
and environmental psychology. Eventually, [13] critically addressed that the chal-
lenge to moving from a subjective measure to an objective one is to ensure technical
reliability. In developing countries, this challenge is unbeatable without a standard
objective method that can counter the limitations of time, cost-effectiveness, micro-­
scale data availability, and the inconsistency of judgments among the raters for any
individual qualities.
Google Maps and Google Earth’s Google Street View (GSV) feature offer us-
ers’ images of cities from more than 20 nations worldwide. This allows users to
see panoramic images of public streets as if they were walking down the streets in
person [14]. It is easily accessible to anyone with internet connectivity and can be
used to objectively determine pedestrian counts on a street and analyze walkability
trends to gain insights into the pedestrian activity in a city. The advancement of
machine-learning technology combined with GSV images significantly contributes
to urban research [15, 16].
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 7

The use of GSV for evaluating streetscape elements was reliable for micro-scale
analysis according to [17]. The greenery and building-to-street ratio (enclosure) [18]
and sidewalk-to-street proportion [19] showed a correlation with the walk score. Some
GSV-based studies estimated only greenery pixels to find their influence on walking
behavior more specifically over walking time [20–24]. The evaluation of urban design
quality in three ways using sky proportion as calculated by [16] also showed itself to be
reliable with pedestrian counts and walk scores. An alternative method for manual pe-
destrian counting through object detection has been proposed [25]. However, focusing
on only one or two physical features fails to provide a comprehensive understanding
of a visual environment’s impact on walkability. Much of the walkability research
was correlation-oriented; the researchers analyzed complex visual environments using
GSV image detection and showed their concordance with manual walking behavior
data from their field observation. Very few of the studies were able to provide a direct
method where walkability was measured by and correlated with the same variables that
were processed by image segmentation [26]. Developed countries have predominantly
adopted objective measures for walkability, while in the developing countries of South
America, Africa, Southeast Asia, and Southern Asia, it is subjectively oriented [27]. For
Bangladesh, existing walking-related studies are incommensurate, qualitative, and
policy review-­oriented [28–32]; even more, none of the studies have applied a computer
vision model and GSVs to measure micro-scale walkability in Khulna to date.
Considering the study gaps, this study aims to propose a comprehensive program-
matic walkability index that takes the design factors of streetscapes into account and
converts subjective assessments into objective ones. The index ranks walkability based
on visual factors and examines the correlations between different features; the results
are presented in terms of percentage and spatial analysis for all of the studied roads.
The study hypothesizes that the visual appearances of streetscapes have a significant
impact on walkability, and the proposed index provides an objective measure through
sensing technology. The research questions that are addressed by this study are related
to how street design affects walkability and the effectiveness of the objective measure:
– How can visual streetscape features be quantified objectively?
– How can visual streetscape features be applied to measure walkability?
– How is walkability correlated to visual streetscape features?
The study’s outcomes can guide urban planners, architects, and policymakers
in addressing walkability and improving urban health by incorporating the findings
into developmental plans. It may also inspire similar studies for walkability in other
metropolitan cities in Bangladesh.

2. Study Area
Situated in the southwest of Bangladesh, Khulna is the third-largest city and is
bounded by the Bay of Bengal to its south. Khulna City Corporation (KCC) consists
8 G. Biswas, T.K. Roy

of a population of 720,000 with an area of 45.17 km2. Khulna has a robust multimodal
transportation system that includes roads, rivers, and railways; over time, however,
the road network is gaining a competitive advantage over maritime and rail trans-
portation. The total road network of Khulna includes 1215 roads that total 824.47 km
(primary, secondary, and tertiary roads). Several inclusive transportation develop-
ment projects have been conducted over time that have facilitated convenient walking
behavior via the construction of footpaths/walkways and extensions of existing roads
(including 88 km of separate slow-moving vehicle lanes) [33]. Researchers have found
that main roads that cover mixed land use areas, roads that connect multiple desti-
nations over short distances, and access to primary roads that have potential street-
scape infrastructure encourage pedestrians regarding both leisure and utilitarian
walking [34]. In the city areas of Bangladesh, secondary and tertiary roads are usual-
ly poorly attributed to road enclosures (disproportionate street-building ratios) [35],
openness (congested roads with low sky proportions), and attractiveness elements
(greenery); these are the significant influential features that demotivate pedestrians
due to comfort and safety concerns. Considering these facts, only seven major prima-
ry roads were selected as study roads, and a total of 127 GSV images were accepted
as study samples (Fig. 1). The total lengths of the study roads are described in Table 1.

Fig. 1. Study road map of Khulna

Measuring Objective Walkability from Pedestrian-Level Visual Perception... 9

Table 1. Selected study roads

Study Roads Start and End Points Lengths [km]

Outer Bypass Road Notun Rasta to Gollamari 7.1
Old Jessore Road Goalkahli Bus Stand to Jora Gate 3.4
KD Ghosh Road Thanar More to Zilla School 1.6
Jalil Sarani Boyra Girls’ College to Rayer Mahal 2.2
Khan Jahan Ali Road Rupsa Ghat Road to Ferry Ghat Road 3.1
KDA Avenue Shibbari More to Royal More 2.0
Sher-E-Bangla Road Gollamari to Power House More 3.2

3. Methodology
3.1. Methodological Framework
The methodology was initiated
by conceptualizing a “street level”
walkability study design that incor-
porated four phases, including street
view data collection, image process-
ing, calculating and evaluating visual
walkability, and addressing the eval-
uative impact (Fig. 2). First, a data set
that was comprised of 127 panoramic
street view images was created by
using Google Earth. Second, the po-
tential physical components that im-
pacted or might impact the contextual
built environment and physical activi-
ty were classified pixel-wise by apply-
ing the ResNet computer vision model
after an extensive literature review.
Classified physical components were
converted into five visual features by
applying the proposed formulas, and
the walkability was analyzed by calcu-
lating the OVW index. The evaluation
part was comprised of three parts, in-
cluding walkable road-rank determi-
nation, mapping representation of
visual features, and a correlation anal-
ysis of the visual features and OVW. Fig. 2. Methodological framework
 10

Fig. 3. Reviewed streetscape features and sub-features to measure walkability

G. Biswas, T.K. Roy
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 11

3.2. Overview of Streetscape Features

Understanding its multidimensional nature, walkability has become a complex
concept that encompasses multiple factors that influence pedestrian walkability. In
recent years, this topic has been examined from different perspectives (such as ur-
ban planning, public health, and analytical techniques), and researchers have ex-
plored numerous features and sub-features in order to assess walkability based on
these perspectives in attempts to capture its comprehensive nature (Fig. 3) [36, 37].
All of these streetscape features and sub-features have been previously used in
the literature (categorized in Table 2).

Table 2. List of walkability literature using reviewed streetscape features and sub-features

Streetscape features Studies

Functional Environment [2], [38], [39], [40], [41], [42], [43], [44], [45]
(Accessibility, Street Connectivity, Land Use, Density)

Urban Design Quality [9], [16], [25], [26], [27], [46], [47], [48], [49], [50]
(Transparency, Coherence, Imageability, Complexity,
Human Scale, Legibility, Enclosure, Crowdedness)

Safety [39], [40], [44], [45], [51], [52], [53]

(Traffic Safety, Crime Security)

Streetscape Design Quality [17], [23], [38], [39], [44], [45], [54]
(Comfort, Sense of Place, Pleasurability, Aesthetics,
Attractiveness)

Pedestrian Facility [17], [27], [39], [44], [52], [53], [54]

(Sidewalk Widths, Sidewalk Slopes, Parking Spaces,
Obstacles on Sidewalks, Cleanliness on Sidewalks,
Pedestrian Infrastructures)

Functional Definition of Key Streetscape Visual Features

Before the image processing and pixel calculation, five key visual design fea-
tures were generated from the 11 initial physical features that were viewed in the
panoramic GSV image. This selection focused on how frequently the features were
used in urban design studies, how easily their functional definitions could be under-
stood, and their computational compatibility with existing machine-learning models
(including SegNet, ResNet, DeepLab, and YOLO) [55–58]. Publications [12, 13, 59]
first addressed the visual characteristics that covered a majority of the complex ur-
ban design and spatial analytics.
Greenness
Street vegetation has been shown to act as a stimulant for the promotion of out-
door activity, and researchers significantly emphasize this factor in the assessment
of walkability. More precisely, it has been shown that an increase in the amount of
12 G. Biswas, T.K. Roy

visible flora in an area has a positive impact on easing unpleasant psychological

symptoms [60]. The counterpart ascendancy of greenness and visual crowdedness on
walking is positively attributed to greenness; on the other hand, crowding the obsta-
cles of streets limit smooth walking activities. Greenness is the strongest visual attri-
bute that directly captivates pedestrians’ visual senses of aesthetics and beauty. Even
though vegetation is being measured by the conventional GIS-based NDVI indices,
advanced machine learning and GSV are being employed to objectively quantify sub-
jective greenery in health, social, environmental, and psychological studies [61–63].
Openness
Though openness is related to an enclosure, it conceptually refers to the degree
of the exposure to the sky. Openness generates a wide and well-lit visionary impact
that induces comfort and relaxation in users [64]. In this study, openness has been
quantified as the sky proportion that is visible from a standing stance to the total
environment’s pixel number. The presence of proportionate vertical structures and
trees with wide horizontal elements of roads, sidewalks, and setbacks creates a rela-
tively high exposure of openness [65]. Also, a road with a relatively higher openness
may question the feeling of safety and create discomfort and emptiness.
Visual Enclosure
In the walkability study, enclosure defines how pedestrians visualize a street’s
walking environment to be separated and surrounded by its horizontal and vertical
elements [66]. The visual enclosure is estimated with the proportions of the road
widths, sidewalks, setbacks, and vertical structures and canopies. The majority of
the time, vertical features determine how roadways are enclosed; it will be a more
successful place when the outdoor area is distinctively proportioned in shape as
compared to the nearby buildings [67]. The visual confinement of the enclosure has
a profound impact on walking willingness; a higher vertical and lower horizontal
ratio can be oppressive and discomforting [9].
Visual Crowdedness
Street elements like vehicles, billboards, signboards, electric poles, lamp posts,
and sign-symbols (which tend to create disquietness and unwillingness to walk)
are compositely considered to be obstacles. A higher number of obstacles tend to
make a walking environment noisier and visually crowded. From some conceptual
aspects, crowdedness and complexity represent the same meaning but are different
in their direction of perception [68, 69]. Complexity refers to the aesthetical diversity
of streetscape and architectural embellishments [9]; on the contrary, pedestrian en-
vironments with higher complexities or that are monotonously established are dis-
couraging to walkers. Two methods for evaluating complexity have been suggest-
ed by a thorough architectural study on visual complexity: the first involves ambiguȬ
˜žœȱpatterns, and the second involves patterns that are created by environmental
ŠŒtors
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 13

Visual Pavement
Visual pavement represents the degree of the arrangement of horizontal com-
ponents. The proportionate appearance between the road width and the sideways
elements like sidewalks, footpaths, and fences are calculated to measure the visual
pavement. A higher proportion of the sideways parts allows for suitably arranged
pathways for walking [71].

3.3. Data Processing: Objective Visual Walkability (OVW)

Street View Image Collection
The data-collection phase started by selecting seven study roads from the unit-
ed road network of Khulna (using Google Earth) and generating the study points
by splitting the roads into 200 m intervals (using ArcGIS 10.5). A reconnaissance
survey on the study roads revealed that a 200-meter-distance interval was sufficient
for capturing relevant information on roadside features, traffic density, land use,
transportation infrastructure, and key points of interest. This interval was aligned
with the standard practices in related studies [72] and was systematically effective
for minimizing data overload. Choosing this interval was practical and feasible in
terms of time, budget, and computing resources while allowing for efficient data
collection and maintaining the necessary level of detail for analysis. Accordingly,
the data set was created by capturing a 360° panoramic-street-view image for each
of the study points by compiling Google Maps and Street View Download 360. Goo-
gle Maps is an open-accessible street-view image resource that is available in Ban-
gladesh; it is provided with high resolution and substantial detailed information
on the studied roads. This study required panoramic views of the roads to make
them equivalent to the visual experiences of pedestrians. So, iStreetView software
was used to get the panorama URL link of the study points, and the 360° panoramic
images were downloaded from Street View Download 360 software using Panora-
ma ID. These 360° panoramic images were dimensioned with 360° horizontal and
180° vertical coverage of the street sites. However, for those points where land-
marks and structures were changed or erected over time, GSV was not appropriate
for showing accurate views. For those points, real-time 360° panoramic images were
captured using Google Camera, and both types of images from Google Maps and
Google Camera were resized. In this method, the field-of-view (FoV) (or the central
field of human vision for the panoramic image boxes) was set to 60°. FoV generally
refers to the extent of the angle that is viewed in a virtual image that is equiva-
lent to the eye-level pedestrian experience for a specific study point. This is how
six 60° images can cover a 360° horizontal surrounding area [73]. Figure 4 shows
that the FoV that was extracted from the panorama was represented in the frames
of the vision boxes for analyzing the visual perspectives of pedestrians. Setting the
necessary FoV is important for achieving real-time perspectives from each part of
the images.
 14
G. Biswas, T.K. Roy

Fig. 4. Field-of-view (FoV) determination in frames of vision boxes from panoramic image
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 15

Image Feature Recognition:

ResNet Training, Image Segmentation, and Pixel Quantification
MATLAB was used for the segmentation process, where a machine-learning
algorithm was utilized to make the machine recognize streetscape features accord-
ing to the classified pixels. To operate these algorithms, an artificial neural net-
work (ANN) called a residual neural network (ResNet) was devised. This is the first
fully functional very deep feedforward neural network with hundreds of layers with
a deep convolutional encoder-decoder architecture for semantic pixel-wise labeling
for increasing segmentation accuracy (far better than prior neural networks) [74].
There are 18 deep layers in the architecture’s 72 tiers; first, a convolution layer of
a size of 33 receives the input, while the batch normalization, activation, and pool-
ing layers are the following three layers. ReLU (rectified linear unit) is the activation
function that is utilized. The pooling layer has a stride of 2 and measures 33. There
is a “residual learning unit” that makes use of any skip connections between two
such units. The “fully connected” layer with the “Softmax” activation function is
employed at the network’s termination. The network’s input size is 224 × 224 × 3,
which has been predetermined. Due to its intricate layer structure and the fact that
each layer receives input from other layers and outputs to other layers, the network
is considered to be a DAG network. Its goal is to make it possible for numerous
convolutional layers to operate well. ResNet’s main concept is the usage of jumping
connections – often known as identity connections or shortcut connections. Most
of the time, these connections work by jumping over one or more levels to provide
shortcuts between them. The purpose of establishing these shortcut connections was
to address the primary problem of disappearing gradients that deep networks com-
monly experience. By reusing the activations from the prior layer, these shortcut
connections fix the vanishing gradient problem.
ResNet uses reinforcement learning to infer pixel-wise class labels, where it re-
quires a training data set that consists of a large number of GSV images. For this cur-
rent image segmentation, a pre-trained network algorithm called “deeplabv3plus-
Resnet18CamVid” (developed by Cambridge University) was used for validation;
it contained a data set of 701 training images, 140 test images, and 140 images. This
whole mechanism is represented in Figure 4; it shows the application of the pre-
trained “deeplabv3plusResnet18CamVid” network algorithm on its training set in
the convolutional encoder-decoder of the ResNet architecture, which optimizes the
machine to recognize the features and segment a whole image into feature-wise pix-
el classification according to the designated RGB colors. This involves the whole
process of image training, testing, and validation. When the machine was optimized
with supervision learning, the study area’s GSV image was inserted as input, and
the final segmented output was derived (shown in Figure 5).
 16

Fig. 5. ResNet architecture

Source: Basic ResNet architecture of this research (encoder-decoder architecture collected from [56])
G. Biswas, T.K. Roy

Fig. 6. Streetscape attribute declaration and re-classification

Measuring Objective Walkability from Pedestrian-Level Visual Perception... 17

Objective Visual Walkability (OVW) Calculation

The ResNet architecture was supervised for feature-wise pixel segmentation ac-
cording to RGB inferences. Using the necessary codes in MatLab, the feature-wise
pixel number from each segmented image was extracted. A total of 11 features were
defined in the initial segmentation and, thereafter, re-classified into a total of seven
features (shown in Figure 6) for the calculative convenience of the OVW index
(shown in Table 3). After the total 11 features were recognized by the RGB character-
izations, their pixel numbers were estimated.
Table 3 shows that the feature-wise classified pixel numbers from all six 60° part-
ed sub-images of Royal More were calculated in order to obtain the total pixel num-
ber of the panoramic image. In the same way, the total pixel count was determined
from all of the sample images.

Table 3. Estimated pixel counts of segmented features (Royal More)

Images

Features

Sky 199,377 128,303 238,332 241,860 280,436 241,330 1,336,917

Buildings 75,507 99,633 19,374 39,303 41,354 62,561 482,591

Poles 125 315 63 549 1412 88 673

Roads 216,276 238,098 266,439 269,601 225,859 276,977 1,529,158

Sidewalks 46,495 24,075 12,392 28,734 26,083 28,595 77,038

Trees 207 102 367 355 3141 32 40,886

Sign symbols 21,082 44,051 31,442 6051 50 2460 22,258

Fences 695 542 400 638 642 591 2166

Cars 18,366 26,913 40,051 27,847 34,557 13,441 236,712

Pedestrians 497 185 118 112 175 110 1216

Bikes 660 476 343 502 520 492 2385

Total pixels 641,750 621,591 628,747 608,383 623,128 608,401 3,732,000

18 G. Biswas, T.K. Roy

To calculate the objectively measured walkability, these features were com-

piled to build five key formulas that indicated five key features; these five features
constructed a walkability formula called “objective visual walkability” (shown in
Table 4), which is a modified adaptation from [26]. Greenness, openness, visual
crowdedness, visual enclosure, and visual pavement were the five key features for
calculating the OVW index. The calculated values were the pixel numbers where the
higher the values were, the better the level that the features represented (except for
the visual crowdedness feature). In the same way, a higher index value represented
the better walkability of that location (for this study, this ranged between 3 and 8 on
a scale of 1–10).

Table 4. Formulations and definitions of OVW Index

Key Functional
Formula
features definition

Degree to
which sky por- Sum of sky pixels
Openness O-level =
tion is exposed Sum of total pixels
to pedestrians

Degree to
which street
greenery expo- Sum of tree pixels
Greenness G-level =
sure can affect Sum of total pixels
how pedestri-
ans feel

Degree to
which obstruc- C-level =
Visual
tion visibility
crowded-
can affect how = Sum of obstacle (Pole, sign-symbols, car, pedestrian, and bike) pixels
ness Sum of total pixels
pedestrians
feel

Way outdoor
area resembles
Visual room (ratio of E-level = Sum of vertical objective (Building and tree) pixels
enclosure vertical objects Sum of horizontal featured (Pavement, road and fence) pixels
to horizontal
features)

Effects of
proportions
Visual of sideways Sum of sideway (Pavement and fence) pixels
P-level =
pavement and roads on Sum of road pixels
perceptions of
pedestrians

Objective visual walkability (OVW) = (O + G + C + E + P) ⋅ 5

Measuring Objective Walkability from Pedestrian-Level Visual Perception... 19

The objective visual walkability (OVW) index calculation was started by apply-
ing the formula that was constructed by assembling the five visual indices that are
shown in Equation (1). Next, the OVW values of each study point of each study road
were summed up, and this cumulative value was averaged by the total number of
study points that existed on that study road.

∑ OVW of study points

OVW for each road = (1)
No. of study points

4. Results
4.1. Walkability Ranking
After the composite OVW index calculations for the seven study roads, a rank-
ing is illustrated in Table 5 according to their value priority. Here, KD Ghosh Road
appears to be ranked first (with the highest walkability index value – 6.0046), and
KDA Avenue ranks last (with the lowest index score – 4.1753). KD Ghosh Road is
a popular route for leisure walking for locals, despite the fact that it is the shortest
route; this is due to its location near important government buildings (like Circuit
House, Khulna Divisional Court, and the police station) and its abundance of street
amenities and greenery. On the contrary, KDA Avenue is less inviting for walking be-
cause it is surrounded by fast-growing economic development, high-rise infrastruc-
ture, and multiple mixed crowds (making it even more visually less enclosed). On-
going disruptions throughout the year for road maintenance and repair by various
authorities make it unable to walk due to a lack of adequate coordination. The study
showed that walkability is influenced by the visual appeal of a street, which is affect-
ed by factors like the availability of street amenities and the level of maintenance.

Table 5. OVW calculation and ranking of study roads

∑OVW No. ∑OVW of study points/

Study roads Ranking
of study points of study points No. of study points

Outer Bypass Road 199.3215 41 4.8615 4

Old Jessore Road 95.9934 18 5.3329 2

KD Ghosh Road 42.0322 9 6.0046 1

Jalil Sarani Road 86.6761 16 5.0985 3

Khan Jahan Ali Road 76.4345 16 4.7771 5

Sher-E-Bangla Road 73.5244 17 4.3249 6

KDA Avenue Road 45.9284 10 4.1753 7

20 G. Biswas, T.K. Roy

Figure 7 represents one set of sample images from each study road; these imag-
es provide insight into how real-time pedestrian environments have been segment-
ed by feature-wise pixel classification.

Fig. 7. Sample segmented images of study roads

4.2. Correlation Analysis of Initial Elements

and Generated Key Visual Features
To identify the statistically meaningful relationship among multiple vari-
ables, a two-tailed significance-tested multiple correlation analysis was conduct-
ed over a sample data set of 127 GSV images (shown in Table 6). The corre-
sponding relationship was represented as the Pearson correlation coefficient in
a comparison matrix. The first part of the four-stage correlation analysis evalu-
ated the multi-­collinearity among the visual indices and the degree of influence
of the independent visual indices on the dependent variable (“walkability”). The
relatively low (or negative) correlation among the visual indices indicates that
the seven initial explanatory elements were individual, and the five key visual
indices that were generated from the initial components did not overlap (inde-
pendently influencing the walkability). This made the comparison matrix valid
without an interpretation bias. The correlation coefficients (0.614, 0.750, 0.483)
showed that greenness and visual enclosure had a strong positive effect, and
visual pavement had a moderate positive influence on walkability. Conversely,
openness (−0.511) and visual crowdedness (−0.070) had a negative correlation
with walkability, which was systematically valid because congested roads with
crowds make it disturbing for walking.
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 21

Table 6. Correlation analysis of walkability index,

key walkability features, and initial elements

Part A: Correlation coefficient of five streetscape features and walkability (OVW)

Visual
Visual Visual
Features Openness Greenness crowded- IVW
enclosure pavement
ness
Openness 1 −0.651** −0.001 −.0754** 0.014 −0.511**
Greenness −0.651** 1 −0.400** 0.765** −0.204* 0.614**
Visual
−0.001 −0.400** 1 −0.213* 0.200* −0.070
crowdedness
Visual enclosure −0.754** 0.765** −0.213* 1 −0.142 0.750**
Visual pavement 0.014 −0.204* 0.200* −0.142 1 0.483**
IVW −0.511** 0.614** −0.070 0.750** 0.483** 1
Part B: Correlation coefficient of visual crowdedness and its visual elements
Visual Sign-
Features Pole Car Pedestrian Bike
crowdedness symbols
Visual
1 −0.124 0.164 0.863** 0.247** 0.236**
crowdedness
Pole −0.124 1 −0.060 −0.142 −0.092 −0.033
Sign-symbol 0.164 −0.060 1 −0.010 0.167 0.259**
Car 0.863** −0.142 −0.010 1 0.187* 0.141
Pedestrian 0.247** −0.092 0.167 0.187* 1 0.051
Bike 0.236** −0.033 0.259** 0.141 0.051 1
Part C: Correlation coefficient of visual enclosure and its visual elements
Visual
Features Building Tree Sidewalk Road Fence
enclosure
Visual enclosure 1 0.216* 0.662** −0.225* −0.023 0.203*
Building 0.216* 1 −0.456** 0.117 −0.130 −0.142
Tree 0.662** −0.456** 1 −0.262** 0.165 0.325**
Sidewalk −0.225* 0.117 −0.262** 1 −0.584** 0.295**
Road −0.023 −0.130 0.165 −0.584** 1 −0.095
Fence 0.203* −0.142 0.325** 0.295** −0.095 1
Part D: Correlation coefficient of visual pavement and its visual elements
Visual
Features Sidewalk Road Fence
pavement
Visual pavement 1 0.914** −0.682** 0.315**
Sidewalk 0.914** 1 −0.584** 0.295**
Road −0.682** −0.584** 1 −0.095
Fence 0.315** 0.295** −0.095 1

* Correlation is significant at the 0.05 level (2-tailed).

** Correlation is significant at the 0.01 level (2-tailed).
22 G. Biswas, T.K. Roy

The next three parts of the correlation analysis evaluated the relationships
among the visual indices and the streetscape elements from which they were gen-
erated. Openness and greenness were not included in this analysis, as they were
determined using a single component.
Part B revealed that the sub-elements of car, pedestrian, bike, and sign-symbol
had strong (correlation coefficient range of 0.7 to 0.9), moderate (range of 0.5 to 0.7),
and weak (range of 0.2 to 0.5) positive correlations with visual crowdedness, respec-
tively. The pole had a negative relationship (with a coefficient range of −0.1 to −0.3),
as it was considered to be less disruptive to walkability as a vertical infrastructure. Pe-
destrians and bikes had the highest correlation, with a maximum of four co-elements.
Part C found that the vertical features of buildings, trees, and fences had strong
influences on the visual enclosure, with positive correlations ranging from 0.2
to 0.65. Meanwhile, horizontal elements were found to have a negative correlation,
indicating that the construction and combination of vertical elements were more
important for a proportionate streetscape design. All of the co-elements were indi-
vidually important for the visual enclosure, resulting in negative or zero interactive
correlations among them.
In the comparison matrix for visual pavement, pavement, and fence, it had a pos-
itive correlation (coefficient range from 0.3 to 0.9), while road had a negative correla-
tion. The interactive correlations among the co-elements followed a similar trend,
with sidewalks and fences positively correlating, and roads negatively correlating.

4.3. Percentage-Level Representation of Visual Walkability Features

The stacked columns in Figure 8 show at what percentages all of the five visu-
al indices are present and viewed from a totality of vision from a standpoint. So,
the percentage level of the five visual indices at each of the study points for all of
the study roads is shown. Since the walkability index for each study point is de-
rived by compositing the five visual indices, the degree of the walkability of a study
point is combinedly dependent on all of the five key features. In the OVW ranking,
KD Ghosh Road ranked first, with a comparatively higher degree of proportioned
greenness, enclosure, and sidewalk (which made the road visually open, comfort-
able, and pleasant). Although the lowest level of greenery reduced the shades result-
ed in increasing openness, a comparatively lower degree of road pavement, enclo-
sure, and greater crowdedness compositely made KDA Avenue the least walkable
in the OVW index.
A correlation analysis of enclosure suggested vertical elements to be influential,
which is reflected in the graphical representation of road-wise feature distribution.
Also, the study roads with approximately the same widths and sidewalks impact-
ed relatively the same over the horizontal part of the enclosure. Accordingly, the
buildings with comparatively lower building heights and the higher setbacks of the
residential building along with the trees on Old Jessore Road represented higher
ranges of the enclosure.
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 23

Fig. 8. Stacked bar chart of visual feature percentages

24 G. Biswas, T.K. Roy

a) b)

Openness Greenness
0.072200–0.219500 0.001000–0.030700
0.219501–0.317600 0.030701–0.067300
0.317601–0.366400 0.067301–0.133800
0.366401–0.405000 0.133801–0.201600
0.405001–0.502200 0.201601–0.312100

c) d)

Visual Crowdedness Visual Enclosure

0.021900–0.044800 0.089500–0.185800
0.044801–0.062600 0.185801–0.270800
0.062601–0.082800 0.270801–0.389700
0.082801–0.108300 0.389701–0.567100
0.108301–0.154200 0.567101–0.819400

e) f)

Visual Pavement OVW

0.017400–0.070400 3.288580–3.913500
0.070401–0.140000 3.913501–4.549900
0.140001–0.223900 4.549901–5.203100
0.223901–0.368000 5.203101–6.009500
0.368001–0.550500 6.009501–7.281100
KCC Boundary 0 0.5 1 2 Kilometers

Fig. 9. Spatial distribution of visual features and walkability index:

a) openness; b) greenness; c) visual crowdedness; d) visual enclosure;
e) visual pavement; f) objective visual walkability (OVW)
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 25

4.4. Spatial Distribution of Visual Walkability

The study conducted a spatial analysis where the choropleth mapping in Fig-
ure 8 showed how the five walkability measuring indices values varied spatially
within the 127 study points. Figure 9a represents a lower degree of openness in
KD Ghosh and Old Jessore Roads. In contrast, these two roads had a higher degree
of greenness with trees and canopies in Figure 9b, which minimized sky exposure.
This implied a fact that, even though a road that has a moderate horizontal-­vertical
enclosure can be distorted by lower openness, large vertical canopies provide shad-
ing and reduce sky exposure. However, the greenness mapping indicated that
roads that were ranked less-walkable in the OVW index had lower ranges of green-
ness. In Figure 9c, the values are quite interspersed where Old Jessore Road is the
least-crowded road because it is surrounded by residential land use (where the hu-
man crowd and vehicular movement was less). Oppositely, Khan Jahan Ali Road,
KDA Avenue, and Sher-E-Bangla Road had a higher range of crowdedness because
they run across the CBD and the major economic hub of Khulna. The enclosure
mapping in Figure 9d tends to illustrate a similar trend of crowdedness in Out-
er Bypass Road, since this long route covers multiple land uses. Theoretically and
functionally, the overall pavement conditions of Khulna’s roads are not suitable for
overall walking, so the overall values in Figure 9e are distorted. Finally, Figure 9f
illustrates the aggregated OVW index scores that were obtained from the respective
five indices. This is the final understanding of the spatial walkable conditions for all
of the study points, where KD Ghosh Road appeared to be the most-walkable road,
and KDA Avenue was the least-walkable.

5. Discussions
Studies from various fields such as behavioral geography, urban planning, and
cognitive psychology have discovered the concept of a “sense of place” that involves
how individuals visually perceive and connect with their surroundings. Despite
this, visual street design elements have been less explored – only 5% [27]; this is due
to the lack of a standard and user-friendly objective method. An objective measure
combined with an advanced machine-learning algorithm and GSVs for assessing the
visual designs of streets offers a robust tool. For this objective approach, it is no lon-
ger obscured to relate visionary notions for cityscape designing and planning – even
at a micro-scale level – as visual elements are calculated through human-scale ob-
servation (which is automated and can be replicated without manual observation).
The image-segmentation process that is applied through the ResNet architecture has
enormous advantages for achieving the study goal, as ResNet models can be pre-
trained on large data sets and then fine-tuned on smaller data sets; this can be useful
in built-environment analysis where labeled data is limited [75]. The deeper net-
work principle makes it capable to extract a detailed number of features to alleviate
26 G. Biswas, T.K. Roy

the vanishing gradient problem. The current study used 11 physical features syn-
thesized into five key visual features that were compositely framed for pedestrian-­
oriented comfort; this has significantly contributed to visual cognitive studies, urban
planning, and architectural design. The results showed that roads that are close to
CBD or economic-commercial zones distress its visual comfort for crowded side-
walks, multi-modal traffic flow, and high-rise infrastructure. The roads with higher
walkable values ranked the presence of visible greenness and enclosure higher than
other features, which attributed them as the predominant features. The remaining
features could not resonate with distinctive influence, as the overall roads were not
accommodating enough with diversified and standard streetscape facilities. This
is the perverse effect of prioritizing motorized transportation over non-motorized
traffic. In contrast with human scale intelligence, this method can supplementarily
be used as a technical tool for zoning rules, land-use resizing, and architectural de-
sign guidelines like “Active Design Guidelines” [76]; to identify problematic roads
and determine the features that were difficult to examine. It can be simulated in the
comparative analysis with the conventional subjective approach and a GIS-based
objective measure. The current research can be extended to evaluate socio-economic
behavioral and planning studies. Also, it scopes up the opportunities to integrate
multidimensional research interests, including public health, real estate, medical
research [77], and cycling behavior. From a futuristic viewpoint, a global online sys-
tem can be generated that enables image-segmentation services to be available for
relevant types of image data sets and integrated into walkability indexes like Neigh-
borhood Environment Walkability Scale (NEWS) [78] and Walkscore® [79].
Policies and strategies that address sustainability and transportation are essen-
tial for promoting a walkable city. The BRT (Bus Rapid Transit) Walkability Strategy
aims to promote a sustainable and walkable city through improved access, securi-
ty, and vibrancy in its streets, parks, and public spaces [80]. National transporta-
tion policies such as the National Land Transport Policy (2004) and the Integrated
Multi-Modal Transport Policy (2013) focus on safe and developed transportation
systems and infrastructure investment [32]. However, market-driven land-use pol-
icies and financial interests can hinder progress. Major cities in Bangladesh (like
Khulna) face challenges in promoting walkability due to their heavy traffic flows
and inadequate road infrastructures. This is due to the lack of coordination between
urban and transportation planning authorities, which prioritize automotive mobili-
ty over pedestrian needs. The proposed visual walkability may encourage planners
and policymakers to prioritize walkability as a sustainable planning strategy and
approach it from a technologically driven human-centered visual perspective.
The study of the visual walkability index has limitations, as it only analyzed
certain aspects of the walking environment and did not take other sensory factors
like smell, sound, and mental perception into account. It also did not consider sub-
jectively measured elements such as social cohesion, comfort, safety, and pleasur-
ability [2]. Vision-oriented perceptual features were analyzed without the inclusion
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 27

of other sensual features that are oriented to smells, sounds, and cognitive sensitiv-
ity. Conventional methods of assessing walkability use spatial factors like land-use
mix, road networks, dwellings, and intersection densities, which is a different ap-
proach from this study. This study is not a complete replacement for other methods
of assessing the multidimensional aspects of walkability. In addition, conducting
GSV-based studies in developing countries like Bangladesh can be challenging due
to the lack of updated Street View images in Google Maps and the unavailability of
GSVs in rural areas (which restricts the study’s reach).

6. Conclusion

To conclude, this objective approach proposed a visual walkability in Khulna

that was intended to quantitatively measure “unmeasurable” visual streetscape el-
ements using an artificial pedestrian’s visual level perception, which was difficult
with a subjective approach. The application of a machine learning-based ResNet
model with the input of Google Street View images was able to extract five key visu-
al streetscape features through image segmentation, providing a cost-effective and
scalable solution to objectively measure walkability. A quantitative analysis of clas-
sified features and the OVW index showed quite satisfactory real-time performance.
This study highlights the potential for using machine-learning technology to support
urban planning and design efforts by providing objective data on the walkability of
a given area, which can help when making decisions to ensure diversified cityscape
design elements, greenery, and other pedestrian-friendly infrastructures. With the
responsive supervision of planners, scholars, and decision-makers, this scopes up the
further development and research opportunities that are related to a “sense of place.”

References

[1] Guthold R., Stevens G.A., Riley L.M., Bull F.C.: Worldwide trends in insufficient
physical activity from 2001 to 2016: A pooled analysis of 358 population-based sur-
veys with 1.9 million participants. The Lancet Global Health, vol. 6(10), 2018,
pp. e1077–e1086. [Link]
[2] Alfonzo M.A.: To walk or not to walk? The hierarchy of walking needs. Envi-
ronment and Behavior, vol. 37(6), 2005, pp. 808–836. [Link]
0013916504274016.
[3] Litman T.: Evaluating Public Transportation Health Benefits. 2011. [Link]
ebrary.​com/​lib/sfu/[Link]?docID=10534560 [access: 1.09.2019].
[4] Hallal P.C., Lee I.M.: Prescription of physical activity: An undervalued interven-
tion. The Lancet, vol. 381(9864), 2013, pp. 356–357. [Link]
S0140-6736(12)61804-2.
28 G. Biswas, T.K. Roy

[5] Southworth M.: Designing the walkable city. Journal of Urban Planning and De-
velopment, vol. 131(4), 2005, pp. 246–257. [Link]
9488​(2005)131:4(246).
[6] Lwin K.K., Murayama Y.: Modelling of urban green space walkability: Eco-­
friendly walk score calculator. Computers, Environment and Urban Systems,
vol. 35(5), Sep. 2011, pp. 408–420. [Link]
2011.05.002.
[7] Imani M.: City sustainability: The influence of walkability on built environments.
Transportation Research Procedia, vol. 24, 2017, pp. 97–104. [Link]
10.1016/[Link].2017.05.074.
[8] Telega A., Telega I., Bieda A.: Measuring walkability with GIS-methods overview
and new approach proposal. Sustainability, vol. 13(4), 2021, 1883. [Link]
org/10.3390/su13041883.
[9] Ewing R., Handy S., Brownson R.C., Clemente O., Winston E.: Identifying
and measuring urban design qualities related to walkability. Journal of Physical
Activity and Health, vol. 3(1), 2006, pp. s223–s240. [Link]
jpah.3.s1.s223.
[10] Ewing R., Hajrasouliha A., Neckerman K.M., Purciel-Hill M., Greene W.: Street-
scape features related to pedestrian activity. Journal of Planning Education and
Research, vol. 36(1), 2016, pp. 5–15. [Link]
[11] Lee C., Moudon A.V.: Physical activity and environment research in the health
field: Implications for urban and transportation planning practice and research.
Journal of Planning Literature, vol. 19(2), 2004, pp. 147–181. [Link]
10.1177/​0885412204267680.
[12] Ewing R., Handy S.: Measuring the unmeasurable: Urban design qualities related
to walkability. Journal of Urban Design, vol. 14(1), 2009, pp. 65–84. [Link]
org/​10.1080/13574800802451155.
[13] Ewing R., Clemente O., Neckerman K.M., Purciel-Hill M., Quinn J.W., Run-
dle A.: Measuring Urban Design: Metrics for Livable Places. Metropolitan Plan-
ning + Design, Island Press, Washington – Covelo – London 2013. [Link]
org/​10.5822/978-1-61091-209-9.
[14] Anguelov D., Dulong C., Filip D., Frueh Ch., Lafon S., Lyon R., Ogale A.,
Vincent L., Weaver J.: Google Street View: Capturing the world at street level.
Computer, vol. 43(6), 2010, pp. 32–38. [Link]
[15] Nagata S., Nakaya T., Hanibuchi T., Amagasa S., Kikuchi H., Inoue S.: Objec-
tive scoring of streetscape walkability related to leisure walking: Statistical modeling
approach with semantic segmentation of Google Street View images. Health & Place,
vol. 66, 2020, 102428. [Link]
[16] Yin L., Wang Z.: Measuring visual enclosure for street walkability: Using ma-
chine learning algorithms and Google Street View imagery. Applied Geography,
vol. 76, 2016, pp. 147–153. [Link]
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 29

[17] Steinmetz-Wood M., Velauthapillai K., O’Brien G., Ross N.A.: Assessing the
micro-scale environment using Google Street View: The Virtual Systematic Tool
for Evaluating Pedestrian Streetscapes (Virtual-STEPS). BMC Public Health,
vol. 19(1), 2019, 1246. [Link]
[18] Li X., Santi P., Courtney T.K., Verma S.K., Ratti C.: Investigating the association
between streetscapes and human walking activities using Google Street View and
human trajectory data. Transactions in GIS, vol. 22(4), 2018, pp. 1029–1044.
[Link]
[19] Koo B.W., Guhathakurta S., Botchwey N.: How are neighborhood and street-­level
walkability factors associated with walking behaviors? A big data approach using
street view images. Environment and Behavior, vol. 54(1), 2022, pp. 211–241.
[Link]
[20] Lu Y.: The association of urban greenness and walking behavior: Using Google
Street View and deep learning techniques to estimate residents’ exposure to ur-
ban greenness. International Journal of Environmental Research and Public
Health, vol. 15(8), 2018, 1576. [Link]
[21] Yang Y., He D., Gou Z., Wang R., Liu Y., Lu Y.: Association between street green-
ery and walking behavior in older adults in Hong Kong. Sustainable Cities and
Society, vol. 51, 2019, 101747. [Link]
[22] Ki D., Lee S.: Analyzing the effects of Green View Index of neighborhood streets on
walking time using Google Street View and deep learning. Landscape and Urban
Planning, vol. 205, 2021, 103920. [Link]
103920.
[23] Yang L., Ao Y., Ke J., Lu Y., Liang Y.: To walk or not to walk? Examining non-­
linear effects of streetscape greenery on walking propensity of older adults. Journal
of Transport Geography, vol. 94, 103099. [Link]
2021.​103099.
[24] Yang L., Liu J., Liang Y., Lu Y., Yang H.: Spatially varying effects of street green-
ery on walking time of older adults. ISPRS International Journal of Geo-Infor-
mation, vol. 10(9), 2021, 596. [Link]
[25] Yin L., Cheng Q., Wang Z., Shao Z.: ‘Big data’ for pedestrian volume: Exploring
the use of Google Street View images for pedestrian counts. Applied Geography,
vol. 63, 2015, pp. 337–345. [Link]
[26] Zhou H., He S., Cai Y., Wang M., Su S.: Social inequalities in neighborhood visual
walkability: Using street view imagery and deep learning technologies to facilitate
healthy city planning. Sustainable Cities and Society, vol. 50, 2019, 101605.
[Link]
[27] Fonseca F., Ribeiro P.J.G., Conticelli E., Jabbari M, Papageorgiou G., Ton-
delli S., Ramos R.A.R.: Built environment attributes and their influence on walk-
ability. International Journal of Sustainable Transportation, vol. 16(7), 2022,
pp. 660-679. [Link]
30 G. Biswas, T.K. Roy

[28] Shumi S., Zuidgeest M.H.P., Martinez J.A., Efroymson D., van Maarse-
veen M.F.A.M.: Understanding the relationship between walkability and quality-­of-­
life of women garment workers in Dhaka, Bangladesh. Applied Research Quality
Life, vol. 10(2), 2015, pp. 263–287. [Link]
[29] Siddiqua F., Kabir S., Taher M.T.: Assessing walkability of planned and his-
torical streetscape of urban Dhaka. AIUB Journal of Science and Engineering,
vol. 16(1), 2017, pp. 19–28. [Link]
[30] Al Mamun M.M., Begum A.A., Mowla Q.A.: Walkability for urban sustainability:
Study of pedestrian traffic in Chittagong. Jahangirnagar University Plannind Re-
view, vol. 16, 2018, pp. 87–102. [Link]
[31] Nasrin S., Afifah F.: Walkability assessment tool for a developing country.
IOP Conference Series: Materials Science and Engineering, vol. 527(1), 2019,
012073. [Link]
[32] Al Noman A., Sharna F.K.: An overview of pedestrian service relevant standards and
guidelines: Correlative approaches of international examples with existing policies of
Bangladesh. Bangladesh Institute of Planners (BIP), November 2019, pp. 44–51.
[33] Moniruzzaman M.: Sustainable and inclusive transport development of Khulna
City. Khulna City Corporation, Khulna 2013.
[34] Kowaleski-Jones L., Zick C., Smith K.R., Brown B., Hanson H., Fan J.: Walk-
able neighborhoods and obesity: Evaluating effects with a propensity score approach.
SSM – Population Health, vol. 6, 2018, pp. 9–15. [Link]
[Link].​2017.11.005.
[35] Leather J., Fabian H., Gota S., Mejia A.: Walkability and Pedestrian Facilities in
Asian Cities: State and Issues. ADB Sustainable Development Working Paper
Series, no. 17, Asian Development Bank, 2011.
[36] Blečić I., Congiu T., Fancello G., Trunfio G.A.: Planning and design support
tools for walkability: A guide for urban analysts. Sustainability, vol. 12(11), 2020,
4405. [Link]
[37] Hasan M.M., Oh J.S., Kwigizile V.: Exploring the trend of walkability measures
by applying hierarchical clustering technique. Journal of Transport & Health,
vol. 22, 2021, 101241. [Link]
[38] Rafiemanzelat R., Emadi M.I., Kamali A.J.: City sustainability: the influence of
walkability on built environments. Transportation Research Procedia, vol. 24,
2017, pp. 97–104. [Link]
[39] Arellana J., Saltarín M., Larrañaga A.M., Alvarez V., Henao C.A.: Urban walk-
ability considering pedestrians’ perceptions of the built environment: A 10-year re-
view and a case study in a medium-sized city in Latin America. Transport Reviews,
vol. 40(2), 2020, pp. 183–203. [Link]
[40] Oreskovic N.M., Roth P., Charles S.L., Tsigaridi D., Shepherd K., Nel-
son K.P., Bar M.: Attributes of form in the built environment that influence per-
ceived walkability. Journal of Architectural and Planning Research, vol. 31(3),
2014, pp. 218–232. [Link]
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 31

[41] Zhu W., Nedovic-Budic Z., Olshansky R.B., Marti J., Gao Y., Park Y., McAu-
ley E., Chodzko-Zajko W.: Agent-based modeling of physical activity behavior and
environmental correlations: An introduction and illustration. Journal of Physical
Activity and Health, vol. 10(3), 2013, pp. 309–322. [Link]
10.3.309.
[42] Lotfi S., Koohsari M.J.: Neighborhood walkability in a city within a developing
country. Journal of Urban Planning and Development, vol. 137(4), 2011,
pp. 402–408. [Link]
[43] Fan P., Wan G., Xu L., Park H., Xie Y., Liu Y., Yue W., Chen J.: Walkability in ur-
ban landscapes: A comparative study of four large cities in China. Landscape Ecol-
ogy, vol. 33(2), 2018, pp. 323–340. [Link]
[44] Ramakreshnan L., Fong C.S., Sulaiman N.M., Aghamohammadi N.: Motiva-
tions and built environment factors associated with campus walkability in the trop-
ical settings. Science of the Total Environment, vol. 749, 2020, 141457. https://
[Link]/10.1016/[Link].2020.141457.
[45] Khder H.M., Mousavi S.M., Khan T.H.: Impact of street’s physical elements on
walkability: A case of Mawlawi Street in Sulaymaniyah, Iraq. International Jour-
nal of Built Environment and Sustainability, vol. 3(1), 2016, pp. 18–26. https://
[Link]/10.11113/ijbes.v3.n1.106.
[46] Ye Y., Zeng W., Shen Q., Zhang X., Lu Y.: The visual quality of streets: A human-­
centred continuous measurement based on machine learning algorithms and street
view images. Environment and Planning B: Urban Analytics and City Science,
vol. 46(8), 2019, pp. 1439–1457. [Link]
[47] Ma X. Ma C., Wu C., Xi Y., Yang R., Peng N., Zhang C., Ren F.: Measuring
human perceptions of streetscapes to better inform urban renewal: A perspective of
scene semantic parsing. Cities, vol. 110, 2021, 103086. [Link]
[Link].2020.103086.
[48] Dai L., Zheng C., Dong Z., Yao Y., Wang R., Zhang X., Ren S., Zhang J., Song X.,
Guan Q.: Analyzing the correlation between visual space and residents’ psychol-
ogy in Wuhan, China using street-view images and deep-learning technique. City
and Environment Interactions, vol. 11, 2021, 100069. [Link]
[Link].2021.100069.
[49] Tao Y., Wang Y., Wang X., Tian G., Zhang S.: Measuring the correlation between
human activity density and streetscape perceptions: An analysis based on Baidu
street view images in Zhengzhou, China. Land, vol. 11(3), 2022, 400. [Link]
org/​10.3390/land11030400.
[50] Huang G., Yu Y., Lyu M., Sun D., Zeng Q., Bart D.: Using Google Street View
panoramas to investigate the influence of urban coastal street environment on vi-
sual walkability. Environmental Research Communications, vol. 5(6), 2023,
065017. [Link]
[51] Dong H.: Does walkability undermine neighbourhood safety? Journal of Urban De-
sign, vol. 22(1), 2017, pp. 59–75. [Link]
32 G. Biswas, T.K. Roy

[52] Reisi M., Nadoushan M.A., Aye L.: Local walkability index: Assessing built en-
vironment influence on walking. Bulletin of Geography Socio-economic Series,,
vol. 46(46), 2019, pp. 7–21. [Link]
[53] Adkins A., Dill J., Luhr G., Neal M.: Unpacking walkability: Testing the influence
of urban design features on perceptions of walking environment attractiveness. Jour-
nal of Urban Design, vol. 17(4), 2012, pp. 499–510. [Link]
13574809.2012.706365.
[54] Moayedi F., Zakaria R., Bigah Y., Mustafar M., Che Puan O., Zin I.S., Klufal-
lah M.M.A.: Conceptualising the indicators of walkability for sustainable transpor-
tation. Jurnal Teknologi, vol. 65(3), pp. 85–90, 2013. [Link]
jt.v65.2151.
[55] He K., Zhang X., Ren S., Sun J.: Deep residual learning for image recognition.
[in:] 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR
2016), Las Vegas, Nevada, USA, 27–30 June 2016, IEEE, Poscataway 2016,
pp. 770–778. [Link]
[56] Badrinarayanan V., Kendall A., Cipolla R.: SegNet: A deep convolutional en-
coder-decoder architecture for image segmentation. IEEE Transactions on Pattern
Analysis and Machine Intelligence, vol. 39(12), 2017, pp. 2481–2495. https://
[Link]/10.1109/TPAMI.2016.2644615.
[57] Chen L.-C., Papandreou G., Kokkinos I., Murphy K., Yuille A.L.: DeepLab:
Semantic image segmentation with deep convolutional nets, atrous convolution,
fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine In-
telligence, vol. 40(4), 2018, pp. 834–848. [Link]
2699184.
[58] Diwan T., Anirudh G., Tembhurne J.V.: Object detection using YOLO: Challenges,
architectural successors, datasets and applications. Multimedia Tools and Applica-
tions, vol. 82, 2023, pp. 9243–9275. [Link]
[59] Montgomery J.: Making a city: urbanity, vitality and urban design. Jour-
nal of Urban Design, vol. 3(1), 1998, pp. 93–116. [Link]
13574809808724418.
[60] Li X., Ghosh D.: Associations between body mass index and urban ‘Green’ streetscape
in Cleveland, Ohio, USA. International Journal of Environmental Research and
Public Health, vol. 15(10), 2018, 2186. [Link]
[61] Villeneuve P.J. et al.: Comparing the normalized difference vegetation index with
the google street view measure of vegetation to assess associations between green-
ness, walkability, recreational physical activity, and health in Ottawa, Canada. In-
ternational Journal of Environmental Research and Public Health, vol. 15(8),
2018, 1719. [Link]
[62] Dong R., Zhang Y., Zhao J.: How green are the streets within the sixth ring road
of Beijing? An analysis based on tencent street view pictures and the green view
index. International Journal of Environmental Research and Public Health,
vol. 15(7), 2018, 1367. [Link]
Measuring Objective Walkability from Pedestrian-Level Visual Perception... 33

[63] Zhang J., Heng C.K., Malone-Lee L.C., Hii D.J.C., Janssen P., Leung K.S.,
Tan B.K.: Evaluating environmental implications of density: A comparative case
study on the relationship between density, urban block typology and sky exposure.
Automation in Construction, vol. 22, 2012, pp. 90–101. [Link]
[Link].2011.06.011.
[64] Tang J., Long Y.: Measuring visual quality of street space and its temporal variation:
Methodology and its application in the Hutong area in Beijing. Landscape and Urban
Planning, vol. 191, 2019, 103436. [Link]
2018.09.015.
[65] Molaei P., Tang L., Hardie M.: Measuring walkability with street connectivity
and physical activity: A case study in Iran. World, vol. 2(1), 2021, pp. 49–61.
[Link]
[66] Edirisinghe T., Hewawasam D.C.: An investigation of the relationship of street-
scape visual enclosure and the pedestrian movement in selected case studies in Co-
lombo. Journal of Engineering and Architecture, vol. 8(1), 2020, pp. 10–30.
[Link]
[67] Imamoglu Ç.: Complexity, liking and familiarity: architecture and non-architec-
ture turkish students’ assessments of traditional and modern house facades. Jour-
nal of Environmental Psychology, vol. 20(1), 2000, pp. 5–16. [Link]
10.1006/JEVP.1999.0155.
[68] Stamps A.E.: Advances in visual diversity and entropy. Environment and Plan-
ning B: Planning and Design, vol. 30(3), 2003, pp. 449–463. [Link]
10.1068/B12986.
[69] Tucker C., Ostwald M.J., Chalup S.K.: A method for the visual analysis of street-
scape character using digital image processing. [in:] Bromberek Z. (ed.), Contexts
of Architecture: Proceedings of the 38th Annual Conference of the Architectural Sci-
ence Association ANZAScA and the International Building Performance Simulation
Association – Australasia, Launceston, 10–12 November 2004, School of Architec-
ture, University of Tasmania, Locked Bag, Launceston 2004, pp. 134–141.
[70] Adams M.A., Phillips C.B., Patel A., Middel A.: Training computers to see the
built environment related to physical activity: Detection of microscale walkabili-
ty features using computer vision. International Journal of Environmental
Research and Public Health, vol. 19(8), 2022, 4548. [Link]
ijerph19084548.
[71] Lichstein J.W., Simons T.R., Franzreb K.E.: Landscape effects on breeding song-
bird abundance in managed forests. Ecological Applications, vol. 12(3), 2002,
pp. 836–857. [Link]
[72] Fourie P.J., Jittrapirom P., Binder R.B., Tobey M.B., Medina S.O., Mahesh-
wari T., Yamagata Y.: Modeling and Design of Smart Mobility Systems. [in:] Ya-
magata Y., Yang P.P.J. (eds.), Urban Systems Design: Creating Sustainable Smart
Cities in the Internet of Things Era, Elsevier, 2020, pp. 163–197. [Link]
org/10.1016/B978-0-12-816055-8.00006-3.
34 G. Biswas, T.K. Roy

[73] Agarwal P., Burgard W., Spinello L.: Metric localization using Google Street
View. [in:] IROS: IEEE/RSJ International Conference on Intelligent Robots and
Systems: September 28-October 2, 2015, Hamburg, Germany, IEEE, Piscataway
2015, pp. 3111–3118. [Link]
[74] Dhillon A., Verma G.K.: Convolutional neural network: a review of models, meth-
odologies and applications to object detection. Progress in Artificial Intelligence,
vol. 9(2), 2020, pp. 85–112. [Link]
[75] Zaeemzadeh A., Rahnavard N., Shah M.: Norm-preservation: Why residu-
al networks can become extremely deep? IEEE Transactions on Pattern Analy-
sis and Machine Intelligence, vol. 43(11), 2021, pp. 3980–3990. [Link]
org/10.1109/TPAMI.2020.2990339.
[76] Lee K.K.: Developing and implementing the Active Design Guidelines in New
York City. Health & Place, vol. 18(1), 2012, pp. 5–7. [Link]
[Link].2011.09.009.
[77] Sarwinda D., Paradisa R. H., Bustamam A., Anggia P.: Deep learning in image
classification using Residual Network (ResNet) variants for detection of colorectal
cancer. Procedia Computer Science, vol. 179, 2021, pp. 423–431. [Link]
org/10.1016/[Link].2021.01.025.
[78] Cerin E., Saelens B.E., Sallis J.F., Frank L.D.: Neighborhood environment walkabil-
ity scale: Validity and development of a short form. Medicine & Science in Sports
& Exercise, vol. 38(9), 2006, pp. 1682–1691. [Link]
0000227639.83607.4d.
[79] Hall C.M., Ram Y.: Walk score® and its potential contribution to the study of active
transport and walkability: A critical and systematic review. Transportation Re-
search Part D: Transport and Environment, vol. 61(part B), 2018, pp. 310–324.
[Link]
[80] Efroymson D. et al.: Moving Dangerously, Moving Pleasurably: Improving Walk-
ability in Dhaka: Using a BRT Walkability Strategy to Make Dhaka’s Transportation
Infrastructure Pedestrian-Friendly. 2012. [Link]
BRT_Walkability_Strategy_Summary_final.pdf.