we proposed two types of accidents—

accidents involving damaged cars and

accidents involving overturned cars—

and developed three different design methods for comparing vehicles involved in accidents involving
damaged cars.

Application of a Model that Combines the

YOLOv3
Object Detection Algorithm and Canny Edge
Detection Algorithm to Detect Highway
Accidents
Motivation:
According to World Health Organization statistics [13], vehicular accidents result in about
1.35 million deaths and 20 to 50 million people becoming injured annually. Two factors that
contribute to the high number of deaths are delays in seeking medical treatment and
secondary accidents (multiple-vehicle accidents). Delays in seeking medical attention refer
to the time taken to send an injured victim to the emergency room being too long, due to
problems including delayed accident reporting, erroneously reported accident locations, and
misjudgment of accident severity. Secondary accidents mainly occur when a driver behind
an accident scene is unable to react in a timely manner. Traffic accidents in Taiwan are
classified as Type A1, Type A2, and Type A3 [14]. Type A1 accidents are those that result in
death on the spot or within 24 h (as shown in Table 1); Type A2 accidents are those that
result in injuries, or death after 24 h; Type A3 accidents are those that result in property
damage, but no injuries. Driver safety has always been an important issue.

Traffic accidents not only lead to traffic congestion, but also the loss of lives and property.
Due to higher car speeds, highway accidents, in particular, differ significantly from those
occurring on other road types in terms of driver characteristics and accident types, as well
as the creation of more serious impacts. In the event of a serious accident, the driver is
unable to call for help on his or her own, and passersby pay no attention to the accident,
especially on highways where other drivers will not stop to call for help. This could
regrettably result in delays in victims’ medical treatment. The implementation of a robust
accident detection system will alleviate the aforementioned problems.

Goal
In this study, the severity of an accident was determined by classifying accidents based on
whether a car is damaged or has overturned. Accidents involving overturned cars, in which a
large impact upon collision causes a car to destabilize and overturn, are more likely to
become fatal and lead to higher death rates as the driver may be flung out of the car or
become stuck inside. This study on accident detection was conducted in the context of
highways. Due to higher car speeds on highways relative to other road types, there are
stricter requirements with regard to the timeliness of object detection.

More specifically,
the condition of a car can be categorized into one of the following three types:
1. Class A: vehicle A car without any damage is defined as a vehicle.
2. Class B: damaged car A car with its hood, bumper, headlights, and other front or back
parts damaged, due to an accident to the point of deformity and becomes different from a
normal car, is defined as a damaged car. Accidents that cause defects in the cars involved
are minor and have a lower injury rate.
3. Class C: overturned car A car that overturns, due to a serious accident involving only itself
(single-vehicle collision) or a collision with another car, is defined as an overturned car. In
either case, the high speed of the car upon impact is great enough to structurally destabilize
and overturn the car. Consequently, drivers become stuck inside, and this type of accident
has a high death rate.

Big Data Analytics for Processing Real-time

Unstructured Data from CCTV in Traffic
Management
Object Detection:

2) Multiple-object (vehicle) Sensing: To accurately count the traffic flow, the Vehicle Counting
System needs to be capable of sensing multiple objects and it will be classified based their type
of vehicles with multiple detections [11].
3) Vehicle Classification: In the real-world scenario, there will be many types of objects picked
up by the camera. This data is important to give the feedbacks for the authorities to know the
priority based on this data [11].
4) Anomaly Detection: In the real system, we also can detect the real time anomaly detection
such as a traffic jam and illegal parking. This system can improve the quality of traffic
management and hopefully it can change the people’s behavior in using the public roads [11].

Fig. 2. Object detection with deep learning.

Data generated by CCTV is in unstructured form. It is video or image type of data. Stream data from CCTV displays
only captured activity without understanding what is happening in real situations. Deep learning is the newest
technology to understand images. It can recognize the object and understand the situation. Deep learning is not only
able to recognize objects in traffic but also in other domains such as railway stations, plate recognition, fire
detection, traffic incidents, Fight events and others [2][3][4][5][6]. Several deep learning algorithms are AE, CNN,
DBN, LSTM, RBM, VAE, GAN and RNN [7].
Introduction:

 Video surveillance systems are been used for security monitoring, anomaly detection, traffic
monitoring and many other purposes.
 Video surveillance systems have decreased the need of human presence to monitor activities
captured by video cameras.
 And also one of the advantages of visual surveillance systems is videos can been stored and
analyzed for future reference.

 Road accident detection and vehicle behavior analysis is of great interest to the research
community in intelligent transportation systems.
 There is one death every four minutes due to road accidents in the developing nations [Sinnu].
 The increasing number of vehicles on road will even worsen the problem of road accidents.
 Road Accident are one of the leading causes of death or people got injured globally.
 This is of deep concern to the entire humanity.
 With the increase in number of vehicles in the country vehicle detection is an important in road
traffic management system.
 Different traffic accident causes such as vehicle over speeding, wrong way driving, collision and
accident can be detected by CCTV installed on roads.

Video synopsis is a technique used to browse surveillance videos in an easy and fast manner [1]. It aims to provide a
summarized video by dropping redundant frames from it. Video synopsis differs from other summarization
techniques in a way that it provides activity-based video shortening instead of frame-based video shortening. So, it
provides detailed video analysis.

Video synopsis alleviates browsing videos for long and shortens the original video. It is important because most of
the videos contain spatiotemporal repetitiveness where the same kind of activities occurs for a long period. Spatial
information refers to video frame changes on time. Video synopsis uses activity as a pre-processing unit instead of
frames [2].It trends to obtain out the best rearrangement of activities and display most of the important activities in
the shortest period of time.

We work on accident detection from a surveillance system which is very needful to the user who wants to monitor
the events. Researchers from both academy and industries use artificial intelligence and image processing techniques
to improve automated detection techniques, however, the scope of today's technology remains challenging to use
them inside the world. Recently, deep learning methods have been extended to various computer vision activities
such as scene classification, object detection, segmentation, action recognition, etc.
How to efficiently detect traffic accidents, mainly including vehicle collisions, is one of the important problems for
intelligent transportation systems. Since vision can provide a large amount of traffic information, it is an economic
way for automatic traffic accident detection. However, it is still a challenging task.

Search About it: Used Darknet Framework with yolo