Object tracking algorithms - additional materials
Hi!
As I mentioned in the welcome lecture, the goal of the course is to present only the basic intuition of
the algorithms. If you want more information about them, you can access the following links
BOOSTING
cv::TrackerBoosting Class
Reference: [Link]
Real-Time Tracking via On-line
Boosting: [Link]
MIL
cv::TrackerMIL Class
Reference: [Link]
Visual tracking with online multiple instance
learning: [Link]
content/uploads/2014/09/[Link]
KCF
cv::TrackerKCF Class
Reference: [Link]
Geometric affine transformation estimation via correlation
filter for visual
tracking: [Link]
EnKCF: Ensemble of Kernelized Correlation Filters for High-
Speed Object
Tracking: [Link]
of-kernelized-correlation-filters-for-high-speed-object-
tracking/1
High-Speed Tracking with Kernelized Correlation
Filters: [Link]
CSRT
cv::TrackerCSRT Class
Reference: [Link]
Discriminative Correlation Filter with Channel and Spatial
Reliability: [Link]
Faster RCNN Detection Based OpenCV CSRT Tracker Using
Drone
Data: [Link]
MEDIANFLOW
cv::TrackerMedianFlow Class
Reference: [Link]
Evaluation of Visual Tracking Algorithms for Embedded
Devices: [Link]
Forward-Backward Error: Automatic Detection of Tracking
Failures: [Link]
TLD
cv::TrackerTLD Class
Reference: [Link]
Tracking-Learning-
Detection: [Link]
[Link]
Real-Time Pedestrian Tracking and Counting with
TLD: [Link]
Time_Pedestrian_Tracking_and_Counting_with_TLD
An improved TLD target tracking algorithm based on the
variable-scale, compressing
tracking: [Link]
scale_compressing_tracking
MOSSE
c v::TrackerMOSSE Class
Reference: [Link]
Visual Object Tracking using Adaptive Correlation
Filters: [Link]
GOTURN
cv::TrackerGOTURN Class
Reference: [Link]
GOTURN : Deep Learning based Object
Tracking: [Link]
based-object-tracking/
Learning to Track at 100 FPS with Deep Regression
Networks: [Link]
VOT 2014
dataset: [Link]
COMPARISON BETWEEN ALGORITHMS
Comparison of tracking algorithms implemented in
OpenCV: [Link]
[Link]/articles/matecconf/pdf/2016/39/matecconf_cscc2016_04031.pdf
Comparing state of the art Region of Interest
trackers: [Link]
of-the-art-region-of-interest-trackers-906ba420e80d
OpenCV Object
Tracking: [Link]
object-tracking/
Object Tracking using OpenCV
(C++/Python): [Link]
using-opencv-cpp-python/
MEANSHIFT and CAMSHIFT
Meanshift and
Camshift: [Link]
Meanshift and Camshift: [Link]
[Link]/en/latest/py_tutorials/py_video/py_meanshift/py_meanshift.html
MEANSHIFT
TRACKING: [Link]
Mean Shift: A Robust Approach Toward Feature Space
Analysis: [Link]
Track objects with Camshift using
OpenCV: [Link]
camshift-using-opencv/
Learning OpenCV 3 Computer Vision with Python - Second
Edition: [Link]
Object Tracking Using Improved CAMShift Algorithm
Combined with Motion
Segmentation: [Link]
Computer Vision Face Tracking for Use in Perceptual User
Interface: [Link]
1.0.0_org/docs/papers/[Link]
OPTICALFLOW (SPARSE AND DENSE)
Evaluation Datasets: [Link]
Taylor Series as
Approximations: [Link]
title=Taylor_Series_as_Approximations
Introduction to Motion Estimation with Optical
Flow: [Link]
Optical
Flow: [Link]
Optical flow: [Link]
A COMBINED CORNER AND EDGE
DETECTOR: [Link]
Harris Corner Detector-An Overview of the Original
Paper: [Link]
overview-of-the-original-paper-cf20c502ab0f
Notes on the Harris
Detector: [Link]
Optical Flow Measurement using Lucas kanade
Method: [Link]
Lucas–Kanade
method: [Link]
Good features to
track: [Link]
Feature Detection: [Link]
beta/modules/imgproc/doc/feature_detection.html#goodfeaturestotrack
Two-Frame Motion Estimation Based on Polynomial
Expansion: [Link]
[Link]/smash/get/diva2:273847/[Link]
Video Segmentation via Object
Flow: [Link]
