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: https://docs.opencv.org/3.4/d1/d1a/classcv_1_1TrackerBoosting.html
Real-Time Tracking via On-line
Boosting: http://www.bmva.org/bmvc/2006/papers/033.pdf
MIL
cv::TrackerMIL Class
Reference: https://docs.opencv.org/3.4/d0/d26/classcv_1_1TrackerMIL.html
Visual tracking with online multiple instance
learning: https://vision.cornell.edu/se3/wp-
content/uploads/2014/09/0fcfd5086e4e9dd86c000000.pdf
KCF
cv::TrackerKCF Class
Reference: https://docs.opencv.org/3.4/d2/dff/classcv_1_1TrackerKCF.html
Geometric affine transformation estimation via correlation
filter for visual
tracking: https://www.sciencedirect.com/science/article/abs/pii/S0925231216305422
EnKCF: Ensemble of Kernelized Correlation Filters for High-
Speed Object
Tracking: https://www.groundai.com/project/enkcf-ensemble-
of-kernelized-correlation-filters-for-high-speed-object-
tracking/1
High-Speed Tracking with Kernelized Correlation
Filters: https://arxiv.org/pdf/1404.7584.pdf
CSRT
cv::TrackerCSRT Class
Reference: https://docs.opencv.org/3.4/d2/da2/classcv_1_1TrackerCSRT.html
Discriminative Correlation Filter with Channel and Spatial
Reliability: https://arxiv.org/pdf/1611.08461.pdf
Faster RCNN Detection Based OpenCV CSRT Tracker Using
Drone
Data: https://www.researchgate.net/publication/339555637_Faster_RCNN_Detection_Based_OpenC
MEDIANFLOW
cv::TrackerMedianFlow Class
Reference: https://docs.opencv.org/3.4/d7/d86/classcv_1_1TrackerMedianFlow.html
Evaluation of Visual Tracking Algorithms for Embedded
Devices: https://www.researchgate.net/publication/317803149_Evaluation_of_Visual_Tracking_Algo
Forward-Backward Error: Automatic Detection of Tracking
Failures: http://kahlan.eps.surrey.ac.uk/featurespace/tld/Publications/2010_icpr.pdf
TLD
cv::TrackerTLD Class
Reference: https://docs.opencv.org/3.4/dc/d1c/classcv_1_1TrackerTLD.html
Tracking-Learning-
Detection: http://vision.stanford.edu/teaching/cs231b_spring1415/papers/Kalal-
PAMI.pdf
Real-Time Pedestrian Tracking and Counting with
TLD: https://www.researchgate.net/publication/328608910_Real-
Time_Pedestrian_Tracking_and_Counting_with_TLD
An improved TLD target tracking algorithm based on the
variable-scale, compressing
tracking: https://www.researchgate.net/publication/322001178_An_improved_TLD_target_tracking_
scale_compressing_tracking
MOSSE
c v::TrackerMOSSE Class
Reference: https://docs.opencv.org/3.4/d0/d02/classcv_1_1TrackerMOSSE.html
Visual Object Tracking using Adaptive Correlation
Filters: https://www.cs.colostate.edu/~draper/papers/bolme_cvpr10.pdf
GOTURN
cv::TrackerGOTURN Class
Reference: https://docs.opencv.org/3.4/d7/d4c/classcv_1_1TrackerGOTURN.html
GOTURN : Deep Learning based Object
Tracking: https://www.learnopencv.com/goturn-deep-learning-
based-object-tracking/
Learning to Track at 100 FPS with Deep Regression
Networks: http://davheld.github.io/GOTURN/GOTURN.pdf
VOT 2014
dataset: https://www.votchallenge.net/vot2014/dataset.html
COMPARISON BETWEEN ALGORITHMS
Comparison of tracking algorithms implemented in
OpenCV: https://www.matec-
conferences.org/articles/matecconf/pdf/2016/39/matecconf_cscc2016_04031.pdf
Comparing state of the art Region of Interest
trackers: https://medium.com/teleidoscope/comparing-state-
of-the-art-region-of-interest-trackers-906ba420e80d
OpenCV Object
Tracking: https://www.pyimagesearch.com/2018/07/30/opencv-
object-tracking/
Object Tracking using OpenCV
(C++/Python): https://www.learnopencv.com/object-tracking-
using-opencv-cpp-python/
MEANSHIFT and CAMSHIFT
Meanshift and
Camshift: https://docs.opencv.org/3.4/d7/d00/tutorial_meanshift.html
Meanshift and Camshift: https://opencv-python-
tutroals.readthedocs.io/en/latest/py_tutorials/py_video/py_meanshift/py_meanshift.html
MEANSHIFT
TRACKING: https://www.bogotobogo.com/python/OpenCV_Python/python_opencv3_mean_shift_t
Mean Shift: A Robust Approach Toward Feature Space
Analysis: https://courses.csail.mit.edu/6.869/handouts/PAMIMeanshift.pdf
Track objects with Camshift using
OpenCV: https://www.geeksforgeeks.org/track-objects-with-
camshift-using-opencv/
Learning OpenCV 3 Computer Vision with Python - Second
Edition: https://subscription.packtpub.com/book/application_development/9781785283840
Object Tracking Using Improved CAMShift Algorithm
Combined with Motion
Segmentation: https://www.researchgate.net/publication/261194641_Object_Tracking_Using_Impr
Computer Vision Face Tracking for Use in Perceptual User
Interface: http://opencv.jp/opencv-
1.0.0_org/docs/papers/camshift.pdf
OPTICALFLOW (SPARSE AND DENSE)
Evaluation Datasets: http://vision.middlebury.edu/flow/data/
Taylor Series as
Approximations: http://www.norsemathology.org/wiki/index.php?
title=Taylor_Series_as_Approximations
Introduction to Motion Estimation with Optical
Flow: https://nanonets.com/blog/optical-flow/#opticalflow
Optical
Flow: https://docs.opencv.org/3.4/d4/dee/tutorial_optical_flow.html
Optical flow: https://en.wikipedia.org/wiki/Optical_flow
A COMBINED CORNER AND EDGE
DETECTOR: http://www.bmva.org/bmvc/1988/avc-88-023.pdf
Harris Corner Detector-An Overview of the Original
Paper: https://medium.com/swlh/harris-corner-detector-an-
overview-of-the-original-paper-cf20c502ab0f
Notes on the Harris
Detector: https://courses.cs.washington.edu/courses/cse576/06sp/notes/HarrisDetector.pdf
Optical Flow Measurement using Lucas kanade
Method: https://research.ijcaonline.org/volume61/number10/pxc3884611.pdf
Lucas–Kanade
method: https://en.wikipedia.org/wiki/Lucas%E2%80%93Kanade_method
Good features to
track: http://www.ai.mit.edu/courses/6.891/handouts/shi94good.pdf
Feature Detection: https://docs.opencv.org/3.0-
beta/modules/imgproc/doc/feature_detection.html#goodfeaturestotrack
Two-Frame Motion Estimation Based on Polynomial
Expansion: http://www.diva-
portal.org/smash/get/diva2:273847/FULLTEXT01.pdf
Video Segmentation via Object
Flow: http://files.is.tue.mpg.de/black/papers/TsaiCVPR2016.pdf