Problem
Tracking is challenging due to the following factors: deformation, illumination variation, blur&fast motion, background clutter, rotation, scale, boundary effect
History
Tracking methods can be roughly categorized into generative methods and discriminative methods(feature+machine learning). Recently, correlation filter based methods and deep learning methods are dominant.
- Meanshift: density based, ASMS https://github.com/vojirt/asms
- Particle filter: particle based statistical method
- Optical flow: match feature points between neighboring frames
- correlation filter: KCF, DCF, CSK, CN, DSST, SRDCF, ECO. Basic CF methods are sensitive to deformation, fast motion, and boundary effect.
- deep learning: GOTURN, MDNet, TCNN, SiamFC
Two research groups contribute to CF methods most:
- Oxford: https://www.robots.ox.ac.uk/~luca/,
- Linkoping: http://users.isy.liu.se/en/cvl/marda26/
Comparison of Speed and Performance
Survey papers
- Object tracking: A survey, 2006
- Object tracking benchmark, 2015
Benchmark
- OTB50/100: http://cvlab.hanyang.ac.kr/tracker_benchmark/
- VOT2016: http://www.votchallenge.net/vot2016/dataset.html
Challenge
- Visual Object Tracking (VOT) challenge:
http://www.votchallenge.net/challenges.html
VOT2016 has released the code of many trackers: http://votchallenge.net/vot2016/trackers.html - Multiple Object Tracking Challenge (MOT) challenge:
https://motchallenge.net/
Detection based Tracking
Detection based tracking is also named as tracking by detection or multiple object tracking. (MOT Challenge)
TLD (tracking-learning-detection): update tracker and detector during learning
http://personal.ee.surrey.ac.uk/Personal/Z.Kalal/tld.html