Skip to content

I studied 10 tracking algorithms available in opencv, namely BOOSTING, MIL (Multiple Instance Learning), KCF (Kernelized Correlation Filters), TLD (Tracking, learning and detection), MEDIANFLOW, GOTURN, MOSSE (Minimum Output Sum of Squared Error), CSRT (Channel and Spatial Reliability), Optical Flow. Two other tracking algorithms (Sift and surf)…

Notifications You must be signed in to change notification settings

UtkarshBhardwaj007/Tracking-Algorithms-Comparative-study-

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Tracking-Algorithms-Comparative-study

I studied 10 tracking algorithms available in opencv, namely BOOSTING, MIL (Multiple Instance Learning), KCF (Kernelized Correlation Filters), TLD (Tracking, learning and detection), MEDIANFLOW, GOTURN, MOSSE (Minimum Output Sum of Squared Error), CSRT (Channel and Spatial Reliability), Optical Flow. Two other tracking algorithms (Sift and surf) were found to be patented. So testing on these couldn't be done.

I conducted test flights and implemented these algorithms on a video taken from a drone at a height of 40m and tracked humans in the field of view.

Just specify the path to the video file in the code and it becomes usable.

About

I studied 10 tracking algorithms available in opencv, namely BOOSTING, MIL (Multiple Instance Learning), KCF (Kernelized Correlation Filters), TLD (Tracking, learning and detection), MEDIANFLOW, GOTURN, MOSSE (Minimum Output Sum of Squared Error), CSRT (Channel and Spatial Reliability), Optical Flow. Two other tracking algorithms (Sift and surf)…

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages