Conferences in Research and Practice in Information Technology
  

Online Version - Last Updated - 20 Jan 2012

 

 
Home
 

 
Procedures and Resources for Authors

 
Information and Resources for Volume Editors
 

 
Orders and Subscriptions
 

 
Published Articles

 
Upcoming Volumes
 

 
Contact Us
 

 
Useful External Links
 

 
CRPIT Site Search
 
    

Jointly Compatible Pair Linking for Visual Tracking with Probabilistic Priors

Reid, R.

    Video sequences of real-world situations are often difficult to track with machine vision. Scenes frequently contain visual clutter, repetitive textures and occlusions that make online visual feature tracking difficult. If the camera is allowed to shake or moving objects are present, the exponential search-space of potential feature matches rapidly becomes intractable for real-time applications. In this paper we introduce "Jointly Compatible Pair Linking" (JCPL), an algorithm that efficiently and deterministically identifies the most globally consensual set of feature-measurement matches in tracking problems with probabilistic priors. We demonstrate JCPL as part of a two-stage visual tracking algorithm, showing it correctly resolving significant matching ambiguities in sequences with highly dynamic camera motion while robustly ignoring moving scene objects. In these experiments we show JCPL and the two-stage tracker evaluating a fixed number of tests in an exponential search-space. In one experiment JCPL tested less than 1/200th of the total search space and executed 4.6 times faster than the current gold-standard algorithm "Joint Compatibility Branch and Bound" (JCBB). Given highly ambiguous sequences we show JCPL tracking successfully while standard JCBB chooses incorrect matches and fails. Throughout our experiments the number of costly image matching operations are minimised, where in a typical sequence only 20.4% of the full image matching operations are required.
Cite as: Reid, R. (2011). Jointly Compatible Pair Linking for Visual Tracking with Probabilistic Priors. In Proc. Australasian Computer Science Conference (ACSC 2011) Perth, Australia. CRPIT, 113. Mark Reynolds Eds., ACS. 35-42
pdf (from crpit.com) pdf (local if available) BibTeX EndNote GS