Vision-based tracking is a basic elementary task in many computer vision-based applications such as video surveillance and monitoring, sensing and navigation in robotics, video compression, video annotation, and many more. However, reliable recovery of targets and their trajectories in an uncontrolled environment is affected by a wide range of conditions exhibited by the environment such as sudden illumination changes and clutter. This work addresses the problem of (i) combining information from a set of cues in order to obtain reasonably accurate estimates of multiple targets in uncontrolled environments and (ii) a collection of data association methods for cues containing less information for robust tracking through persistent clutter. Specifically, we introduce a novel geometric template constrained data association method for robust tracking of point features, while using the Joint Probabilistic Data Association (JPDA) method for blob cue measurements. Extensive experimental validation of the tracking and the data association framework is presented in the work for several real-world outdoor traffic intersection image sequences.
Bibliographical noteFunding Information:
This work has been supported in part by the National Science Foundation through grant IIS-0219863, Architecture Technology Corporation, the Minnesota Department of Transportation, and the ITS Institute at the University of Minnesota. The authors also thank the reviewers for their useful comments and suggestions.
- Data association
- Expectation maximization
- Measurement error estimation
- Multiple cue combination