Outdoor People Tracking
Abstract
We address the problem of automatically detecting and tracking outdoor people. We propose to combine background subtraction based tracking with tracking-by-detection approach in a Kalman filtering framework. For the detection purpose, we use HOG detector, which detects people only in those regions suggested by background subtraction model. Since detectors may give false positives or miss targets, background subtraction is used to complement the detector outcomes.
Keywords
people detection, people tracking, tracking-by-detection, surveillance, Kalman filtering
References
- [1] Q. Zhou, J.K. Aggarwal