Abstract
In this paper, we tackle the problem of ob ject detection and tracking in a new and challenging domain of wide area surveillance. This problem poses several challenges: large camera motion, strong parallax, large number of moving ob jects, small number of pixels on target, sin- gle channel data and low framerate of video. We propose a method that overcomes these challenges and evaluate it on CLIF dataset. We use me- dian background modeling which requires few frames to obtain a work- able model. We remove false detections due to parallax and registration errors using gradient information of the background image. In order to keep complexity of the tracking problem manageable, we divide the scene into grid cells, solve the tracking problem optimally within each cell us- ing bipartite graph matching and then link tracks across cells. Besides tractability, grid cells allow us to define a set of local scene constraints such as road orientation and ob ject context. We use these constraints as part of cost function to solve the tracking problem which allows us to track fast-moving ob jects in low framerate videos. In addition to that, we manually generated groundtruth for four sequences and performed quantitative evaluation of the proposed algorithm.