International Journal of Computer Science Issues

More than a traditional journal...

In this paper, we have addressed a quite researched problem in vision for tracking objects in realistic scenarios containing complex situations. Our framework comprises of four phases: object detection and feature extraction, tracking event detection, integrated statistical and cognitive modules, and object tracker. The objects are detected using fused background subtraction approach along with feature computation. Next, the tracking events are inferred by finding spatial occupancy of moving objects. Third module is the key to proposed approach and the motivation is to tackle the tracking problem by axiomatizing and reasoning human-tracking abilities with associated weights. Each object contains a unique identity and a data structure of cognitive and statistical attributes whilst satisfying the global constraints of continuity during motion. Consequently, the results are linked with Kalman filter based tracker to estimate the trajectories of moving objects. We show that combining cognitive and statistical information gives a straightforward way to interpret and disambiguate the uncertainties occurred due to conflicted situations in tracking. The performance of the proposed approach is demonstrated on a set of videos representing various challenges. Besides, quantitative evaluation with annotated ground truth is also presented.