Shape context based object recognition and tracking in structured underwater environment

While visual tracking problem has been actively studied in computer vision discipline, recoginition and tracking objects beneath the water surface still remains a challenging problem since this problem open deals with several difficulties: 1) poor light condition 2) limited visibility 3) high turbidity condition 4) lack of benchmark image data, etc. Nevertheless, the importance of vision based capabilities in underwater environment cannot be overstated because, in these days, many underwater robots are guided by vision systems. In this research work, we propose an efficient and accurate method of tracking texture-free objects in underwater environment. The challenge is to segment out and to track interesting objects in the presence of camera motion and scale changes of the objects. We approached this problem with a two phased algorithm: detection phase and tracking phase. In the detection phase, we extract shape context descriptors that used for classifying objects into predetermined interesting targets. In the tracking phase, we resorted to meanshift tracking algorithm based on Bhattacharyya coefficient measurement. The proposed framework is validated with real data sets obtained from a water tank, and we observed promising performance of the algorithm.