An Adaptive Binning Color Model for Mean Shift Tracking

The mean shift (MS) algorithm for object tracking using color has recently received a significant amount of attention thanks to its effectiveness and efficiency. Most current work, unfortunately, failing to notice that object color is usually very compactly distributed, partitions uniformly the whole color space and thus leads to a large number of void bins and limited capability of representing object color distribution. Also, there lacks a systematic way to determine automatically the number of bins. Aiming to address these problems, this paper presents an adaptive binning color model for MS tracking. First, the object color is analyzed based on a clustering algorithm and, according to the clustering result, the color space of the object is partitioned into subspaces by orthonormal transformation. Then, a color model is defined by considering the weighted number of pixels as well as intra-cluster distribution based on independent component analysis (ICA), and a similarity measure is introduced to evaluate likeness between the reference and the candidate models. Finally, the MS algorithm is developed based on the proposed color model and its computational complexity is analyzed. Experiments show that the proposed algorithm has better tracking performance than the conventional MS algorithm at the cost of moderately increasing computational load.