Probabilistic Tracking Method Based on the Spatial Bin-Ratio Information

Abstract

We proposed a new similarity measure method which could be used within the framework of probability trackers based on the particle filter to track the object. In the particle filter framework, the state transition model is chosen as the simple second-order auto-regressive mode, and the state measure is chosen as the BBRS (Blocks-Bin-Ratio-Similarity). The BBRS considers both the spatial information and the ratios between bin values of histograms. The simulation experiment was made to compare with the similarity measures based on color-histogram and the Bin-Ratio Similarity, and the tracking results in the videos showed that the BBRS-based similarity measure was more discriminative than the color histogram similarity measure in robustly tracking the object in challenging videos where the appearance and motion are drastically changing over time.

Object Tracking Based on Online Semi-Supervised SVM and Adaptive-Fused Feature

“…Nevertheless, it is prone to neglecting spatial information of the object. To improve the performance of distinguishing objects, we have introduced a modified BRD named the SBRS [14] which is better than the similarity Bhattacharyya and the BRS. We introduce a Modified Similarity SBRS (MSSBRS) which considers not only the spatial structure of the object but also the relation of the bins of the histogram of between the candidate object and the reference object.…”

“…Assume qref with second-order spatiogram [15] d hh is a bin ratio similarity measure that improved the bin ratio dissimilarity [14], which is defined as ; q is a reference histogram set corresponding fragments, and p is a candidate histogram set. The similarity measure between q and p is expressed as  is expressed as…”