IEEE Transactions on Image Processing
In this paper, we propose a simple yet effective object descriptor and a novel tracking algorithm to track a target object accurately. For the object description, we divide the bounding box of a target object into multiple patches and describe them with color and gradient histograms. Then, we determine the foreground weight of each patch to alleviate the impacts of background information in the bounding box. To this end, we perform random walk with restart (RWR) simulation. We then concatenate the weighted patch descriptors to yield the spatially ordered and weighted patch (SOWP) descriptor. For the object tracking, we incorporate the proposed SOWP descriptor into a novel tracking algorithm, which has three components: locator, checker, and scaler (LCS). The locator and the scaler estimate the center location and the size of a target, respectively. The checker determines whether it is safe to adjust the target scale in a current frame. These three components cooperate with one another to achieve robust tracking. Experimental results demonstrate that the proposed LCS tracker achieves excellent performance on recent benchmarks.
We evaluate the performance of the proposed tracker on the Online Tracking Benchmark (OTB) datasets.
Han-Ul Kim, and Chang-Su Kim, "Locator-Checker-Scaler Object Tracking Using Spatially Ordered and Weighted Patch Descriptor," IEEE Transactions on Image Processing, Aug. 2017. [pdf] [source code (coming soon)] [bibex]