Spatial-aware correlation filters with adaptive weight maps for visual tracking

Abstract Recently discriminative correlation filter (DCF) methods demonstrate excellent performance for visual tracking. These methods, however, often suffer from boundary effects, especially when the target search area is small. To mitigate boundary effects, a larger target search area is chosen, which, however, introduces many background pixels so that the tracking filter is contaminated by the introduced background pixels and the tracking performance is degraded. In order to alleviate the effects of the background pixels, this paper proposes a spatial-aware adaptive weight map, which wisely assigns large weights to pixels of the target and small weights to pixels in the background. Such desired weight map is adaptively generated by combining the target likelihood, which quantitatively measures whether a pixel belongs to the target or the background, and prior spatial weights of pixels. By integrating the spatial-aware adaptive weight map into the DCF framework, the obtained DCF tracking method can achieve more precise target location and suffer from less tracking drift than those conventional tracking methods. Moreover, we compute a confidence score from the response map and train the tracking filter only in the high-confidence situation. This high-confidence updating strategy can effectively avoid the tracking filter corruption problem when the target is severely occluded and the target search area is mainly filled with pixels of the background. The proposed tracking method is compared with some state-of-the-art methods through extensive experiments on four benchmark datasets, which confirm the performance superiority of the proposed one.