Pixel-Wise Spatial Pyramid-Based Hybrid Tracking

In this paper, we propose a novel tracking algorithm that combines complementary tracking modules with a new object representation model to balance between stability and adaptivity. To reduce the update error of online tracking, we present three complementary modules (a stable module, a soft stable module, and an adaptive module) and fuse them by using a biased multiplicative criterion. The combination of those modules not only facilitates the accurate location of the tracked object but also makes our tracker adaptive to appearance change. For objection representation, we present an appearance model named pixel-wise spatial pyramid (PSP), which employs pixel feature vector to combine several pixel characteristics. During the updating process, we update the codebook by using the reserved pixel feature vectors that are selected by a distance-based scheme. Then, we generate an evolving target representation by using a hybrid feature map that consists of the reserved pixel vectors and antipart of the previous hybrid feature map. Numerous experiments on various challenging image sequences demonstrate that the proposed algorithm performs favorably against several state-of-the-art algorithms, especially for drastic appearance change.