Research on scale adaptive particle filter tracker with feature integration

This research proposes an improved particle filter tracking algorithm based on SGA (the adaptive genetic algorithm supervised by population convergence). In order to improve the robustness and efficiency of the particle filter tracker in various tracking scenarios, this study proposes an adaptive feature selection strategy based on Harris corner detection, SIFT features and colour features. In addition, the tracking frame scale of the traditional target tracking algorithm is fixed in the tracking process, which leads to many problems such as more invalid features and lower positioning accuracy. To solve these problems, this study proposes an adaptive tracking frame scale adjustment model based on the spatial position of particles. Furthermore, considering that the scale adaptive model cannot accurately reflect the target rotation deformation, this paper proposes an adaptive tracking frame scale and direction adjustment model based on the covariance descriptors to accurately track the rotation of the target and further reduce the invalid features of the rectangle frame. The extensive empirical evaluations on the benchmark dataset (OTB2015) and VOT2016 dataset demonstrate that the proposed method is very promising for the various challenging scenarios.