Boundary-aware vehicle tracking upon UAV

Discriminative correlation filters (DCFs) have recently achieved competitive performance in visual tracking benchmarks. However, such trackers perform poorly when the target undergoes occlusion, viewpoint variation or other challenging attributes. To tackle these issues, in this Letter, the authors combine the fast DCF trackers with the precise deep learning methods to eliminate the accumulating drift for the vehicle tracking based on unmanned aerial vehicle platform. Specifically, the authors employ the tracking result of the DCF tracker as the input of the boundary regressing network. After judging the existence of the target in the input patch, the proposed network would estimate the boundary of the target vehicle. Furthermore, the output would be updated to the tracking template, aiming at eliminating the accumulation errors and achieving a longterm tracking. The effectiveness of the proposed algorithm is validated through experimental comparison on widely used tracking benchmark data sets.