Biblio

Although the deep learning technology effectively improves the effect of person re-identification (re-ID) in video surveillance, there is still a lack of efficient framework in practical, especially in terms of computational cost, which usually requires GPU support. So this paper explores to solve the actual running performance and an effective person re-ID framework is proposed. A tiny network is designed for person detection and a triplet network is adopted for training feature extraction network. The motion detection and person detection is combined to speed up the whole process. The proposed framework is tested in practice and the results show that it can run in real-time on an ordinary PC machine. And the accuracy achieves 91.6% in actual data set. It has a good guidance for person re-ID in actual application.