[1] [1] Smeulders, Arnold WM. Visual tracking: An experimental survey［J］. IEEE transactions on pattern analysis and machine intelligence, 2014, 36(7): 1442-1468.

[2] [2] Zhao Y, Wang C, Gong L, et al. Deep learning accelerators［J］. High Technology Letter, 2019, 25(4): 9.

[3] [3] Chen Zhang, Peng Li, Guangyu Sun, et al. Optimizing fpga-based accelerator design for deep convolutional neural networks［C］. In Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. ACM, 2016, 161170. New York, United States.

[4] [4] Redmon J, Farhadi A. YOLO9000: Better, Faster, Stronger［C］. IEEE Conference on Computer Vision & Pattern Recognition, 2017, 2053: 6517-6525.

[5] [5] Jiantao Qiu, Jie Wang, Song Yao, et al. Going deeper with embedded FPGA platform for convolutional neural network［C］. In Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. ACM, 2016, 2635. New York, United States.

[6] [6] Chao Wang, Lei Gong, Qi Yu, et al. DLAU: A scalable deep learning accelerator unit on FPGA［J］. IEEE Trans. on CAD of Integrated Circuits and Systems, 2017, 36(3): 513-517.