基于策略梯度的目标跟踪方法

王康豪,殷海兵,黄晓峰

Visual object tracking based on policy gradient

Kang-hao WANG,Hai-bing YIN,Xiao-feng HUANG

表 1 不同设定下的算法性能对比

Tab.1 Performance of proposed algorithm with different settings

设定 LaSOT结果 OTB100结果 平均速度/(帧·s−1) DP OP DP OP Never update (Baseline) 42.5% 0.363 74.2% 0.567 67 Always update (Baseline) 38.1% 0.337 75.8% 0.571 50 Adaptive update without re-detection 40.8% 0.359 78.0% 0.587 46 Response map based 43.8% 0.366 77.8% 0.587 33 Weighted confidence margin map based 44.2% 0.368 78.5% 0.592 32