Multi-shot Pedestrian Re-identification via Sequential Decision Making
Multi-shot Pedestrian Re-identification via Sequential Decision Making
复制标题
DOI：
10.1109/cvpr.2018.00709
复制
发表时间：
2017-12
期刊：
影响因子：
--
通讯作者：
Jianfu Zhang;Naiyan Wang;Liqing Zhang
中科院分区：
文献类型：
--
作者：
Jianfu Zhang;Naiyan Wang;Liqing Zhang
多镜头行人再识别问题是监控视频分析的核心问题。它匹配了两个不同摄像头拍到的行人轨迹。与现有的通过时间序列模型（如递归神经网络）聚合单帧特征的工作相反，本文提出了一种基于可解释强化学习的方法来解决这个问题。特别地，我们训练一个代理来每次验证一对图像。代理可以选择输出结果（相同或不同）或请求另一对图像进行验证（不确定）。通过这种方式，我们的模型隐式地学习图像对的难度，并在模型没有积累足够的证据时推迟决策。此外，通过调整不确定行为的奖励，我们可以很容易地在速度和准确性之间进行权衡。在三个开放的基准测试中，我们的方法与最先进的方法竞争，而只使用3%到6%的图像。这些有希望的结果表明，我们的方法是有利的效率和性能。
Multi-shot pedestrian re-identification problem is at the core of surveillance video analysis. It matches two tracks of pedestrians from different cameras. In contrary to existing works that aggregate single frames features by time series model such as recurrent neural network, in this paper, we propose an interpretable reinforcement learning based approach to this problem. Particularly, we train an agent to verify a pair of images at each time. The agent could choose to output the result (same or different) or request another pair of images to verify (unsure). By this way, our model implicitly learns the difficulty of image pairs, and postpone the decision when the model does not accumulate enough evidence. Moreover, by adjusting the reward for unsure action, we can easily trade off between speed and accuracy. In three open benchmarks, our method are competitive with the state-of-the-art methods while only using 3% to 6% images. These promising results demonstrate that our method is favorable in both efficiency and performance.