Revisiting Jump-Diffusion Process for Visual Tracking: A Reinforcement Learning Approach
Revisiting Jump-Diffusion Process for Visual Tracking: A Reinforcement Learning Approach
复制标题
DOI：
10.1109/tcsvt.2018.2862891
复制
发表时间：
2019-08
影响因子：
8.4
通讯作者：
Xiaobai Liu;Qian Xu;Thuan Chau;Yadong Mu;Lei Zhu;Shuicheng Yan
中科院分区：
文献类型：
--
作者：
Xiaobai Liu;Qian Xu;Thuan Chau;Yadong Mu;Lei Zhu;Shuicheng Yan
在本文中，我们重新审视经典的随机跳跃扩散过程，并开发了一个有效的变种估计的可见性状态的对象，同时跟踪他们在视频中。处理部分或完全遮挡是计算机视觉中的一个长期存在的问题，但在很大程度上仍未解决。在本文中，我们将上述问题转化为马尔可夫决策过程，并开发了一种基于策略的跳跃扩散方法来联合跟踪视频中的对象位置并估计其可见性状态。我们的方法采用了一组跳跃动力学来改变对象的可见性状态和一组扩散动力学来跟踪视频中的对象。与传统的随机生成动态的跳跃扩散过程不同，我们利用深度策略函数来确定当前状态的最佳动态，并使用强化学习方法学习最优策略。我们的方法是能够在拥挤的场景中跟踪完全或部分遮挡的对象。我们评估所提出的方法具有挑战性的视频序列，并将其与其他跟踪方法进行比较。特别是对于具有频繁交互或遮挡的视频进行了显著改进。
In this paper, we revisit the classical stochastic jump-diffusion process and develop an effective variant for estimating visibility statuses of objects while tracking them in videos. Dealing with partial or full occlusions is a long standing problem in computer vision but largely remains unsolved. In this paper, we cast the above problem as a Markov decision process and develop a policy-based jump-diffusion method to jointly track object locations in videos and estimate their visibility statuses. Our method employs a set of jump dynamics to change visibility statuses of objects and a set of diffusion dynamics to track objects in videos. Different from the traditional jump-diffusion process that stochastically generates dynamics, we utilize deep policy functions to determine the best dynamic for the present state and learn the optimal policies using reinforcement learning methods. Our method is capable of tracking objects with full or partial occlusions in crowded scenes. We evaluate the proposed method over challenging video sequences and compare it to alternative tracking methods. Significant improvements are made particularly for videos with frequent interactions or occlusions.