Wang Junjie, Su Xiaohong, Zhao Lingling, Zhang Jun
School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China.
Department of Rehabilitation, Heilongjiang Province Land Reclamation Headquarters General Hospital, Harbin, China.
Front Bioeng Biotechnol. 2020 Apr 9;8:298. doi: 10.3389/fbioe.2020.00298. eCollection 2020.
Accurate target detection and association are vital for the development of reliable target tracking, especially for cell tracking based on microscopy images due to the similarity of cells. We propose a deep reinforcement learning method to associate the detected targets between frames. According to the dynamic model of each target, the cost matrix is produced by conjointly considering various features of targets and then used as the input of a neural network. The proposed neural network is trained using reinforcement learning to predict a distribution over the association solution. Furthermore, we design a residual convolutional neural network that results in more efficient learning. We validate our method on two applications: the multiple target tracking simulation and the ISBI cell tracking. The results demonstrate that our approach based on reinforcement learning techniques could effectively track targets following different motion patterns and show competitive results.
准确的目标检测与关联对于可靠的目标跟踪发展至关重要，特别是对于基于显微镜图像的细胞跟踪，因为细胞之间具有相似性。我们提出一种深度强化学习方法来关联帧间检测到的目标。根据每个目标的动态模型，通过联合考虑目标的各种特征来生成代价矩阵，然后将其用作神经网络的输入。所提出的神经网络使用强化学习进行训练，以预测关联解决方案上的分布。此外，我们设计了一种残差卷积神经网络，可实现更高效的学习。我们在两个应用中验证了我们的方法：多目标跟踪模拟和ISBI细胞跟踪。结果表明，我们基于强化学习技术的方法能够有效地跟踪遵循不同运动模式的目标，并显示出具有竞争力的结果。
