Deep Reinforcement Learning for Data Association in Cell Tracking

Accurate target detection and association are vital for the development of reliable target tracking, especially for the cell tracking based on microscopy image 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 association solution. Further, we design a residual convolutional neural network which results in more efficient learning. We validate our method on two exemplar applications: a multiple target tracking simulation and a 2D stem cell tracking. The results demonstrate that our approach based on reinforcement learning techniques could effectively track targets following different motion patterns and achieve the approximately optimum solution.