Cell Tracking based on Multi-frame Detection and Feature Fusion
Wanli Yang, Huawei Li, Fei Wang, Dianle Zhou · 2021
Cell tracking is a challenging task in computer vision because of dramatic changes of cell morphology, unregular movement pattern, and complex physiological phenomena such as mitosis and apoptosis. In recent years, cell image processing benefits a lot from the rapid development of deep learning: cell detection, segmentation, classification, especially tracking. In this paper, we propose a multiple cell tracking framework based-on multi-feature fusion. First, we propose an improved cell detection algorithm, which can detect cell mitosis and cell centroid with higher efficiency and accuracy. Second, we design a tracking framework based on the fusion of deep appearance feature and deep motion feature. Experimental results show that our proposed tracking method outperforms most traditional method and some state-of-the-art methods.