AUTHOR=Chen Zhong , Yang Jinkun , Luo Chen , Zhang Changheng TITLE=A method for sperm activity analysis based on feature point detection network in deep learning JOURNAL=Frontiers in Computer Science VOLUME=Volume 4 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2022.861495 DOI=10.3389/fcomp.2022.861495 ISSN=2624-9898 ABSTRACT=Sperm motility is an important index to evaluate semen quality. Computer assisted Sperm analysis (CASA) is based on the sperm image, through the image processing algorithm to detect the position of the sperm target and track tracking, so as to judge the sperm activity. Due to the small and dense sperm targets in sperm images, traditional image processing algorithms take a long time to detect sperm targets, while target detection algorithms based on deep learning have a lot of missed detection problems in the process of sperm target detection. In order to accurately and efficiently analyze sperm activity in sperm image sequence, this paper proposes a sperm activity analysis method based on deep learning. Firstly, the deep learning feature point detection network based on the improved SuperPoint was used to detect the location of sperm. Then, multi-sperm target tracking was carried out through SORT and sperm movement trajectory was plotted. Finally, sperm survival was judged by sperm trajectory and sperm activity was analyzed. Experimental results show that the proposed method can effectively analyze sperm activity in sperm image sequence, and the average detection speed of sperm target detection method is 65fps, and the detection accuracy is 92%.