Analysis of technical features in basketball video based on deep learning algorithm

作者：

Highlights：

• We introduced a spatial and temporal scoring mechanism for video analysis to define and extract the key video frames.

• A clustering-based algorithm is designed to extract the court area and eliminate the interference of the auditorium.

• An in-depth study on the behavior of the players is carried out.

摘要

•We introduced a spatial and temporal scoring mechanism for video analysis to define and extract the key video frames.•A clustering-based algorithm is designed to extract the court area and eliminate the interference of the auditorium.•An in-depth study on the behavior of the players is carried out.

论文关键词：Basketball,Movement analysis,HCI,Video,CNN,RNN,Encoder–decoder

论文评审过程：Received 25 July 2019, Revised 2 January 2020, Accepted 15 January 2020, Available online 20 January 2020, Version of Record 14 February 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115786