Appearance-based multiple hypothesis tracking: Application to soccer broadcast videos analysis
作者：
Highlights：
• An effective AMHT framework is introduced to account for players’ appearance, nonlinear movements and occlusions.
• A blob-guided PSO player detection is introduced into the MHT, which is capable of detecting and labeling multiple players and resolving partial occlusions simultaneously. Only teammates in occluding blobs are detected by erasing the previously detected ones.
• Player labeling is solved within the player tracking step.
摘要
•An effective AMHT framework is introduced to account for players’ appearance, nonlinear movements and occlusions.•A blob-guided PSO player detection is introduced into the MHT, which is capable of detecting and labeling multiple players and resolving partial occlusions simultaneously. Only teammates in occluding blobs are detected by erasing the previously detected ones.•Player labeling is solved within the player tracking step.
论文关键词：PSO,Appearance,MHT,Soccer,Player,Tracking
论文评审过程：Received 4 May 2016, Revised 31 October 2016, Accepted 3 April 2017, Available online 7 April 2017, Version of Record 26 April 2017.
论文官网地址：https://doi.org/10.1016/j.image.2017.04.001
