作者: Cheng-Shian Lin , Tsung-Kang Chiang , Jin-Jang Leou
DOI:
关键词: Computer science 、 Discriminative model 、 Selection (genetic algorithm) 、 Tracking system 、 Window (computing) 、 Object (computer science) 、 Computer vision 、 Artificial intelligence 、 Tracking (particle physics) 、 Simulation 、 Precision and recall 、 Mean-shift
摘要: In this study, an improved mean shift algorithm based tracking system with motion prediction and object window enlarging for soccer game analysis is proposed. The objective of the proposed to track players (moving objects) efficiently accurately. Discriminative color selection modeling employed, occlusions are well handled, incoming outgoing detected handled in system. Based on experimental results obtained as recall precision rates better than those three comparison systems.