Multi-Object Tracking Based on Segmentation and Collision Avoidance

• 作 者: Meng Zhao Junhui Wang Maoyong Cao Peirui Bai Hongyan Gu Mingtao Pei
• 机 构: College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qin
• 出 处: Journal of Beijing Institute of Technology
• 发表日期: 2018年02期
• 关键词: multi-object tracking conditional random field superpixel collision avoidance

An approach to track multiple objects in crowded scenes with long-term partial occlusions is proposed. Tracking-by-detection is a successful strategy to address the task of tracking multiple objects in unconstrained scenarios,but an obvious shortcoming