Person Re-Identification Based on PS Model and Multi-features

摘要：

　　In this paper, a method to extract multi-features with the framework of PS model (Pictorial Structures model) is proposed for person re-identification.PS model has inferred a full body pose by solving their kinematic constraints and made feature extraction more pure and more reliable as it has introduced improved body localizations and appearance signatures.Multi-feature types have been combined for signature matching which is assigned to be universally good for a wider ranger.The experimental results show that the method in this paper obtains competitive performance.All above is validated on widely used VIPER dataset.

关键词： Person Re-identification PS model Multi-features

作者: Lingyan Qu Jie Guo Peng Xu Weidong Qiu

作者单位: School of Information Security Engineering, Shanghai Jiao Tong University, Shanghai, 200240,China Institute of Information Technology, Police Training Institute, Shandong, 250002, China

会议类型: 国际会议

会议名称: International Conference on Computational Science and Engineering Applications(CSEA2015)2015计算机科学与工程应用国际会议

会议地点: 三亚

会议语种:英文

页码: 459-464

在线出版日期: 2015-12-26（万方平台首次上网日期，不代表论文的发表时间）