Deep Convolutional Neural Networks with Adaptive Spatial Feature for Person Re-Identification
In order to extract effective image features in different areas of an image,a method of deep convolutional neural networks with adaptive spatial characteristics for person re-identification is proposed.Firstly,each pedestrian image is divided into multiple blocks according to the characteristics of spatial distribution.Secondly,multi-branch of convolutional neural networks is used to extract deep features of individual pedestrian image block adaptively.Finally,the images are discriminated whether belong to the same person by calculating the deep features similarity.Different from traditional methods which extracts whole pedestrians feature and feedback adjusted,the proposed method extract deep features from various areas of an image,and improved results are obtained on VIPeR dataset.
spatial feature adaptive person re-identification CNN
Zongtao Song Xiaodong Cai Yuelin Chen Yan Zeng Lu Lv Hongxin Shu
School of Mechanical and Electrical Engineering,Guilin University of Electronic Technology,China China Comservice Public Information Industry Co.ltd
国际会议
重庆
英文
2020-2023
2017-03-25（万方平台首次上网日期，不代表论文的发表时间）