Deep convolutional neural networks with adaptive spatial feature for person re-identification
Zongtao Song, Xiaodong Cai, Yuelin Chen, Yan Zeng, Lu Lv, Hongxin Shu · 2017
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 feature's similarity. Different from traditional methods which extracts whole pedestrian's feature and feedback adjusted, the proposed method extract deep features from various areas of an image, and improved results are obtained on VIPeR dataset.