基于局部深度匹配的行人再识别

针对行人再识别精度低的难题进行研究，提出了一种新的基于分块匹配的行人再识别方法。首先，引入带人体结构信息的人体DPM模型对行人外观进行分割，得到的带语义信息的身体部件作为匹配识别的基本单元；其次，基于深度神经网络模型提取各部件的深度特征作为匹配依据；再次，基于余弦距离判断各身体部件与目标行人对应部件的相似性；最后，融合所有身体部件的识别结果得到最终的再识别结果。实验结果表明，跟已有方法相比，本文方法具有更好的鲁棒性，在识别精度上有较明显的优势。

Person Re-identification based on Locally Deep Matching

This paper presents a new method based on part matching to improve the accuracy of person re-identification,. First of all, a person DPM which carries the information of person structure is used to segment the human body into parts with semantic meanings, and these parts are used as basic units for re-identification. Secondly, the deep features of these body parts are extracted by deep neural network model. Thirdly, each body part of the testing person is compared with the corresponding body part of the target person based on the deep feature and cosine distance. Finally, the matching results from all the body parts are fused to make the final decision. Experimental results show that our method is more robust and it outperforms most state-of-art methods.