基于行人属性异质性的行人再识别神经网络模型

doi:10.19678/j.issn.1000-3428.0050934

摘要/Abstract

摘要： 为提高基于行人属性学习的行人再识别算法识别精度,提出一种改进的行人再识别神经网络模型。该模型基于属性之间的异质性,在神经网络中设计不同的识别方法对各类属性进行识别,以提高行人属性识别的准确率。针对不同属性识别方法损失度量算法的不一致,给出异质属性损失度量函数,使得不同识别方法能在同一个网络模型中进行训练和学习,实现网络参数的最优化。实验结果表明,该模型在Market1501数据集、DukeMTMC数据集和DukeMTMC数据集上的首位准确率分别达到88.13%、74.96%和77.64%。

关键词: 行人再识别, 异质性, 深度学习, 属性分类, 回归预测, 多分类

Abstract: In order to improve the recognition accuracy of pedestrian re-identification algorithm based on pedestrian attribute learning,an improved pedestrian re-identification neural network model is proposed.Based on the heterogeneity between attributes,different recognition methods are designed in the neural network to identify various kinds of attributes to improve the accuracy of pedestrian attribute recognition.Aiming at the inconsistency of the loss measurement algorithm of different attribute recognition methods,the heterogeneous attribute loss measurement function is given,so that different recognition methods can be trained and learned in the same network model to optimize the network parameters.Experimental results show that the first accuracy rate of the model on the Market1501 dataset,DukeMTMC dataset and DukeMTMC dataset respectively reaches 88.13%,74.96% and 77.64%.

Key words: pedestrian re-identification, heterogeneity, deep learning, attribute classification, regression prediction, multiple classification

中图分类号:

TP18

吴彦丞, 陈鸿昶, 李邵梅, 高超. 基于行人属性异质性的行人再识别神经网络模型[J]. 计算机工程, 2018, 44(10): 196-203.

WU Yancheng, CHEN Hongchang, LI Shaomei, GAO Chao. Pedestrian Re-identification Neural Network Model Based on Pedestrian Attribute Heterogeneity [J]. Computer Engineering, 2018, 44(10): 196-203.

参考文献

［1］FARENZENA M,BAZZANI L,PERINA A,et al.Person re-identification by symmetry-driven accumulation of local features［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2010:2360-2367.br/ ［2］PEDAGADI S,ORWELL J,VELASTIN S,et al.Local fisher discriminant analysis for pedestrian re-identification［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Computer Society,2013:3318-3325.br/ ［3］陈鸿昶,陈雷,李邵梅,等.基于显著度融合的自适应分块行人再识别［J］.电子与信息学报,2017,39(11):2652-2660.br/ ［4］ZHENG W S,GONG S,XIANG T.Person re-identification by probabilistic relative distance comparison［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2011:649-656.br/ ［5］HIRZER M.Large scale metric learning from equivalence constraints［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:2288-2295.br/ ［6］杜宇宁,艾海舟.基于统计推断的行人再识别算法［J］.电子与信息学报,2014,36(7):1612-1618.br/ ［7］齐美彬,檀胜顺,王运侠,等.基于多特征子空间与核学习的行人再识别［J］.自动化学报,2016,42(2):299-308.br/ ［8］LI W,ZHAO R,XIAO T,et al.DeepReID:deep filter pairing neural network for person re-identification［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:152-159.br/ ［9］LIU H,FENG J,QI M,et al.End-to-end comparative attention networks for person re-identification［J］.IEEE Transactions on Image Processing,2017,26(7):3492-3506.br/ ［10］MATSUKAWA T,SUZUKI E.Person re-identification using CNN features learned from combination of attributes［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2428-2433.br/ ［11］LIN Y,ZHENG L,ZHENG Z,et al.Improving person re-identification by attribute and identity learning［EB/OL］.［2018-02-21］.https://www.researchgate.net.br/ ［12］VISIN F,KASTNER K,CHO K,et al.ReNet:A recurrent neural network based alternative to convolutional networks［J］.Computer Science,2015,25(7):2983-2996.br/ ［13］HAN H,JAIN A K,SHAN S,et al.Heterogeneous face attribute estimation:a deep multi-task learning approach［J］.IEEE Transactions on Pattern Analysis and Machine Intel-ligence,2017(99):1.br/ ［14］USTINOVE E,GANIN Y,LEMPITSKY V.Multiregion bilinear convolutional neural networks for person re-identification［J］.Computer Science,2015,48(10):2993-3003.br/ ［15］VARIOR R R,SHUAI B,LU J,et al.A siamese long short-term memory architecture for human re-identification［C］//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2016:135-153.br/ ［16］ZHENG Z,ZHENG L,YANG Y.A discriminatively learned CNN embedding for person re-identification［J］.ACM Transactions on Multimedia Computing Communica-tions and Applications,2016,14(1).br/ ［17］ZHEN Z,ZHENG L,YANG Y.Unlabeled samples generated by GAN improve the person re-identification baseline in vitro［EB/OL］.［2018-02-21］.https://www.researchgate.net.br/ ［18］ZHENG L,HUANG Y,LU H,et al.Pose invariant embedding for deep person re-identification［EB/OL］.［2018-02-21］.https://www.researchgate.net.br/ ［19］GENG M,WANG Y,XIANG T,et al.Deep transfer learning for person re-identification［EB/OL］.［2018-02-21］.https://www.researchgate.net.br/ ［20］ZHENG L,SHEN L,TIAN L,et al.Scalable person re-identification:a benchmark［C］//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2016:1116-1124.br/ ［21］LIAO S,HU Y,ZHU X,et al.Person re-identification by local maximal occurrence representation and metric learning［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:2197-2206.br/ ［22］MAJI S,BERG A C,MALIK J.Classification using intersection kernel support vector machines is efficient［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2008:1-8.br/ ［23］DENG Y,LUO P,CHEN C L,et al.Learning to recognize pedestrian attribute［EB/OL］.［2018-02-21］.https://www.researchgate.net.br/ ［24］SUDOWE P,SPITZER H,LEIBE B.Person attribute recognition with a jointly-trained holistic CNN model［C］//Proceedings of IEEE International Conference on Computer Vision Workshop.Washington D.C.,USA:IEEE Press,2015:329-337.br/

[1]	刘瑄, 池明旻. 基于多粒度特征蒸馏的遥感图像场景分类研究[J]. 计算机工程, 2021, 47(1): 224-229,238.
[2]	徐龙壮, 彭力, 朱凤增. 多任务金字塔重叠匹配的行人重识别方法[J]. 计算机工程, 2021, 47(1): 239-245,254.
[3]	王润涵, 李兵, 滕奇志. 基于卷积神经网络的岩心FIB-SEM图像分割算法[J]. 计算机工程, 2021, 47(1): 264-274.
[4]	王嘉庆, 梅礼晔, 张俊华. 基于深度学习的手骨X射线图像骨龄评估[J]. 计算机工程, 2021, 47(1): 291-297.
[5]	李兰, 郑雨薇, 魏少玮, 胡克勇. 基于注意力机制的商家招牌分类研究[J]. 计算机工程, 2021, 47(1): 305-311.
[6]	姜妍, 张立国. 面向深度学习模型的对抗攻击与防御方法综述[J]. 计算机工程, 2021, 47(1): 1-11.
[7]	韩虎, 赵启涛, 孙天岳, 刘国利. 面向社交媒体评论的上下文语境讽刺检测模型[J]. 计算机工程, 2021, 47(1): 66-71.
[8]	辛伟瑶, 李剑, 王小亮, 李禹剑. 基于深度学习的地下浅层震源定位方法[J]. 计算机工程, 2020, 46(9): 292-297.
[9]	肖经纬, 田军委, 王沁, 程希希, 王佳. 基于改进残差网络的果实病害分类方法[J]. 计算机工程, 2020, 46(9): 221-225.
[10]	生龙, 马建飞, 杨瑞欣, 吴迪. 基于特征交换的CNN图像分类算法研究[J]. 计算机工程, 2020, 46(9): 268-273.
[11]	尚迪雅, 孙华, 洪振厚, 曾庆亮. 基于无梯度进化的神经架构搜索算法研究综述[J]. 计算机工程, 2020, 46(9): 16-26.
[12]	张国令, 王晓丹, 李睿, 来杰, 向前. 基于栈式降噪稀疏自编码器的极限学习机[J]. 计算机工程, 2020, 46(9): 61-67.
[13]	谢瑞, 邵堃, 霍星, MITHUN Md Masud Parvej. 一种改进的DIQaM_FR/NR图像质量评价模型[J]. 计算机工程, 2020, 46(8): 258-263,270.
[14]	赵亚南, 刘渊, 宋设. 融合多头自注意力机制的金融新闻极性分析[J]. 计算机工程, 2020, 46(8): 85-92.
[15]	熊亚辉, 陈东方, 王晓峰. 基于多尺度反向投影的图像超分辨率重建算法[J]. 计算机工程, 2020, 46(7): 251-259.