2020年 04期

摘要(Abstract)：

针对目前的行人属性识别方法存在鲁棒性差、特征表达能力不足和行人的细粒度特征识别精度不高的缺点,提出一种基于注意力机制与空间金字塔池化的行人属性识别方法,通过注意力机制强化不同维度的特征,提升行人整体特征表达;通过空间金字塔池化操作,实现任意大小图像的输入,更好地保留图像的特征信息。结果表明,与现有的其他方法相比,所提出的行人属性识别方法可以精确地识别行人多种属性,具有较高的行人细粒度特征识别精度。

关键词(KeyWords)： 模式识别;行人属性识别;注意力机制;空间金字塔池化

基金项目(Foundation): 山西省自然科学基金项目(201801D121136)

作者(Author): 段迅达,韩晓红

DOI: 10.13349/j.cnki.jdxbn.2020.04.005

参考文献(References)：

[1] LI A N,LIU L Q,WANG K,et al.Clothing attributes assisted person reidentification[J].IEEE Transactions on Circuits and Systems for Video Technology,2014,25(5):869-878.

[2] SU C,ZHANG S L,YANG F,et al.Attributes driven tracklet-to-tracklet person re-identification using latent prototypes space mapping[J].Pattern Recognition,2017,66:4-15.

[3] KUMAR N,BERG A C,BELHUMEUR P N,et al.Describable visual attributes for face verification and image search[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(10):1962-1977.

[4] LIN L,GONG H F,LI L,et al.Semantic event representation and recognition using syntactic attribute graph grammar[J].Pattern Recognition Letters,2009,30(2):180-186.

[5] CAO L L,DIKMEN M,FU Y,et al.Gender recognition from body[C]//Proceedings of the 16th ACM International Conference on Multimedia,October 26-31,2008,Vancouver,Canada.Baltimore:ACM,2008:725-728.

[6] ZHU J Q,LIAO S C,LEI Z,et al.Pedestrian attribute classification in surveillance:database and evaluation[C]//2013 IEEE International Conference on Computer Vision Workshops,Dcecmber 2-8,2013,Sydney,Australia.New York:IEEE,2013:331-338.

[7] CHEN H Z,GALLAGHER A,GIROD B.Describing clothing by semantic attributes[C]//FITZGIBBON A,LAZEBNIK S,PERONA P,et al.Proceedings of the 12th European Conference on Computer Vision(ECCV 2012):Part Ⅲ.LNCS,Vol.7574.Berlin:Springer-Verlag,2012:609-623.

[8] LIU F,XIANG T,HOSPEDALES T M,et al.Semantic regularisation for recurrent image annotation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition,July 21-26,2017,Honolulu,USA.New York:IEEE,2017:2872-2880.

[9] ZHU J Q,LIAO S C,LEI Z,et al.Multi-label convolutional neural network based pedestrian attribute classification[J].Image and Vision Computing,2017,10(58):224-229.

[10] CHEN S Z,WANG X J,ZHAO X J.An attribute recognition model based on entropy weight for evaluating the quality of groundwater sources[J].Journal of China University of Mining & Technology,2008,18(1):72-75.

[11] MA L Y,YANG X K,TAO D C.Person re-identification over camera networks using multi-task distance metric learning[J].IEEE Transactions on Image Processing,2014,23(8):3656-3670.

[12] HE K M,ZHANG X Y,REN S Q,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.

[13] SZEGEDY C,VANHOUCKE V,LOFFE S,et al.Rethinking the inception architecture for computer vision[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition,June 27-30,2016,Las Vegas,USA.New York:IEEE,2016:2818-2826.

[14] DENG Y B,LUO P,LOY C C,et al.Pedestrian attribute recognition at far distance[C]//Proceedings of the 22nd ACM International Conference on Multimedia,November 3-7,2014,Orlando,USA.Baltimore:ACM,2014:789-792.

[15] LIU X H,ZHAO H Y,TIAN M Q,et al.Hydraplus-net:attentive deep features for pedestrian analysis[C]//2017 IEEE International Conference on Computer Vision,October 22-29,2017,Venice,Italy.New York:IEEE,2017:350-359.

[16] LI W,ZHAO R,XIAO T,et al.DeepReID:deep filter pairing neural network for person re-identification[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition,June 23-28,2014,Columbus,USA.New York:IEEE Computer Society,2014:152-159.

[17] LI Y,LIN G S,ZHUANG B H,et al.Sequential person recognition in photo albums with a recurrent network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition,July 21-26,2017,Honolulu,USA.New York:IEEE,2017:5660-5668.

[18] FABBRI M,CALDERARA S,CUCCHIARA R.Generative adver-sarial models for people attribute recognition in surveillance[C]//2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS),August 29-September 1,2017,Lecce,Italy.New York:IEEE,2017:1-6.

[19] LOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//International Conference on Machine Learning,July 6-11,2015,Lille,France.[S.l.]:International Machine Learning Society,2015:448-456.

[20] GRAY D,TAO H.Viewpoint invariant pedestrian recognition with an ensemble of localized features[C]//FORSYTH D,TORR P,ZISSERMAN A.Proceedings of the 2008 10 th European Conference on Computer Vision(ECCV 2008):Part I.LNCS,Vol.5302.Berlin:Springer,2008:262-275.

[21] PROSSER B,ZHENG W S,GONG S G,et al.Person re-identification by support vector ranking[C]//British Machine Vision Conference,August 31-September 3,2010.Aberystwyth,UK.[S.l.]:British Machine Vision Association,2010,2(5):1-11.

[22] 郭志影.基于深度学习的室外监控场景下行人属性识别[D].北京:北京邮电大学,2018.