[1]李梦静,吉根林.视频行人重识别研究进展[J].南京师范大学学报(自然科学版),2020,43(02):120-130.[doi:10.3969/j.issn.1001-4616.2020.02.019]
 Li Mengjing,Ji Genlin.Research Progress on Video-based Person Re-Identification[J].Journal of Nanjing Normal University(Natural Science Edition),2020,43(02):120-130.[doi:10.3969/j.issn.1001-4616.2020.02.019]
点击复制

视频行人重识别研究进展()
分享到:

《南京师范大学学报》(自然科学版)[ISSN:1001-4616/CN:32-1239/N]

卷:
第43卷
期数:
2020年02期
页码:
120-130
栏目:
·计算机科学与技术·
出版日期:
2020-05-30

文章信息/Info

Title:
Research Progress on Video-based Person Re-Identification
文章编号:
1001-4616(2020)02-0120-11
作者:
李梦静吉根林
南京师范大学 计算机科学与技术学院,江苏 南京 210023
Author(s):
Li MengjingJi Genlin
School of Computer Science and Technology,Nanjing Normal University,Nanjing 210023,China
关键词:
行人重识别视频行人重识别视频分析计算机视觉
Keywords:
person re-identificationvideo-based person re-identificationvideo analysiscomputer vision
分类号:
TP391
DOI:
10.3969/j.issn.1001-4616.2020.02.019
文献标志码:
A
摘要:
视频行人重识别是指在不同摄像头拍摄的视频中检索特定行人的技术. 与图像行人重识别相比,视频行人重识别赋含信息更多,包含了帧与帧之间的时间信息、运动信息等,这有利于提高行人检索的准确率,因此视频行人重识别引起了国内外学者的广泛关注. 本文探讨了视频行人重识别的处理过程,详细介绍了其中特征提取和距离度量的方法,并对各种特征提取方法的特点及应用进行了总结,给出了一些视频行人重识别实验数据集和评价标准,提出了视频行人重识别研究领域面临的挑战及相应的解决方案,最后对视频行人重识别技术未来的研究问题做了展望.
Abstract:
Video-based person re-identification is a technique for retrieving specific pedestrians from video captured by different cameras. Compared with image-based person re-identification,video-based person re-identification has more information,including time information and motion information between frames,which is more conducive to improving the accuracy of pedestrian retri,so it has attracted widespread attention from scholars at home and abroad. This paper discusses the process of video-based person re-identification,introduces the methods of feature extraction and distance metric in detail,summarizes the characteristics and applications of various feature extraction methods,and some video-based person re-identification experimental data sets and uation standards are also given,what’s more,the challenges and corresponding solutions in the field of video person re-identification are presented. Finally an outlook to the future research problems of video person re-identification technology is given.

参考文献/References:

[1] WOJCIECH Z,ZORAN Z,BEN J A K. Keeping track of humans:have I seen this person before?[C]//IEEE International Conference on Robotics and Automation,Barcelona,Spain,2005.
[2]NILOOFAR G,THOMAS B S,RICHARD I. Hartley. person re-identification using spatiotemporal appearance[C]//IEEE Conference on Computer Vision and Pattern Recognition,New York,USA,2006.
[3]LORIS B,MARCO C,ALESSANDRO P,et al. Multiple-shot person re-identification by hpe signature[C]//International Conference on Pattern Recognition,Istanbul,Turkey,2010.
[4]MICHELA F,LORIS B,ALESSANDRO P,et al. Person re-identification by symmetry-driven accumulation of local features[C]//IEEE Conference on Computer Vision and Pattern Recognition,San Francisco,USA,2010.
[5]XIU Z,FEDERICO P,BIR B. Attributes co-occurrence pattern mining for video-based person re-identification[C]//Advanced Video and Signal Based Surveillance,Lecce,Italy,2017.
[6]LIU H,JIE Z,JAYASHREE K,et al. Video-based person re-identification with accumulative motion context[J]. IEEE transactions on circuits and systems for video technology,2017,28(10):2788-2802.
[7]NIALL M,JESUS M D R,PAUL M,et al. Recurrent convolutional network for video-based person re-identification[C]//IEEE Conference on Computer Vision and Pattern Recognition,Las Vergas,USA,2016.
[8]DAHJUNG C,KHALID T,EDWARD J D. A two stream siamese convolutional neural network for person re-identification[C]//International Conference on Computer Vision,Venice,Italy,2017.
[9]YAN Y C,NI B B,SONG Z C,et al. Person re-identification via recurrent feature aggregation[C]//European Conference on Computer Vision,Amstordam,The Netherlands,2016.
[10]CHEN L,YANG H,GAO Z Y. Joint attentive spatial-temporal feature aggregation for video-based person re-identification[J]. IEEE access 7,2019:41230-41240.
[11]ZHANG W,MA B P,LIU K,et al. Video-based pedestrian re-identification by adaptive spatio-temporal appearance model[J]. IEEE transactions on image processing,2017,26(4):2042-2054.
[12]LIU H,JIE Z Q,KARLEKAR J,et al. Video-based person re-identification with accumulative motion context[J]. IEEE transactions on circuits and system for video technology,2017,28(10):2788-2802.
[13]ZHOU Z,HUANG Y,WANG W,et al. See the forest for the trees:joint spatial and temporal recurrent neural networks for video-based person re-identification[C]//IEEE Conference on Computer Vision and Pattern Recognition,Honolulu,USA,2017.
[14]LI S,SLAWOMIR B,PETER C,et al. Diversity regularized spatiotemporal attention for video-based person re-identification[C]//IEEE Conference on Computer Vision and Pattern Recognition,Salt Lake City,USA,2018.
[15]LI J N,ZHANG S L,HUANG T J. Multiscale 3d convolution network for video based person reidentification[C]//The Association for the Advance of Artificial Intelligence,Honolulu,USA,2019.
[16]LIU J W,ZHA Z J,CHEN X J,et al. Dense 3D-convolutional neural network for person re-identification in videos[J]. ACM transactions on multimedia computing,communications,and applications,2019,15:1-19.
[17]LIU J,SUN C,XI X,et al. A spatial and temporal features mixture model with body parts for video-based person re-identification[J]. Applied intelligence,2019,49(9):3436-3446.
[18]YU B Z,XU N,ZHOU J. Cross-media body-part attention network for image-to-video person re-identification[J]. IEEE access 7, 2019:94966-94976.
[19]WU Y M,OMAR E F B,LI X. Adaptive graph representation learning for video person re-identification[EB/OL]. arXiv:1909.02240,2019.
[20]XU S M,HU S Q. Video-based person re-identification by region quality estimation and attributes[C]//International Conference on Cognitive Systems and Signal Processing,Beijing,China. 2018.
[21]SONG W R,ZHENG J Y,WU Y H,et al. A two-stage attribute-constraint network for video-based person re-identification[J]. IEEE access 7,2019:8508-8518.
[22]SUN R,HUANG Q H,XIA M M,et al. Video-based person re-identification by an end-To-end learning architecture with hybrid deep appearance-temporal feature[J]. Sensors,2018,18(11):3669-3689.
[23]NEERAJ M,GAURAV S. Video person re-identification using learned clip similarity aggregation[EB/OL]. arXiv:1910.08055,2019.
[24]CHEN P X,DAI P Y,WU Q,et al. Video-based Person re-identification with two-stream convolutional network and co-attentive snippet embedding[EB/OL]. arXiv:1905.11862,2019.
[25]XIE Z W,LI L,ZHONG X,et al. Image-to-video person re-identification by reusing cross-modal embeddings[EB/OL]. arXiv:1810.03989,2018.
[26]BHASWATI S,SAI R K,JAYANTA M,et al. Video based person re-identification by re-ranking attentive temporal information in deep recurrent convolutional networks[C]//IEEE International Conference on Image Processing,Athems,Greece,2018.
[27]CHEN D P,LI H S,XIAO T,et al. Video person re-identification with competitive snippet-similarity aggregation and co-attentive snippet embedding[C]//IEEE Conference on Computer Vision and Pattern Recognition,Salt Lake City,USA,2018.
[28]ZHANG D Y,WU W X,CHENG H,et al. Image-to-video person re-identification with temporally memorized similarity learning[J]. IEEE Transactions on Circuits and Systems for Video Technology,2018,28(10):2622-2632.
[29]DAI J,ZHANG P P,WANG D,et al. Video person re-identification by temporal residual learning[J]. IEEE Transactions on Image Processing,2019,28(3):1366-1377.
[30]OUYANG D Q,ZHANG Y H,SHAO J. Video-based person re-identification via spatio-temporal attentional and two-stream fusion convolutional networks[J]. Pattern recognition letters,2019,117:153-160.
[31]SONG W R,WU Y H,ZHENG J Y,et al. Extended global-local representation learning for video person re-identification[J]. IEEE access 7,2019:122684-122696.
[32]LIU Z,CHEN J X,WANG Y H. A fast adaptive spatio-temporal 3D feature for video-based person re-identification[C]//International Conference on Image Processing,Phoenix,USA,2016.
[33]WU L,WANG Y,SHAO L,et al. 3D person VLAD:learning deep global representations for video-based person re-identification[EB/OL]. CoRR abs/1812.10222,2018.
[34]CHENG L,JING X Y,ZHU X K,et al. A hybrid 2D and 3D convolution based recurrent network for video-based person re-identification[C]//International Conference on Neural Information Processing,Siem Reap,Cambodia,2018.
[35]NAOKI K,KOHEI H,MASAMOTO T,et al. Video-based person re-identification by 3d convolutional neural networks and improved parameter learning[C]//International Conference on Image Analysis and Recognition,Povoa de Varzim,Portugal,2018.
[36]LIAO X Y,HE L X,YANG Z W,et al. Video-based person re-identification via 3D convolutional networks and non-local attention[C]//Asian Conference on Computer Vision,Perth,Australia,2018.
[37]LIU Y H,YUAN Z X,ZHOU W G,et al. Spatial and temporal mutual promotion for video-based person re-identification[C]//AAAI Conference on Artificial Intelligence,Honolulu,USA,2019.
[38]LI J N,ZHANG S L,HUANG T J. Multi-scale 3D convolution network for video based person re-identification[C]//AAAI Conference on Artificial Intelligence,Honolulu,USA,2019.
[39]YANG X,ZHANG B,DONG Y,et al. Spatiotemporal attention on sliced parts for video-based person re-identification[C]//Visual Communications and Image Processing,Taichung,China,2018.
[40]WU L,WANG Y,GAO J B,et al. Where-and-when to look:deep siamese attention networks for video-based person re-identification[J]. IEEE transactions on multimedia,2019,21(6):1412-1424.
[41]XI J L,ZHOU Q,ZHAO Y R,et al. Fine-grained fusion with distractor suppression for video-based person re-identification[J]. IEEE access 7,2019:114310-114319.
[42]LI J N,WANG J D,TIAN Q,et al. Global-local temporal representations for video person re-identification[EB/OL]. arXiv:1908.10049,2019.
[43]YE M,LI J W,ANDY J M,et al. Dynamic graph co-matching for unsupervised video-based person re-identification[J]. IEEE transactions on image processing,2019,28(6):2976-2990.
[44]ABHIMANYU S,ANANDA S C. A graph-theoretic framework for summarizing first-person videos[C]//Graph Based Representations in Pattern Recognition,Tours,France,2019.
[45]SUN L C,ZHOU Y,LIU J L,et al. Graph regularized and label-matched dictionary learning for video-based person re-identification[C]//Visual Communications and Image Processing,Taichung,China,2018.
[46]ZHENG Y,CHEN Z H,SENEM V,et al. Person detection and re-identification across multiple images and videos obtained via crowdsourcing[C]//International Conference on Distributed Smart Cameras,Paris,France,2016.
[47]LI Y J,ZHUO L,LI J F,et al. Video-based person re-identification by deep feature guided pooling[C]//IEEE Conference on Computer Vision and Pattern Recognition,Honolulu,USA,2017.
[48]TANZILA R,MRIGANK R,WANG Y. Convolutional temporal attention model for video-based person re-identification[C]//IEEE International Conference on Multimedia and Expo,Shanghai,China,2019.
[49]OUYANG D Q,SHAO J,ZHANG Y H,et al. Video-based person re-identification via self-paced learning and deep reinforcement learning framework[C]//ACM Multimedia,Seoul,Korea,2018.
[50]BASSEM H,WALID A,MOHAMED A. Multi-shot person re-identification using a novel video covariance approach[C]//ACM Symposium on Applied Computing,Marrakech,Morocco,2017.
[51]WEINBERGER K Q,SAUL L K. Fast solvers and efficient implementations for distance metric learning[C]//International Conference on Machine Learning,Helsinki,Finland,2008.
[52]OSTINGER,HIRZER M,WOHLHART P,et al. Large scale metric learning from equivalence constraints[C]//IEEE Conference on Computer Vision and Pattern Recognition,Providence,USA,2012.
[53]LIAO S,HU Y,ZHU X,et al. Person re-identification by local maximal occurrence representation and metric learning[C]//IEEE Conference on Computer Vision and Pattern Recognition,Boston,USA,2015.
[54]PEDAGADI S,ORWELL J,VELASTIN S,et al. Local fisher discriminant analysis for pedestrian re-identification[C]//IEEE Conference on Computer Vision and Pattern Recognition,Portland,USA,2013.
[55]ZHU X K,JING X Y,YOU X G,et al. Video-based person re-identification by simultaneously learning intra-video and inter-video distance metrics[J]. IEEE transactions image processing,2018,27(11):5683-5695.
[56]ZHANG W,LI Y M,LU W Z,et al. Learning intra-video difference for person re-identification[J]. IEEE transactions circuits system video technology,2019,29(10):3028-3036.
[57]NAVANEET K L,VASUDHA T,VENKATESH B R,et al. All for one:frame-wise rank loss for improving video-based person re-identification[C]//IEEE International Conference on Acoustics,Speech,and Signal Processing,Brighton,UK,2019.
[58]WEI L,ZHANG S,YAO H,et al. Glad:global-local-alignment descriptor for pedestrian retri[C]//ACM multimedia,Mountain View,USA,2017.
[59]ZHAO H,TIAN M,SUN S,et al. Spindle net:person re-identification with human body region guided feature decomposition and fusion[C]//IEEE Conference on Computer Vision and Pattern Recognition,Honolulu,USA,2017.
[60]CHEN Y Z,HUANG T D,NIU Y Z,et al. Pose-guided spatial alignment and key frame selection for one-shot video-based person re-identification[J]. IEEE access 7,2019:78991-79004.
[61]WU J J,JIANG J G,QI M B,et al. Independent metric learning with aligned multi-part features for video-based person re-identification[J]. Multimedia tools application,2019,78(20):29323-29341.
[62]XU S J,CHENG Y,GU K,et al. Jointly attentive spatial-temporal pooling networks for video-based person re-identification[C]//International Conference on Computer Vision,Venice,Italy,2017.
[63]HOU R B,MA B P,CHANG H,et al. VRSTC:occlusion-free video person re-identification[C]//IEEE Conference on Computer Vision and Pattern Recognition,Long Beach,USA,2019.
[64]FARENZENA M,BAZZANI L,PERINA A,et al. Person re-identification by symmetry-driven accumulation of local features[C]//IEEE Conference on Computer Vision and Pattern Recognition,San Francisco,USA,2010.
[65]MA B P,SU Y,FRéDéRIC J. Covariance descriptor based on bio-inspired features for person re-identification and face verification[J]. Image vision computation,2014,32(6-7):379-390.
[66]APARAJITA N,PANKAJ K S,DUSHYANT S C,et al. A person re-identification framework by inlier-set group modeling for video surveillance[J]. Journal ambient intelligence and humanized computing,2019,10(1):13-25.
[67]THUY B N,THI T L,DINH D N,et al. A reliable image-to-video person re-identification based on feature fusion[C]//Asian Conference on Intelligent Information and Database Systems,Pong Hol City,Vietnam,2018.
[68]THUY B N,THI L,NAM P N. Fusion schemes for image-to-video person re-identification[J]. Journal information telecommunication,2019,3(1):74-94.
[69]ZHU X K,JING X Y,YOU X G,et al. Image to video person re-identification by learning heterogeneous dictionary pair with feature projection matrix[J]. IEEE transactions information forensics and security,2018,13(3):717-732.
[70]WANG G C,LAI J H,XIE X H. P2SNet:can an image match a video for person re-identification in an end-to-end way[J]. IEEE transactions circuits system video technology,2018,28(10):2777-2787.
[71]MARTIN H,CSABA B,PETER M R,et al. Person re-identification by descriptive and discriminative classification[C]//Scandinavian Conference on Image Analysis,Ystad,Sweden,2011.
[72]WANG T Q,GONG S G,ZHU X T,et al. Person re-identification by video ranking[C]//European Conference on Computer Vision,Zwrich,Switzerland,2014.
[73]ZHENG L,BIE Z,SUN F Y,et al. MARS:a video benchmark for large-scale person re-identification[C]//European Conference on Computer Vision,Amstordam,the Netherlands,2016.
[74]EMRAH B,YONATAN T T,MUBARAK S. EgoReID:person re-identification in egocentric videos acquired by mobile devices with first-person point-of-view[EB/OL]. arXiv:1812.09570,2018.
[75]ZHANG P,WU Q,XU J S,et al. Long-term person re-identification using true motion from videos[C]//IEEE Winter Conference on Applications of Computer Vision,Lake Tahoe,USA,2018.
[76]MA F,JING X Y,YAO Y F,et al. High-resolution and low-resolution video person re-identification:a benchmark[J]. IEEE access 7,2019:63426-63436.
[77]MA F,JING X Y,YAO Y F,et al. True-color and grayscale video person re-identification[J]. IEEE transactions information forensics and security,2020,15:115-129.
[78]ZHENG M X,KENTARO T,NOBUHIRO M,et al. Privacy-conscious person re-identification using low-resolution videos[C]//Asian Conference on Pattern Recognition,Nanjing,China,2017.

相似文献/References:

[1]朱 繁,王洪元,张 继.基于深度学习的行人重识别研究综述[J].南京师范大学学报(自然科学版),2018,41(04):93.[doi:10.3969/j.issn.1001-4616.2018.04.015]
 Zhu Fan,Wang Hongyuan,Zhang Ji.A Survey of Person Re-identification Based on Deep Learning[J].Journal of Nanjing Normal University(Natural Science Edition),2018,41(02):93.[doi:10.3969/j.issn.1001-4616.2018.04.015]

备注/Memo

备注/Memo:
收稿日期:2019-12-17.
基金项目:国家自然科学基金资助项目(41971343).
通讯作者:吉根林,博士,教授,博士生导师,研究方向:大数据分析与挖掘技术. E-mail:glji@njnu.edu.cn
更新日期/Last Update: 2020-05-15