Pedestrian attribute recognition: A survey

被引：70

作者：

Wang, Xiao ^{[1
,3
]}

Zheng, Shaofei ^{[1
]}

Yang, Rui ^{[1
]}

Zheng, Aihua ^{[2
]}

Chen, Zhe ^{[4
]}

Tang, Jin ^{[1
]}

Luo, Bin ^{[1
]}

机构：

[1] Anhui Univ, Sch Comp Sci & Technol, Hefei, Peoples R China

[2] Anhui Univ, Sch Artificial Intelligence, Hefei, Peoples R China

[3] Peng Cheng Lab, Shenzhen, Peoples R China

[4] Univ Sydney, Sch Comp Sci, Fac Engn, Sydney, NSW, Australia

来源：

PATTERN RECOGNITION | 2022年 / 121卷

基金：

中国博士后科学基金; 澳大利亚研究理事会;

关键词：

Pedestrian attribute recognition; Multi-label learning; Multi-task learning; Deep learning; CNN-RNN; DEEP; GENDER; POSE; AGE;

D O I：

10.1016/j.patcog.2021.108220

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Pedestrian Attribute Recognition (PAR) is an important task in computer vision community and plays an important role in practical video surveillance. The goal of this paper is to review existing works using traditional methods or based on deep learning networks. Firstly, we introduce the background of pedestrian attribute recognition, including the fundamental concepts and formulation of pedestrian attributes and corresponding challenges. Secondly, we analyze popular solutions for this task from eight perspectives. Thirdly, we discuss the specific attribute recognition, then, give a comparison between deep learning and traditional algorithm based PAR methods. After that, we show the connections between PAR and other computer vision tasks. Fourthly, we introduce the benchmark datasets, evaluation metrics in this community, and give a brief performance comparison. Finally, we summarize this paper and give several possible research directions for PAR. The project page of this paper can be found at: https://sites.google.com/view/ahu-pedestrianattributes/ . (c) 2021 Elsevier Ltd. All rights reserved.

引用

页数：15

共 100 条

[1] Multi-Task CNN Model for Attribute Prediction [J].

Abdulnabi, Abrar H. ;

Wang, Gang ;

Lu, Jiwen ;

Jia, Kui .

IEEE TRANSACTIONS ON MULTIMEDIA, 2015, 17 (11) :1949-1959

[2]

[Anonymous], 2006, STREETSCENES SCENE U

[3] Effective training of convolutional neural networks for face-based gender and age prediction [J].

Antipov, Grigory ;

Baccouche, Moez ;

Berrani, Sid-Ahmed ;

Dugelay, Jean-Luc .

PATTERN RECOGNITION, 2017, 72 :15-26

[4]

Bourdev L, 2011, IEEE I CONF COMP VIS, P1543, DOI 10.1109/ICCV.2011.6126413

[5] Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations [J].

Bourdev, Lubomir ;

Malik, Jitendra .

2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, :1365-1372

[6]

Branca A, 2002, 2002 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL III, PROCEEDINGS, P317, DOI 10.1109/ICIP.2002.1038969

[7] Describing Clothing by Semantic Attributes [J].

Chen, Huizhong ;

Gallagher, Andrew ;

Girod, Bernd .

COMPUTER VISION - ECCV 2012, PT III, 2012, 7574 :609-623

[8] Spectral attribute learning for visual regression [J].

Chen, Ke ;

Jia, Kui ;

Zhang, Zhaoxiang ;

Kamarainen, Joni-Kristian .

PATTERN RECOGNITION, 2017, 66 :74-81

[9]

Chen Q, 2015, PROC CVPR IEEE, P5315, DOI 10.1109/CVPR.2015.7299169

[10] Deep and low-level feature based attribute learning for person re-identification [J].

Chen, Yiqiang ;

Duffner, Stefan ;

Stoian, Andrei ;

Dufour, Jean-Yves ;

Baskurt, Atilla .

IMAGE AND VISION COMPUTING, 2018, 79 :25-34

← 1 2 3 4 5 6 7 8 9 10 →