面向公共安全监控的多摄像机车辆重识别

doi:10.19665/j.issn1001-2400.2019.04.026

摘要/Abstract

摘要：

由于现有的车辆重识别方法大多是在已标注车辆边界框的图像间进行的,但在真实场景中无标注信息,同时环境的复杂性、车辆外观的相似性和多样性也是导致重识别精度不高的原因。因此,针对公共安全监控领域中无标注的原始视频,提出一种结合车辆检测与识别的多摄像机车辆重识别方法。首先设计了二值-单点多盒车辆检测网络以获取视频中的车辆边界框,并在线生成候选车辆数据库;其次设计了一种多任务孪生车辆识别网络以提高重识别精度;最后组建“VeRi-1501”车辆数据集。该数据集在现有数据集上扩充车辆身份,并均衡每个车辆身份在不同摄像机下的图像数量。该方法在VeRi-1501数据集和实际交通场景中识别准确且精度高。

关键词: 公共安全, 无标注视频, 车辆检测, 车辆重识别, 卷积神经网络

Abstract:

The existing vehicle re-identification (Re-ID) methods mostly perform Re-ID between images marked with vehicle bounding boxes, but there are no vehicle bounding boxes in the real scene; at the same time, the complexity of environment and the similarity and diversity in appearance among vehicles can also cause a low accuracy of Re-ID. Therefore, this paper proposes a multi-camera vehicle Re-ID method combining vehicle detection and recognition for the unmarked original video in the field of public safety surveillance. First, the Binary-Single Shot MultiBox vehicle detection network is proposed to obtain the vehicle bounding boxes and generate candidate database online. Second, a multi-task Siamese vehicle recognition network is designed to improve the Re-ID accuracy. Finally, the “VeRi-1501” vehicle dataset is established, which expands the number of vehicle IDs and balances the number of images for each ID in the case of different cameras. The proposed method has achieved good results in the VeRi-1501 dataset and the actual traffic scene.

Key words: public safety, unmarked video, vehicle detection, vehicle re-identification, convolutional neural network

中图分类号:

TP391.4

王艳芬,朱绪冉,云霄,孙彦景,石韫开,王赛楠. 面向公共安全监控的多摄像机车辆重识别[J]. 西安电子科技大学学报, 2019, 46(4): 190-196.

WANG Yanfen,ZHU Xuran,YUN Xiao,SUN Yanjing,SHI Yunkai,WANG Sainan. Vehicle re-identification by multi-cameras for public security surveillance[J]. Journal of Xidian University, 2019, 46(4): 190-196.

图/表 7

图1

图2

图3

图4

表1

图5

图6

参考文献 17

[1]	LIU X, LIU W, MA H. et al. Large-scale Vehicle Re-identification in Urban Surveillance Videos [C]//Proceedings of the 2016 IEEE International Conference on Multimedia and Expo. Washington: IEEE Computer Society, 2016: 7553002.
[2]	王瑞, 王康晏, 冯玉田 , 等. 复杂场景下声频传感器网络核稀疏表示车辆识别[J]. 西安电子科技大学学报, 2015,42(4):114-120.
	WANG Rui, WANG Kangyan, FENG Yutian , et al. Vehicle Sparse Representation of Audio Sensor Network in Complex Scenes[J]. Journal of Xidian University, 2015,42(4):114-120.
[3]	LIU X, LIU W, MEI T , et al. PROVID: Progressive and Multimodal Vehicle Reidentification for Large-scale Urban Surveillance[J]. IEEE Transactions on Multimedia, 2018,20(3):645-658.
[4]	LIU H, TIAN Y, WANG Y. et al. Deep Relative Distance Learning: Tell the Difference between Similar Vehicles [C]// Proceedings of the 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2016: 2167-2175.
[5]	LI Y, LI Y, YAN H. et al. Deep Joint Discriminative Learning for Vehicle Re-identification and Retrieval [C]// Proceedings of the 2018 International Conference on Image Processing. Washington: IEEE Computer Society, 2018: 395-399.
[6]	宋俊芳, 宋翔宇, 郭晓军 , 等. 构建多部件关系概率模型的车辆检测方法[J]. 西安电子科技大学学报, 2017,44(3):89-95.
	SONG Junfang, SONG Xiangyu, GUO Xiaojun , et al. Vehicle Detection Method for Constructing Multi-Part Relationship Probability Model[J]. Journal of Xidian University, 2017,44(3):89-95.
[7]	张密科, 胡选儒 . 基于图像纹理分析的动态车辆识别方法研究[J]. 公路交通科技, 2017,34(10):122-127.
	ZHANG Mike, HU Xuanru . Research on Dynamic Vehicle Identification Method Based on Image Texture Analysis[J]. Journal of Highway and Transportation Research and Development, 2017,34(10):122-127.
[8]	耿庆田, 赵浩宇, 于繁华 , 等. 基于改进HOG特征提取的车型识别算法[J]. 中国光学, 2018,11(2):174-181.
	GENG Qingtian, ZHAO Haoyu, YU Fanhua , et al. Vehicle Identification Algorithm Based on Improved HOG Feature Extraction[J]. China Optics, 2018,11(2):174-181.
[9]	LIU W, ANGUELOV D, ERHAN D. et al. SSD: Single Shot MultiBox Detector [C]//Lecture Notes in Computer Science: 9905. Heidelberg:Springer Verlag, 2016: 21-37.
[10]	REN S Q, HE K M, GIRSHICK R , et al. Faster R-CNN: towards Real-time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(6):1137-1149.
[11]	REDMON J, DIVVALA S, GIRSHICK R. et al. You Only Look Once: Unified, Real-time Object Detection [C]// Proceedings of the 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2016: 779-788.
[12]	SIMONYAN K , ZISSERMAN A. Very Deep Convolutional Networks for Large-scale Image Recognition[CP/OL]. [2018-12-10]. https://arxiv.org/pdf/1409.1556.pdf.
[13]	GIRSHICK R. Fast R-CNN [C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 1440-1448.
[14]	HE K, ZHANG X, REN S. et al. Deep Residual Learning for Image Recognition [C]//Proceedings of the 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2016: 770-778.
[15]	KRIZHEVSKY A, SUTSKEVER I, HINTON G E . Image Net Classification with Deep Convolutional Neural Networks[J]. Communications of the ACM, 2017,60(6):84-90.
[16]	HADSELL R, CHOPRA S, LECUN Y. Dimensionality Reduction by Learning an Invariant Mapping [C]//Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2006: 1735-1742.
[17]	ZHENG Z D, ZHENG L, YANG Y. A Discriminatively Learned CNN Embedding for Person Re-identification[J/OL]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2016, 14(1) . [2016-11-30].https://www.researchgate.net/publication/310462231.DOI: 14.10.1145/3159171.

方法	平均精度	rank-1	rank-5
Bow-CN^[1]	0.122	0.339	0.537
LOMO^[1]	0.096	0.253	0.465
GoogLeNet^[1]	0.170	0.498	0.712
FACT^[1]	0.185	0.510	0.735
PROVID^[3]	0.278	0.614	0.788
DRDL^[5]	0.546	0.490	0.735
DJDL^[4]	0.786	0.723	0.857
“MT-S”	0.806	0.834	0.976