Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (9): 2493-2498.DOI: 10.11772/j.issn.1001-9081.2020010006

• Artificial intelligence • Previous Articles     Next Articles

Person re-identification method based on GAN uniting with spatial-temporal pattern

QIU Yaoru, SUN Weijun, HUANG Yonghui, TANG Yuqi, ZHANG Haochuan, WU Junpeng   

  1. School of Automation, Guangdong University of Technology, Guangzhou Guangdong 510006, China
  • Received:2020-01-16 Revised:2020-05-08 Online:2020-09-10 Published:2020-08-19
  • Supported by:
    This work is partially supported by the National Key Research and Development Program of China (2018YFB1802400), the Guangdong Research and Development Planning Project of Key Fields (2019B010118001, 2019B010121001).

基于生成对抗网络联合时空模型的行人重识别方法

邱耀儒, 孙为军, 黄永慧, 唐瑜祺, 张浩川, 吴俊鹏   

  1. 广东工业大学 自动化学院, 广州 510006
  • 通讯作者: 孙为军
  • 作者简介:邱耀儒(1993-),男,广东揭阳人,硕士研究生,主要研究方向:深度学习、图像识别;孙为军(1975-),男,安徽当涂人,讲师,博士,CCF会员,主要研究方向:智能信息处理;黄永慧(1975-),女,湖北麻城人,讲师,博士,主要研究方向:图像处理、模式识别;唐瑜祺(1995-),女,湖南邵阳人,硕士研究生,主要研究方向:深度学习、图像识别;张浩川(1994-),男,江西抚州人,硕士研究生,主要研究方向:深度学习、计算机视觉;吴俊鹏(1994-),男,广东广州人,硕士研究生,主要研究方向:机器学习、模式识别。
  • 基金资助:
    国家重点研发计划项目(2018YFB1802400);广东省重点领域研发计划项目(2019B010118001,2019B010121001)。

Abstract: Tracking of the person crossing the cameras is a technical challenge for smart city and intelligent security. And person re-identification is the most important technology for cross-camera person tracking. Due to the domain bias, applying person re-identification algorithms for cross-scenario application leads to the dramatic accuracy reduction. To address this challenge, a method based on Generative Adversarial Network (GAN) Uniting with Spatial-Temporal pattern (STUGAN) was proposed. First, training samples of the target scenario generated by the GAN were introduced to enhance the stability of the recognition model. Second, the spatio-temporal features were used to construct the spatio-temporal pattern of the target scenario, so as to screen low-probability matching samples. Finally, the recognition model and the spatio-temporal pattern were combined to realize the person re-identification task. On classic datasets of this field named Market-1501 and DukeMTMC-reID, the proposed method was compared with BoW (Bag-of-Words), PUL (Progressive Unsupervised Learning), UMDL (Unsupervised Multi-task Dictionary Learning) and other advanced unsupervised algorithms. The experimental results show that the proposed method achieves 66.4%, 78.9% and 84.7% recognition accuracy for rank-1, rank-5 and rank-10 indicators on the Market-1501 dataset respectively, which are 5.7, 5.0 and 4.4 percentage points higher than the best results of the comparison algorithm, respectively; and the mean Average Precision (mAP) higher than the comparison algorithms except Similarity Preserving cycle-consistent Generative Adversarial Network (SPGAN).

Key words: person tracking, person re-identification, cross-scenario application, Generative Adversarial Network (GAN), spatial-temporal pattern

摘要: 跨摄像头的行人跟踪是智慧城市和智能安防的技术难题,而行人重识别是跨摄像头行人跟踪中最关键的技术。针对因领域偏差而导致行人重识别算法跨场景应用时准确率大幅下降的问题,提出一种基于生成对抗网络(GAN)联合时空模型的方法(STUGAN)。首先,通过引入GAN生成目标场景的训练样本,以增强识别模型的稳定性;然后,利用时空特征构建目标场景样本的时空模型,以筛选低概率匹配样本;最后,融合识别模型与时空模型来进行行人的重识别。在该领域典型的公开数据集Market-1501和DukeMTMC-reID上与词袋模型(BoW)、先进的无监督学习(PUL)、无监督多任务字典学习(UMDL)等先进无监督算法进行实验对比。实验结果分析表明,所提方法在Market-1501数据集上的rank-1、rank-5及rank-10指标的准确率达到66.4%、78.9%及84.7%,比对比算法最好结果分别高5.7,5.0和4.4个百分点;平均精度均值(mAP)仅低于保持主题一致性的循环生成网络(SPGAN)。

关键词: 行人跟踪, 行人重识别, 跨场景应用, 生成对抗网络, 时空模型

CLC Number: