Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (17): 143-151.DOI: 10.3778/j.issn.1002-8331.2205-0390

• Pattern Recognition and Artificial Intelligence • Previous Articles     Next Articles

Person Re-Identification Method Based on IBN-Net and Channel Attention

YANG Yongsheng, DENG Miaolei, ZHANG Dexian   

  1. 1.College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China
    2.Henan International Joint Laboratory of Grain Information Processing, Zhengzhou 450001, China
  • Online:2023-09-01 Published:2023-09-01

基于IBN-Net和通道注意力的行人重识别方法

杨永胜,邓淼磊,张德贤   

  1. 1.河南工业大学 信息科学与工程学院,郑州 450001
    2.河南省粮食信息处理国际联合实验室,郑州 450001

Abstract: Due to the influence of bad factors such as blurred pedestrian images, occlusion, posture, different angles of view, color, style and brightness, it is difficult to extract distinguishing features in person re-identification task. This paper designs a novel network IBNC-Net based on IBN-Net and dual pool channel attention module. Firstly, IBN-Net50-a is used as the backbone network to learn the features that do not change with the appearance changes such as image style, color and brightness. Secondly, the dual pool channel attention module(DPCAM) is embedded in different network layers to suppress irrelevant features and enhance distinguishing features. Then, the generalized mean pooling(GeM) is introduced, and the pool scale is automatically adjusted by the model through training. Finally, in order to verify the effectiveness of the proposed IBNC-Net method, experiments are conducted on three popular datasets, including Market1501, DukeMTMC-ReID and CUHK03. The proposed IBNC-Net model has reached 95.6%/89.1%, 91.2%/80.3% and 80.5%/79.4%(mAP/Rank-1)?respectively. Experimental results show that the proposed method can effectively improve the performance of person re-identification model.

Key words: person re-identification, deep learning, attention mechanism, computer vision

摘要: 针对因拍摄的行人图像模糊、遮挡、姿势、视角、颜色、风格和亮度不同等不良因素的影响,行人重识别任务难以提取具有判别力的特征,设计了一种基于IBN-Net和双池通道注意力模块的新颖网络IBNC-Net。以IBN-Net50-a作为骨干网络学习不因图像风格、颜色和亮度等外观变化而变化的特征;在不同的网络层嵌入双池通道注意力模块DPCAM,抑制无关特征,增强具有判别力的特征;引入广义平均池化GeM,通过模型训练自动调整池化尺度。为了验证提出的IBNC-Net方法的有效性,在三个流行的数据集上进行实验,包括Market1501、DukeMTMC-ReID和CUHK03。IBNC-Net模型的Rank-1分别达到了95.6%、91.2%和80.5%,mAP分别达到了89.1%、80.3%和79.4%,实验结果表明,所提方法能够有效提高行人重识别模型的性能。

关键词: 行人重识别, 深度学习, 注意力机制, 计算机视觉