基于组件特征与多注意力融合的车辆重识别方法

Vehicle Re-Identification Method Based on Part Features and Multi-Attention Fusion

为提升车辆重识别算法的性能,提出一种基于车辆组件特征与多注意力融合的特征学习方法.首先,修改深度残差网络以获取具有丰富语义信息的特征图,同时应用语义分割网络将车辆图像划分为车辆正面、背面、顶面、侧面及背景区域,以实现组件特征提取并消除视角变化的影响.然后,设计多注意力融合模块,基于面积注意力与特征注意力实现组件特征的自适应融合.最后,在多任务学习框架下,优化车辆重识别的三元组损失与辅助分类任务的交叉熵与焦点损失,对网络参数进行训练.在多个数据集上的实验结果表明,提出的方法在大多数性能指标上均超越了现有方法.进一步的消融实验证明了多注意力融合模块与多任务损失函数在特征提取上的有效性.

Vehicle re-identification(ReID),as a critical component for intelligent transportation systems,aims to identify the same vehicle across different cameras with large variations in viewpoints,lighting,and resolution.As the rapid development of surveillance networks,a tremendous amount of data is collected,making it expensive or even impossible to retrieve the same vehicle across multiple cameras via human labor.With the breakthrough in computer vision,a variety of vehicle ReID methods based on convolutional neural networks are recently developed and perform well in real-world scenes.One of the main challenges of ReID task is the variation of viewpoints,under which circumstance the identical vehicle from different viewpoints usually has low intra-instance similarity while different vehicles from similar viewpoints may have relatively small inter-instance discrepancy.To address this challenge and improve vehicle ReID performance,a novel parsing-based vehicle part multi-attention adaptive fusion network(PPAAF)is proposed.First,in order to gain a fine-grained representation of vehicle parts and meanwhile eliminate the effects of viewpoints,we modify the existing deep residual network named ResNet and introduce a parsing network to segment a vehicle image into image background and four different vehicle parts(including front,back,top,and side)respectively.Then vehicle part features are aligned through masked average pooling.Second,a novel part attention module(PAM)is developed to integrate multiple attention mechanism adaptively,providing diverse measurements of vehicle part importance in vehicle ReID task.Compared with previous methods,the additional attention not only enlarges the distance between different vehicles but also strengthens the validity of vehicle part feature extraction.Finally,we optimize the proposed network with Triplet loss and Focal loss in multi-task framework.Extensive experiments and ablation studies conducted on two major vehicle re-identification datasets provide competitive results against state-of-the-art vehicle ReID methods and prove the effectiveness of our method.