当前位置: X-MOL 学术Meas. Sci. Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Stripe-based and attribute-aware network: A two-branch deep model for vehicle re-identification
Measurement Science and Technology ( IF 2.4 ) Pub Date : 2020-06-22 , DOI: 10.1088/1361-6501/ab8b81
Jingjing Qian 1 , Wei Jiang 1 , Hao Luo 1 , Hongyan Yu 2
Affiliation  

Vehicle re-identification (Re-ID) has been attracting increasing interest in the field of computer vision due to the growing utilization of surveillance cameras in public security. However, vehicle Re-ID still suffers a similarity challenge despite the efforts made to solve this problem. This challenge involves distinguishing different instances with nearly identical appearances. In this paper, we propose a novel two-branch stripe-based and attribute-aware deep convolutional neural network (SAN) to learn the efficient feature embedding for vehicle Re-ID task. The two-branch neural network, consisting of stripe-based branch and attribute-aware branches, can adaptively extract the discriminative features from the visual appearance of vehicles. A horizontal average pooling and dimension-reduced convolutional layers are inserted into the stripe-based branch to achieve part-level features. Meanwhile, the attribute-aware branch extracts the global feature under the supervision of vehicle attribute labels to separate the similar vehicle identities with different attribute annotations. Finally, the part-level and global features are concatenated together to form the final descriptor of the input image for vehicle Re-ID. The final descriptor not only can separate vehicles with different attributes but also distinguish vehicle identities with the same attributes. The extensive experiments on both VehicleID and VeRi databases show that the proposed SAN method outperforms other state-of-the-art vehicle Re-ID approaches.

中文翻译:

基于条纹和属性感知的网络:用于车辆重新识别的两分支深度模型

由于公共安全中监控摄像头的使用越来越多,车辆重新识别(Re-ID)在计算机视觉领域引起了越来越多的兴趣。然而,尽管为解决这个问题做出了努力,但车辆 Re-ID 仍然面临着相似性挑战。这个挑战涉及区分具有几乎相同外观的不同实例。在本文中,我们提出了一种新颖的基于两分支条带和属性感知的深度卷积神经网络(SAN)来学习车辆 Re-ID 任务的有效特征嵌入。由基于条纹的分支和属性感知分支组成的两分支神经网络可以自适应地从车辆的视觉外观中提取判别特征。将水平平均池化和降维卷积层插入到基于条带的分支中以实现部分级特征。同时,属性感知分支在车辆属性标签的监督下提取全局特征,以分离具有不同属性注释的相似车辆身份。最后,部件级和全局特征连接在一起,形成车辆 Re-ID 输入图像的最终描述符。最终的描述符不仅可以区分具有不同属性的车辆,还可以区分具有相同属性的车辆身份。VehicleID 和 Veri 数据库上的大量实验表明,所提出的 SAN 方法优于其他最先进的车辆 Re-ID 方法。属性感知分支在车辆属性标签的监督下提取全局特征,以分离具有不同属性注释的相似车辆身份。最后,部件级和全局特征连接在一起,形成车辆 Re-ID 输入图像的最终描述符。最终的描述符不仅可以区分具有不同属性的车辆,还可以区分具有相同属性的车辆身份。VehicleID 和 Veri 数据库上的大量实验表明,所提出的 SAN 方法优于其他最先进的车辆 Re-ID 方法。属性感知分支在车辆属性标签的监督下提取全局特征,以分离具有不同属性注释的相似车辆身份。最后,部件级和全局特征连接在一起,形成车辆 Re-ID 输入图像的最终描述符。最终的描述符不仅可以区分具有不同属性的车辆,还可以区分具有相同属性的车辆身份。VehicleID 和 Veri 数据库上的大量实验表明,所提出的 SAN 方法优于其他最先进的车辆 Re-ID 方法。部件级和全局特征连接在一起,形成车辆 Re-ID 输入图像的最终描述符。最终的描述符不仅可以区分具有不同属性的车辆,还可以区分具有相同属性的车辆身份。VehicleID 和 Veri 数据库上的大量实验表明,所提出的 SAN 方法优于其他最先进的车辆 Re-ID 方法。部件级和全局特征连接在一起,形成车辆 Re-ID 输入图像的最终描述符。最终的描述符不仅可以区分具有不同属性的车辆,还可以区分具有相同属性的车辆身份。VehicleID 和 Veri 数据库上的大量实验表明,所提出的 SAN 方法优于其他最先进的车辆 Re-ID 方法。
更新日期:2020-06-22
down
wechat
bug