Abstract
Vehicle reidentification has important applications in intelligent monitoring systems. However, due to many factors, such as inaccurate vehicle image detection and viewing angle changes, distinguishing features cannot be effectively obtained when the vehicle is reidentified. To improve the recognition ability and robustness of vehicle reidentification, this study proposes a new multiattention part alignment network (MAPANet). The network uses different channels in the feature map to perceive different characteristics of the image clustering of the channels and achieves fine-grained attention to the vehicle. It can automatically locate the distinguishing subregions in the vehicle image and avoid the need for a large number of additional manual pretreatment steps. Moreover, an unsupervised reranking method based on multiple metrics is proposed. The k-reciprocal encoding algorithm can optimize the performance of the sorted list in the reordering problem, recalculate the interclass and intraclass distances of vehicle pictures, and improve sorting results. The experiments in this paper are carried out on the VeRi-776 and VehicleID datasets, and the mean average precision (mAP) results on the two datasets are 72.83% and 75.25%, respectively.
Highlights
(1) Introduce local discriminant features into the vehicle recognition task, use different channel response information to obtain local features, and reduce the impact of local part misalignment and a large number of marked key points
(2) Propose a discriminative and fine-grained network composed of multiple branches—the multiattention part alignment network (MAPANet), which extracts and integrates global and local features in a multibranch network structure
This study proposes a multimetric reordering method based on multiattention part alignment network (MAPANet) and k-reciprocal
Summary
E results showed that with deep features and manual “Compared with” features, vehicles are clearly distinguishable Later, they [11] constructed a large-scale vehicle dataset VehicleID [11] and proposed a progressive vehicle reidentification (PROVID) method. E use of key points increases the data preprocessing work To solve this problem, this study proposes a multimetric reordering method based on multiattention part alignment network (MAPANet) and k-reciprocal. Tumrani et al [25] proposed local attention and multiple attributes based on appearance features for vehicle reidentification, improved the number of output channels of the deconvolution head network proposed by Xiao et al [24], and realized the use of vehicle key points to obtain local features. Wang et al [26] used the k-reciprocal encoding algorithm to propose a discriminative fine-grained vehicle reidentification network based on a two-stage reordering framework. The average feature of the sample is formed by extracting the average center of k-reciprocal encoding nearest neighbors. e final distance is weighted by the original and Jaccard distances
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
