Joint Multiple Fine-grained feature for Vehicle Re-Identification
The process of recognizing the same vehicle in different scenes is called vehicle re-identification. However, due to the different locations of the surveillance cameras, there may be obstacles in the captured vehicle pictures and multiple viewpoints may make the same vehicle look different. In order...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-07-01
|
| Series: | Array |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590005622000200 |
| _version_ | 1828322898300895232 |
|---|---|
| author | Yan Xu Leilei Rong Xiaolei Zhou Xuguang Pan Xianglan Liu |
| author_facet | Yan Xu Leilei Rong Xiaolei Zhou Xuguang Pan Xianglan Liu |
| author_sort | Yan Xu |
| collection | DOAJ |
| description | The process of recognizing the same vehicle in different scenes is called vehicle re-identification. However, due to the different locations of the surveillance cameras, there may be obstacles in the captured vehicle pictures and multiple viewpoints may make the same vehicle look different. In order to effectively reduce the interference of obstacle occlusion, multiple viewpoints, and other factors on vehicle re-identification, in this paper, we propose a multi-fine-grained feature extraction network. While retaining the global information of vehicles, we extract the finegrained features of vehicles precisely by segmenting the vehicle feature map. In addition, we introduce a new evaluation metric mean Inverse Negative Penalty (mINP) to evaluate the vehicle re-identification model more comprehensively. Our method achieves superior accuracy over the state-of-the-art methods on the challenging vehicle datasets: VeRi-776, VehicleID, and VRIC. |
| first_indexed | 2024-04-13T18:46:59Z |
| format | Article |
| id | doaj.art-263a98202dec465996b871d5e937a8f9 |
| institution | Directory Open Access Journal |
| issn | 2590-0056 |
| language | English |
| last_indexed | 2024-04-13T18:46:59Z |
| publishDate | 2022-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Array |
| spelling | doaj.art-263a98202dec465996b871d5e937a8f92022-12-22T02:34:34ZengElsevierArray2590-00562022-07-0114100152Joint Multiple Fine-grained feature for Vehicle Re-IdentificationYan Xu0Leilei Rong1Xiaolei Zhou2Xuguang Pan3Xianglan Liu4Corresponding author.; College of Electronic and Information Engineering, Shandong University of Science & Technology, Qingdao 266590, ChinaCorresponding author.; College of Electronic and Information Engineering, Shandong University of Science & Technology, Qingdao 266590, ChinaCollege of Electronic and Information Engineering, Shandong University of Science & Technology, Qingdao 266590, ChinaCollege of Electronic and Information Engineering, Shandong University of Science & Technology, Qingdao 266590, ChinaCollege of Electronic and Information Engineering, Shandong University of Science & Technology, Qingdao 266590, ChinaThe process of recognizing the same vehicle in different scenes is called vehicle re-identification. However, due to the different locations of the surveillance cameras, there may be obstacles in the captured vehicle pictures and multiple viewpoints may make the same vehicle look different. In order to effectively reduce the interference of obstacle occlusion, multiple viewpoints, and other factors on vehicle re-identification, in this paper, we propose a multi-fine-grained feature extraction network. While retaining the global information of vehicles, we extract the finegrained features of vehicles precisely by segmenting the vehicle feature map. In addition, we introduce a new evaluation metric mean Inverse Negative Penalty (mINP) to evaluate the vehicle re-identification model more comprehensively. Our method achieves superior accuracy over the state-of-the-art methods on the challenging vehicle datasets: VeRi-776, VehicleID, and VRIC.http://www.sciencedirect.com/science/article/pii/S2590005622000200Image retrievalDeep learningVehicle re-identificationFine-grained featureFeature map segmentationmINP |
| spellingShingle | Yan Xu Leilei Rong Xiaolei Zhou Xuguang Pan Xianglan Liu Joint Multiple Fine-grained feature for Vehicle Re-Identification Array Image retrieval Deep learning Vehicle re-identification Fine-grained feature Feature map segmentation mINP |
| title | Joint Multiple Fine-grained feature for Vehicle Re-Identification |
| title_full | Joint Multiple Fine-grained feature for Vehicle Re-Identification |
| title_fullStr | Joint Multiple Fine-grained feature for Vehicle Re-Identification |
| title_full_unstemmed | Joint Multiple Fine-grained feature for Vehicle Re-Identification |
| title_short | Joint Multiple Fine-grained feature for Vehicle Re-Identification |
| title_sort | joint multiple fine grained feature for vehicle re identification |
| topic | Image retrieval Deep learning Vehicle re-identification Fine-grained feature Feature map segmentation mINP |
| url | http://www.sciencedirect.com/science/article/pii/S2590005622000200 |
| work_keys_str_mv | AT yanxu jointmultiplefinegrainedfeatureforvehiclereidentification AT leileirong jointmultiplefinegrainedfeatureforvehiclereidentification AT xiaoleizhou jointmultiplefinegrainedfeatureforvehiclereidentification AT xuguangpan jointmultiplefinegrainedfeatureforvehiclereidentification AT xianglanliu jointmultiplefinegrainedfeatureforvehiclereidentification |