GLFNet: Combining Global and Local Information in Vehicle Re-Recognition
Vehicle re-identification holds great significance for intelligent transportation and public safety. Extracting vehicle recognition information from multi-view vehicle images has become one of the challenging problems in the field of vehicle recognition. Most recent methods employ a single network e...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/2/616 |
| _version_ | 1797339330174255104 |
|---|---|
| author | Yinghan Yang Peng Liu Junran Huang Hongfei Song |
| author_facet | Yinghan Yang Peng Liu Junran Huang Hongfei Song |
| author_sort | Yinghan Yang |
| collection | DOAJ |
| description | Vehicle re-identification holds great significance for intelligent transportation and public safety. Extracting vehicle recognition information from multi-view vehicle images has become one of the challenging problems in the field of vehicle recognition. Most recent methods employ a single network extraction structure, either a single global or local measure. However, for vehicle images with high intra-class variance and low inter-class variance, exploring globally invariant features and discriminative local details is necessary. In this paper, we propose a Feature Fusion Network (GLFNet) that combines global and local information. It utilizes global features to enhance the differences between vehicles and employs local features to compactly represent vehicles of the same type. This enables the model to learn features with a large inter-class distance and small intra-class distance, significantly improving the model’s generalization ability. Experiments show that the proposed method is competitive with other advanced algorithms on three mainstream road traffic surveillance vehicle re-identification benchmark datasets. |
| first_indexed | 2024-03-08T09:46:25Z |
| format | Article |
| id | doaj.art-3d9a3b07b8c84904b01890e61aba560a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T09:46:25Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3d9a3b07b8c84904b01890e61aba560a2024-01-29T14:17:13ZengMDPI AGSensors1424-82202024-01-0124261610.3390/s24020616GLFNet: Combining Global and Local Information in Vehicle Re-RecognitionYinghan Yang0Peng Liu1Junran Huang2Hongfei Song3College of Automotive Engineering, Jilin University, Changchun 130012, ChinaSchool of Mechanical and Aerospace Engineering, Jilin University, Changchun 130012, ChinaSchool of Optoelectronic Engineering, Changchun University of Science and Technology, Changchun 130012, ChinaSchool of Optoelectronic Engineering, Changchun University of Science and Technology, Changchun 130012, ChinaVehicle re-identification holds great significance for intelligent transportation and public safety. Extracting vehicle recognition information from multi-view vehicle images has become one of the challenging problems in the field of vehicle recognition. Most recent methods employ a single network extraction structure, either a single global or local measure. However, for vehicle images with high intra-class variance and low inter-class variance, exploring globally invariant features and discriminative local details is necessary. In this paper, we propose a Feature Fusion Network (GLFNet) that combines global and local information. It utilizes global features to enhance the differences between vehicles and employs local features to compactly represent vehicles of the same type. This enables the model to learn features with a large inter-class distance and small intra-class distance, significantly improving the model’s generalization ability. Experiments show that the proposed method is competitive with other advanced algorithms on three mainstream road traffic surveillance vehicle re-identification benchmark datasets.https://www.mdpi.com/1424-8220/24/2/616intelligent transportation systemvehicle re-identificationmulti-feature fusionvehicle detectorroad traffic monitoring |
| spellingShingle | Yinghan Yang Peng Liu Junran Huang Hongfei Song GLFNet: Combining Global and Local Information in Vehicle Re-Recognition Sensors intelligent transportation system vehicle re-identification multi-feature fusion vehicle detector road traffic monitoring |
| title | GLFNet: Combining Global and Local Information in Vehicle Re-Recognition |
| title_full | GLFNet: Combining Global and Local Information in Vehicle Re-Recognition |
| title_fullStr | GLFNet: Combining Global and Local Information in Vehicle Re-Recognition |
| title_full_unstemmed | GLFNet: Combining Global and Local Information in Vehicle Re-Recognition |
| title_short | GLFNet: Combining Global and Local Information in Vehicle Re-Recognition |
| title_sort | glfnet combining global and local information in vehicle re recognition |
| topic | intelligent transportation system vehicle re-identification multi-feature fusion vehicle detector road traffic monitoring |
| url | https://www.mdpi.com/1424-8220/24/2/616 |
| work_keys_str_mv | AT yinghanyang glfnetcombiningglobalandlocalinformationinvehiclererecognition AT pengliu glfnetcombiningglobalandlocalinformationinvehiclererecognition AT junranhuang glfnetcombiningglobalandlocalinformationinvehiclererecognition AT hongfeisong glfnetcombiningglobalandlocalinformationinvehiclererecognition |