Scale-Invariant Multidirectional License Plate Detection with the Network Combining Indirect and Direct Branches
As the license plate is multiscale and multidirectional in the natural scene image, its detection is challenging in many applications. In this work, a novel network that combines indirect and direct branches is proposed for license plate detection in the wild. The indirect detection branch performs...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/4/1074 |
| _version_ | 1797414896426549248 |
|---|---|
| author | Song-Lu Chen Qi Liu Jia-Wei Ma Chun Yang |
| author_facet | Song-Lu Chen Qi Liu Jia-Wei Ma Chun Yang |
| author_sort | Song-Lu Chen |
| collection | DOAJ |
| description | As the license plate is multiscale and multidirectional in the natural scene image, its detection is challenging in many applications. In this work, a novel network that combines indirect and direct branches is proposed for license plate detection in the wild. The indirect detection branch performs small-sized vehicle plate detection with high precision in a coarse-to-fine scheme using vehicle–plate relationships. The direct detection branch detects the license plate directly in the input image, reducing false negatives in the indirect detection branch due to the miss of vehicles’ detection. We propose a universal multidirectional license plate refinement method by localizing the four corners of the license plate. Finally, we construct an end-to-end trainable network for license plate detection by combining these two branches via post-processing operations. The network can effectively detect the small-sized license plate and localize the multidirectional license plate in real applications. To our knowledge, the proposed method is the first one that combines indirect and direct methods into an end-to-end network for license plate detection. Extensive experiments verify that our method outperforms the indirect methods and direct methods significantly. |
| first_indexed | 2024-03-09T05:41:37Z |
| format | Article |
| id | doaj.art-d6d54dd615be4312b9993e1d76f6cc08 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:41:37Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d6d54dd615be4312b9993e1d76f6cc082023-12-03T12:25:07ZengMDPI AGSensors1424-82202021-02-01214107410.3390/s21041074Scale-Invariant Multidirectional License Plate Detection with the Network Combining Indirect and Direct BranchesSong-Lu Chen0Qi Liu1Jia-Wei Ma2Chun Yang3School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaAs the license plate is multiscale and multidirectional in the natural scene image, its detection is challenging in many applications. In this work, a novel network that combines indirect and direct branches is proposed for license plate detection in the wild. The indirect detection branch performs small-sized vehicle plate detection with high precision in a coarse-to-fine scheme using vehicle–plate relationships. The direct detection branch detects the license plate directly in the input image, reducing false negatives in the indirect detection branch due to the miss of vehicles’ detection. We propose a universal multidirectional license plate refinement method by localizing the four corners of the license plate. Finally, we construct an end-to-end trainable network for license plate detection by combining these two branches via post-processing operations. The network can effectively detect the small-sized license plate and localize the multidirectional license plate in real applications. To our knowledge, the proposed method is the first one that combines indirect and direct methods into an end-to-end network for license plate detection. Extensive experiments verify that our method outperforms the indirect methods and direct methods significantly.https://www.mdpi.com/1424-8220/21/4/1074license plate detectionmultiscalemultidirectionalindirect branchdirect branchend-to-end |
| spellingShingle | Song-Lu Chen Qi Liu Jia-Wei Ma Chun Yang Scale-Invariant Multidirectional License Plate Detection with the Network Combining Indirect and Direct Branches Sensors license plate detection multiscale multidirectional indirect branch direct branch end-to-end |
| title | Scale-Invariant Multidirectional License Plate Detection with the Network Combining Indirect and Direct Branches |
| title_full | Scale-Invariant Multidirectional License Plate Detection with the Network Combining Indirect and Direct Branches |
| title_fullStr | Scale-Invariant Multidirectional License Plate Detection with the Network Combining Indirect and Direct Branches |
| title_full_unstemmed | Scale-Invariant Multidirectional License Plate Detection with the Network Combining Indirect and Direct Branches |
| title_short | Scale-Invariant Multidirectional License Plate Detection with the Network Combining Indirect and Direct Branches |
| title_sort | scale invariant multidirectional license plate detection with the network combining indirect and direct branches |
| topic | license plate detection multiscale multidirectional indirect branch direct branch end-to-end |
| url | https://www.mdpi.com/1424-8220/21/4/1074 |
| work_keys_str_mv | AT songluchen scaleinvariantmultidirectionallicenseplatedetectionwiththenetworkcombiningindirectanddirectbranches AT qiliu scaleinvariantmultidirectionallicenseplatedetectionwiththenetworkcombiningindirectanddirectbranches AT jiaweima scaleinvariantmultidirectionallicenseplatedetectionwiththenetworkcombiningindirectanddirectbranches AT chunyang scaleinvariantmultidirectionallicenseplatedetectionwiththenetworkcombiningindirectanddirectbranches |