Vehicle Logo Recognition Using Spatial Structure Correlation and YOLO-T
The vehicle logo contains the vehicle’s identity information, so vehicle logo detection (VLD) technology has extremely important significance. Although the VLD field has been studied for many years, the detection task is still difficult due to the small size of the vehicle logo and the background in...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/9/4313 |
| _version_ | 1827742597105319936 |
|---|---|
| author | Li Song Weidong Min Linghua Zhou Qi Wang Haoyu Zhao |
| author_facet | Li Song Weidong Min Linghua Zhou Qi Wang Haoyu Zhao |
| author_sort | Li Song |
| collection | DOAJ |
| description | The vehicle logo contains the vehicle’s identity information, so vehicle logo detection (VLD) technology has extremely important significance. Although the VLD field has been studied for many years, the detection task is still difficult due to the small size of the vehicle logo and the background interference problem. To solve these problems, this paper proposes a method of VLD based on the YOLO-T model and the correlation of the vehicle space structure. Aiming at the small size of the vehicle logo, we propose a vehicle logo detection network called YOLO-T. It integrates multiple receptive fields and establishes a multi-scale detection structure suitable for VLD tasks. In addition, we design an effective pre-training strategy to improve the detection accuracy of YOLO-T. Aiming at the background interference, we use the position correlation between the vehicle lights and the vehicle logo to extract the region of interest of the vehicle logo. This measure not only reduces the search area but also weakens the background interference. We have labeled a new vehicle logo dataset named LOGO-17, which contains 17 different categories of vehicle logos. The experimental results show that our proposed method achieves high detection accuracy and outperforms the existing vehicle logo detection methods. |
| first_indexed | 2024-03-11T04:07:17Z |
| format | Article |
| id | doaj.art-dac28b223be545dd85ae854d52ef3b85 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T04:07:17Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-dac28b223be545dd85ae854d52ef3b852023-11-17T23:42:42ZengMDPI AGSensors1424-82202023-04-01239431310.3390/s23094313Vehicle Logo Recognition Using Spatial Structure Correlation and YOLO-TLi Song0Weidong Min1Linghua Zhou2Qi Wang3Haoyu Zhao4School of Software, Nanchang University, Nanchang 330047, ChinaSchool of Mathematics and Computer Science, Nanchang University, Nanchang 330031, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330031, ChinaSchool of Mathematics and Computer Science, Nanchang University, Nanchang 330031, ChinaSchool of Mathematics and Computer Science, Nanchang University, Nanchang 330031, ChinaThe vehicle logo contains the vehicle’s identity information, so vehicle logo detection (VLD) technology has extremely important significance. Although the VLD field has been studied for many years, the detection task is still difficult due to the small size of the vehicle logo and the background interference problem. To solve these problems, this paper proposes a method of VLD based on the YOLO-T model and the correlation of the vehicle space structure. Aiming at the small size of the vehicle logo, we propose a vehicle logo detection network called YOLO-T. It integrates multiple receptive fields and establishes a multi-scale detection structure suitable for VLD tasks. In addition, we design an effective pre-training strategy to improve the detection accuracy of YOLO-T. Aiming at the background interference, we use the position correlation between the vehicle lights and the vehicle logo to extract the region of interest of the vehicle logo. This measure not only reduces the search area but also weakens the background interference. We have labeled a new vehicle logo dataset named LOGO-17, which contains 17 different categories of vehicle logos. The experimental results show that our proposed method achieves high detection accuracy and outperforms the existing vehicle logo detection methods.https://www.mdpi.com/1424-8220/23/9/4313YOLO-Tvehicle logo detectionspatial structural correlationbackground interference |
| spellingShingle | Li Song Weidong Min Linghua Zhou Qi Wang Haoyu Zhao Vehicle Logo Recognition Using Spatial Structure Correlation and YOLO-T Sensors YOLO-T vehicle logo detection spatial structural correlation background interference |
| title | Vehicle Logo Recognition Using Spatial Structure Correlation and YOLO-T |
| title_full | Vehicle Logo Recognition Using Spatial Structure Correlation and YOLO-T |
| title_fullStr | Vehicle Logo Recognition Using Spatial Structure Correlation and YOLO-T |
| title_full_unstemmed | Vehicle Logo Recognition Using Spatial Structure Correlation and YOLO-T |
| title_short | Vehicle Logo Recognition Using Spatial Structure Correlation and YOLO-T |
| title_sort | vehicle logo recognition using spatial structure correlation and yolo t |
| topic | YOLO-T vehicle logo detection spatial structural correlation background interference |
| url | https://www.mdpi.com/1424-8220/23/9/4313 |
| work_keys_str_mv | AT lisong vehiclelogorecognitionusingspatialstructurecorrelationandyolot AT weidongmin vehiclelogorecognitionusingspatialstructurecorrelationandyolot AT linghuazhou vehiclelogorecognitionusingspatialstructurecorrelationandyolot AT qiwang vehiclelogorecognitionusingspatialstructurecorrelationandyolot AT haoyuzhao vehiclelogorecognitionusingspatialstructurecorrelationandyolot |