Fine-grained vehicle recognition under low light conditions using EfficientNet and image enhancement on LiDAR point cloud data
Abstract The detection and recognition of vehicles are crucial components of environmental perception in autonomous driving. Commonly used sensors include cameras and LiDAR. The performance of camera-based data collection is susceptible to environmental interference, whereas LiDAR, while unaffected...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-89002-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862317363757056 |
|---|---|
| author | Guanqiang Ruan Tao Hu Chenglin Ding Kuo Yang Fanhao Kong Jinrun Cheng Rong Yan |
| author_facet | Guanqiang Ruan Tao Hu Chenglin Ding Kuo Yang Fanhao Kong Jinrun Cheng Rong Yan |
| author_sort | Guanqiang Ruan |
| collection | DOAJ |
| description | Abstract The detection and recognition of vehicles are crucial components of environmental perception in autonomous driving. Commonly used sensors include cameras and LiDAR. The performance of camera-based data collection is susceptible to environmental interference, whereas LiDAR, while unaffected by lighting conditions, can only achieve coarse-grained vehicle classification. This study introduces a novel method for fine-grained vehicle model recognition using LiDAR in low-light conditions. The approach involves collecting vehicle model data with LiDAR, performing projection transformation, enhancing the data using contrast limited adaptive histogram equalization combined with Gamma correction, and implementing vehicle model recognition based on EfficientNet. Experimental results demonstrate that the proposed method achieves an accuracy of 98.88% in fine-grained vehicle model recognition and an F1-score of 98.86%, showcasing excellent performance. |
| format | Article |
| id | doaj-art-8dd13120985c4536aeefdfc6f745c581 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-8dd13120985c4536aeefdfc6f745c5812025-02-09T12:33:26ZengNature PortfolioScientific Reports2045-23222025-02-0115111310.1038/s41598-025-89002-3Fine-grained vehicle recognition under low light conditions using EfficientNet and image enhancement on LiDAR point cloud dataGuanqiang Ruan0Tao Hu1Chenglin Ding2Kuo Yang3Fanhao Kong4Jinrun Cheng5Rong Yan61Automotive Structure and Energy Storage Engineering Center, School of Mechanical Engineering, Shanghai Dianji University1Automotive Structure and Energy Storage Engineering Center, School of Mechanical Engineering, Shanghai Dianji UniversityNormal University Tianhua College1Automotive Structure and Energy Storage Engineering Center, School of Mechanical Engineering, Shanghai Dianji University1Automotive Structure and Energy Storage Engineering Center, School of Mechanical Engineering, Shanghai Dianji University1Automotive Structure and Energy Storage Engineering Center, School of Mechanical Engineering, Shanghai Dianji UniversityAowei Technology Development Co LtdAbstract The detection and recognition of vehicles are crucial components of environmental perception in autonomous driving. Commonly used sensors include cameras and LiDAR. The performance of camera-based data collection is susceptible to environmental interference, whereas LiDAR, while unaffected by lighting conditions, can only achieve coarse-grained vehicle classification. This study introduces a novel method for fine-grained vehicle model recognition using LiDAR in low-light conditions. The approach involves collecting vehicle model data with LiDAR, performing projection transformation, enhancing the data using contrast limited adaptive histogram equalization combined with Gamma correction, and implementing vehicle model recognition based on EfficientNet. Experimental results demonstrate that the proposed method achieves an accuracy of 98.88% in fine-grained vehicle model recognition and an F1-score of 98.86%, showcasing excellent performance.https://doi.org/10.1038/s41598-025-89002-3Vehicle recognitionLiDARPoint cloudImage enhanceEfficientNet |
| spellingShingle | Guanqiang Ruan Tao Hu Chenglin Ding Kuo Yang Fanhao Kong Jinrun Cheng Rong Yan Fine-grained vehicle recognition under low light conditions using EfficientNet and image enhancement on LiDAR point cloud data Scientific Reports Vehicle recognition LiDAR Point cloud Image enhance EfficientNet |
| title | Fine-grained vehicle recognition under low light conditions using EfficientNet and image enhancement on LiDAR point cloud data |
| title_full | Fine-grained vehicle recognition under low light conditions using EfficientNet and image enhancement on LiDAR point cloud data |
| title_fullStr | Fine-grained vehicle recognition under low light conditions using EfficientNet and image enhancement on LiDAR point cloud data |
| title_full_unstemmed | Fine-grained vehicle recognition under low light conditions using EfficientNet and image enhancement on LiDAR point cloud data |
| title_short | Fine-grained vehicle recognition under low light conditions using EfficientNet and image enhancement on LiDAR point cloud data |
| title_sort | fine grained vehicle recognition under low light conditions using efficientnet and image enhancement on lidar point cloud data |
| topic | Vehicle recognition LiDAR Point cloud Image enhance EfficientNet |
| url | https://doi.org/10.1038/s41598-025-89002-3 |
| work_keys_str_mv | AT guanqiangruan finegrainedvehiclerecognitionunderlowlightconditionsusingefficientnetandimageenhancementonlidarpointclouddata AT taohu finegrainedvehiclerecognitionunderlowlightconditionsusingefficientnetandimageenhancementonlidarpointclouddata AT chenglinding finegrainedvehiclerecognitionunderlowlightconditionsusingefficientnetandimageenhancementonlidarpointclouddata AT kuoyang finegrainedvehiclerecognitionunderlowlightconditionsusingefficientnetandimageenhancementonlidarpointclouddata AT fanhaokong finegrainedvehiclerecognitionunderlowlightconditionsusingefficientnetandimageenhancementonlidarpointclouddata AT jinruncheng finegrainedvehiclerecognitionunderlowlightconditionsusingefficientnetandimageenhancementonlidarpointclouddata AT rongyan finegrainedvehiclerecognitionunderlowlightconditionsusingefficientnetandimageenhancementonlidarpointclouddata |