YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s
Abstract In computer vision, timely and accurate execution of object identification tasks is critical. However, present road damage detection approaches based on deep learning suffer from complex models and computationally time-consuming issues. To address these issues, we present a lightweight mode...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-10-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13634-022-00931-x |
| _version_ | 1797986082022752256 |
|---|---|
| author | Fang Wan Chen Sun Hongyang He Guangbo Lei Li Xu Teng Xiao |
| author_facet | Fang Wan Chen Sun Hongyang He Guangbo Lei Li Xu Teng Xiao |
| author_sort | Fang Wan |
| collection | DOAJ |
| description | Abstract In computer vision, timely and accurate execution of object identification tasks is critical. However, present road damage detection approaches based on deep learning suffer from complex models and computationally time-consuming issues. To address these issues, we present a lightweight model for road damage identification by enhancing the YOLOv5s approach. The resulting algorithm, YOLO-LRDD, provides a good balance of detection precision and speed. First, we propose the novel backbone network Shuffle-ECANet by adding an ECA attention module into the lightweight model ShuffleNetV2. Second, to ensure reliable detection, we employ BiFPN rather than the original feature pyramid network since it improves the network's capacity to describe features. Moreover, in the model training phase, localization loss is modified to Focal-EIOU in order to get higher-quality anchor box. Lastly, we augment the well-known RDD2020 dataset with many samples of Chinese road scenes and compare YOLO-LRDD against several state-of-the-art object detection techniques. The smaller model of our YOLO-LRDD offers superior performance in terms of accuracy and efficiency, as determined by our experiments. Compared to YOLOv5s in particular, YOLO-LRDD improves single image recognition speed by 22.3% and reduces model size by 28.8% while maintaining comparable accuracy. In addition, it is easier to implant in mobile devices because its model is smaller and lighter than those of the other approaches. |
| first_indexed | 2024-04-11T07:28:29Z |
| format | Article |
| id | doaj.art-2a072116efd04194b5d9aa1e927bb580 |
| institution | Directory Open Access Journal |
| issn | 1687-6180 |
| language | English |
| last_indexed | 2024-04-11T07:28:29Z |
| publishDate | 2022-10-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-2a072116efd04194b5d9aa1e927bb5802022-12-22T04:37:01ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61802022-10-012022111810.1186/s13634-022-00931-xYOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5sFang Wan0Chen Sun1Hongyang He2Guangbo Lei3Li Xu4Teng Xiao5School of Computer Science, Hubei University of TechnologySchool of Computer Science, Hubei University of TechnologyCollege of Engineering and Physical Sciences, The University of BirminghamSchool of Computer Science, Hubei University of TechnologySchool of Computer Science, Hubei University of TechnologySchool of Computer Science, Hubei University of TechnologyAbstract In computer vision, timely and accurate execution of object identification tasks is critical. However, present road damage detection approaches based on deep learning suffer from complex models and computationally time-consuming issues. To address these issues, we present a lightweight model for road damage identification by enhancing the YOLOv5s approach. The resulting algorithm, YOLO-LRDD, provides a good balance of detection precision and speed. First, we propose the novel backbone network Shuffle-ECANet by adding an ECA attention module into the lightweight model ShuffleNetV2. Second, to ensure reliable detection, we employ BiFPN rather than the original feature pyramid network since it improves the network's capacity to describe features. Moreover, in the model training phase, localization loss is modified to Focal-EIOU in order to get higher-quality anchor box. Lastly, we augment the well-known RDD2020 dataset with many samples of Chinese road scenes and compare YOLO-LRDD against several state-of-the-art object detection techniques. The smaller model of our YOLO-LRDD offers superior performance in terms of accuracy and efficiency, as determined by our experiments. Compared to YOLOv5s in particular, YOLO-LRDD improves single image recognition speed by 22.3% and reduces model size by 28.8% while maintaining comparable accuracy. In addition, it is easier to implant in mobile devices because its model is smaller and lighter than those of the other approaches.https://doi.org/10.1186/s13634-022-00931-xRoad damage detectionLightweightObject detectionYOLOv5sDeep learning |
| spellingShingle | Fang Wan Chen Sun Hongyang He Guangbo Lei Li Xu Teng Xiao YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s EURASIP Journal on Advances in Signal Processing Road damage detection Lightweight Object detection YOLOv5s Deep learning |
| title | YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s |
| title_full | YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s |
| title_fullStr | YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s |
| title_full_unstemmed | YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s |
| title_short | YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s |
| title_sort | yolo lrdd a lightweight method for road damage detection based on improved yolov5s |
| topic | Road damage detection Lightweight Object detection YOLOv5s Deep learning |
| url | https://doi.org/10.1186/s13634-022-00931-x |
| work_keys_str_mv | AT fangwan yololrddalightweightmethodforroaddamagedetectionbasedonimprovedyolov5s AT chensun yololrddalightweightmethodforroaddamagedetectionbasedonimprovedyolov5s AT hongyanghe yololrddalightweightmethodforroaddamagedetectionbasedonimprovedyolov5s AT guangbolei yololrddalightweightmethodforroaddamagedetectionbasedonimprovedyolov5s AT lixu yololrddalightweightmethodforroaddamagedetectionbasedonimprovedyolov5s AT tengxiao yololrddalightweightmethodforroaddamagedetectionbasedonimprovedyolov5s |