Research on Visual Perception of Speed Bumps for Intelligent Connected Vehicles Based on Lightweight FPNet
In the field of intelligent connected vehicles, the precise and real-time identification of speed bumps is critically important for the safety of autonomous driving. To address the issue that existing visual perception algorithms struggle to simultaneously maintain identification accuracy and real-t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/7/2130 |
| _version_ | 1797211930318864384 |
|---|---|
| author | Ruochen Wang Xiaoguo Luo Qing Ye Yu Jiang Wei Liu |
| author_facet | Ruochen Wang Xiaoguo Luo Qing Ye Yu Jiang Wei Liu |
| author_sort | Ruochen Wang |
| collection | DOAJ |
| description | In the field of intelligent connected vehicles, the precise and real-time identification of speed bumps is critically important for the safety of autonomous driving. To address the issue that existing visual perception algorithms struggle to simultaneously maintain identification accuracy and real-time performance amidst image distortion and complex environmental conditions, this study proposes an enhanced lightweight neural network framework, YOLOv5-FPNet. This framework strengthens perception capabilities in two key phases: feature extraction and loss constraint. Firstly, FPNet, based on FasterNet and Dynamic Snake Convolution, is developed to adaptively extract structural features of distorted speed bumps with accuracy. Subsequently, the C3-SFC module is proposed to augment the adaptability of the neck and head components to distorted features. Furthermore, the SimAM attention mechanism is embedded within the backbone to enhance the ability of key feature extraction. Finally, an adaptive loss function, Inner–WiseIoU, based on a dynamic non-monotonic focusing mechanism, is designed to improve the generalization and fitting ability of bounding boxes. Experimental evaluations on a custom speed bumps dataset demonstrate the superior performance of FPNet, with significant improvements in key metrics such as the mAP, mAP50_95, and FPS by 38.76%, 143.15%, and 51.23%, respectively, compared to conventional lightweight neural networks. Ablation studies confirm the effectiveness of the proposed improvements. This research provides a fast and accurate speed bump detection solution for autonomous vehicles, offering theoretical insights for obstacle recognition in intelligent vehicle systems. |
| first_indexed | 2024-04-24T10:34:19Z |
| format | Article |
| id | doaj.art-2bcb399d808f4e24b01c8ec3d885a0f5 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-24T10:34:19Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2bcb399d808f4e24b01c8ec3d885a0f52024-04-12T13:26:17ZengMDPI AGSensors1424-82202024-03-01247213010.3390/s24072130Research on Visual Perception of Speed Bumps for Intelligent Connected Vehicles Based on Lightweight FPNetRuochen Wang0Xiaoguo Luo1Qing Ye2Yu Jiang3Wei Liu4School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, ChinaSchool of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, ChinaAutomotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, ChinaSchool of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, ChinaSchool of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, ChinaIn the field of intelligent connected vehicles, the precise and real-time identification of speed bumps is critically important for the safety of autonomous driving. To address the issue that existing visual perception algorithms struggle to simultaneously maintain identification accuracy and real-time performance amidst image distortion and complex environmental conditions, this study proposes an enhanced lightweight neural network framework, YOLOv5-FPNet. This framework strengthens perception capabilities in two key phases: feature extraction and loss constraint. Firstly, FPNet, based on FasterNet and Dynamic Snake Convolution, is developed to adaptively extract structural features of distorted speed bumps with accuracy. Subsequently, the C3-SFC module is proposed to augment the adaptability of the neck and head components to distorted features. Furthermore, the SimAM attention mechanism is embedded within the backbone to enhance the ability of key feature extraction. Finally, an adaptive loss function, Inner–WiseIoU, based on a dynamic non-monotonic focusing mechanism, is designed to improve the generalization and fitting ability of bounding boxes. Experimental evaluations on a custom speed bumps dataset demonstrate the superior performance of FPNet, with significant improvements in key metrics such as the mAP, mAP50_95, and FPS by 38.76%, 143.15%, and 51.23%, respectively, compared to conventional lightweight neural networks. Ablation studies confirm the effectiveness of the proposed improvements. This research provides a fast and accurate speed bump detection solution for autonomous vehicles, offering theoretical insights for obstacle recognition in intelligent vehicle systems.https://www.mdpi.com/1424-8220/24/7/2130intelligent connected vehiclesautonomous drivingvisual perceptionspeed bumpsYOLOv5deep learning |
| spellingShingle | Ruochen Wang Xiaoguo Luo Qing Ye Yu Jiang Wei Liu Research on Visual Perception of Speed Bumps for Intelligent Connected Vehicles Based on Lightweight FPNet Sensors intelligent connected vehicles autonomous driving visual perception speed bumps YOLOv5 deep learning |
| title | Research on Visual Perception of Speed Bumps for Intelligent Connected Vehicles Based on Lightweight FPNet |
| title_full | Research on Visual Perception of Speed Bumps for Intelligent Connected Vehicles Based on Lightweight FPNet |
| title_fullStr | Research on Visual Perception of Speed Bumps for Intelligent Connected Vehicles Based on Lightweight FPNet |
| title_full_unstemmed | Research on Visual Perception of Speed Bumps for Intelligent Connected Vehicles Based on Lightweight FPNet |
| title_short | Research on Visual Perception of Speed Bumps for Intelligent Connected Vehicles Based on Lightweight FPNet |
| title_sort | research on visual perception of speed bumps for intelligent connected vehicles based on lightweight fpnet |
| topic | intelligent connected vehicles autonomous driving visual perception speed bumps YOLOv5 deep learning |
| url | https://www.mdpi.com/1424-8220/24/7/2130 |
| work_keys_str_mv | AT ruochenwang researchonvisualperceptionofspeedbumpsforintelligentconnectedvehiclesbasedonlightweightfpnet AT xiaoguoluo researchonvisualperceptionofspeedbumpsforintelligentconnectedvehiclesbasedonlightweightfpnet AT qingye researchonvisualperceptionofspeedbumpsforintelligentconnectedvehiclesbasedonlightweightfpnet AT yujiang researchonvisualperceptionofspeedbumpsforintelligentconnectedvehiclesbasedonlightweightfpnet AT weiliu researchonvisualperceptionofspeedbumpsforintelligentconnectedvehiclesbasedonlightweightfpnet |