IVP-YOLOv5: an intelligent vehicle-pedestrian detection method based on YOLOv5s
Computer vision is now vital in intelligent vehicle environment perception systems. However, real-time small-scale pedestrian detection in intelligent vehicle environment perception systems is still needs to be improved. This paper proposes an intelligent vehicle-pedestrian detection method based on...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/09540091.2023.2168254 |
| _version_ | 1797683986141544448 |
|---|---|
| author | Yang Sun Jiankun Song Yong Li Yi Li Song Li Zehao Duan |
| author_facet | Yang Sun Jiankun Song Yong Li Yi Li Song Li Zehao Duan |
| author_sort | Yang Sun |
| collection | DOAJ |
| description | Computer vision is now vital in intelligent vehicle environment perception systems. However, real-time small-scale pedestrian detection in intelligent vehicle environment perception systems is still needs to be improved. This paper proposes an intelligent vehicle-pedestrian detection method based on YOLOv5s, named IVP-YOLOv5, to use in vehicle environment perception systems. Based on the network structure of YOLOv5s, we replaced BottleNeck CSP with Ghost-Bottleneck to reduce the complexity of processing feature maps while maintaining good detection performance. To reduce the error between the ground truth box and the predicted box, we apply Alpha-IoU as the bounding box loss function, improving pedestrian detection accuracy and robustness. We introduce the slicing-aided hyper inference (SAHI) strategy, which enables the lightweight backbone network to capture more detailed features of pedestrians by enlarging image pixels. Experiments on the BDD100 K dataset show that the proposed IVP-YOLOv5 achieves 67.1% AP and 18.5% APs of pedestrian detection, and the GFLOPs and the number of parameters are only 10.5 and 4.9M. |
| first_indexed | 2024-03-12T00:23:49Z |
| format | Article |
| id | doaj.art-1fdac917297f4699bc0136e2a299511e |
| institution | Directory Open Access Journal |
| issn | 0954-0091 1360-0494 |
| language | English |
| last_indexed | 2024-03-12T00:23:49Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj.art-1fdac917297f4699bc0136e2a299511e2023-09-15T10:48:01ZengTaylor & Francis GroupConnection Science0954-00911360-04942023-12-0135110.1080/09540091.2023.21682542168254IVP-YOLOv5: an intelligent vehicle-pedestrian detection method based on YOLOv5sYang Sun0Jiankun Song1Yong Li2Yi Li3Song Li4Zehao Duan5School of Mechanical and Equipment Engineering, Hebei University of EngineeringSchool of Mechanical and Equipment Engineering, Hebei University of EngineeringHandan Hansan Construction Engineering Company LimitedSchool of Mechanical and Equipment Engineering, Hebei University of EngineeringSchool of Mechanical and Equipment Engineering, Hebei University of EngineeringSchool of Mechanical and Equipment Engineering, Hebei University of EngineeringComputer vision is now vital in intelligent vehicle environment perception systems. However, real-time small-scale pedestrian detection in intelligent vehicle environment perception systems is still needs to be improved. This paper proposes an intelligent vehicle-pedestrian detection method based on YOLOv5s, named IVP-YOLOv5, to use in vehicle environment perception systems. Based on the network structure of YOLOv5s, we replaced BottleNeck CSP with Ghost-Bottleneck to reduce the complexity of processing feature maps while maintaining good detection performance. To reduce the error between the ground truth box and the predicted box, we apply Alpha-IoU as the bounding box loss function, improving pedestrian detection accuracy and robustness. We introduce the slicing-aided hyper inference (SAHI) strategy, which enables the lightweight backbone network to capture more detailed features of pedestrians by enlarging image pixels. Experiments on the BDD100 K dataset show that the proposed IVP-YOLOv5 achieves 67.1% AP and 18.5% APs of pedestrian detection, and the GFLOPs and the number of parameters are only 10.5 and 4.9M.http://dx.doi.org/10.1080/09540091.2023.2168254yolov5spedestrian detectionghost-bottleneckalpha-iousahi |
| spellingShingle | Yang Sun Jiankun Song Yong Li Yi Li Song Li Zehao Duan IVP-YOLOv5: an intelligent vehicle-pedestrian detection method based on YOLOv5s Connection Science yolov5s pedestrian detection ghost-bottleneck alpha-iou sahi |
| title | IVP-YOLOv5: an intelligent vehicle-pedestrian detection method based on YOLOv5s |
| title_full | IVP-YOLOv5: an intelligent vehicle-pedestrian detection method based on YOLOv5s |
| title_fullStr | IVP-YOLOv5: an intelligent vehicle-pedestrian detection method based on YOLOv5s |
| title_full_unstemmed | IVP-YOLOv5: an intelligent vehicle-pedestrian detection method based on YOLOv5s |
| title_short | IVP-YOLOv5: an intelligent vehicle-pedestrian detection method based on YOLOv5s |
| title_sort | ivp yolov5 an intelligent vehicle pedestrian detection method based on yolov5s |
| topic | yolov5s pedestrian detection ghost-bottleneck alpha-iou sahi |
| url | http://dx.doi.org/10.1080/09540091.2023.2168254 |
| work_keys_str_mv | AT yangsun ivpyolov5anintelligentvehiclepedestriandetectionmethodbasedonyolov5s AT jiankunsong ivpyolov5anintelligentvehiclepedestriandetectionmethodbasedonyolov5s AT yongli ivpyolov5anintelligentvehiclepedestriandetectionmethodbasedonyolov5s AT yili ivpyolov5anintelligentvehiclepedestriandetectionmethodbasedonyolov5s AT songli ivpyolov5anintelligentvehiclepedestriandetectionmethodbasedonyolov5s AT zehaoduan ivpyolov5anintelligentvehiclepedestriandetectionmethodbasedonyolov5s |