Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios
Object detection in road scenarios is crucial for intelligent transport systems and autonomous driving, but complex traffic conditions pose significant challenges. This paper introduces Z-You Only Look Once version 8 small (Z-YOLOv8s), designed to improve both accuracy and real-time efficiency under...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/113306/ http://psasir.upm.edu.my/id/eprint/113306/1/113306.pdf |
| _version_ | 1848866186985472000 |
|---|---|
| author | Zhao, Ruixin Tang, Sai Hong Supeni, Eris Elianddy Abdul Rahim, Sharafiz Fan, Luxin |
| author_facet | Zhao, Ruixin Tang, Sai Hong Supeni, Eris Elianddy Abdul Rahim, Sharafiz Fan, Luxin |
| author_sort | Zhao, Ruixin |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Object detection in road scenarios is crucial for intelligent transport systems and autonomous driving, but complex traffic conditions pose significant challenges. This paper introduces Z-You Only Look Once version 8 small (Z-YOLOv8s), designed to improve both accuracy and real-time efficiency under real-world uncertainties. By incorporating Revisiting Perspective Vision Transformer (RepViT) and C2f into the YOLOv8s framework, and integrating the Large Selective Kernel Network (LSKNet), the model enhances spatial feature extraction. Additionally, the YOLOv8s backbone is optimized with Space-to-Depth Convolution (SPD-Conv) for better small object detection. The Softpool-Spatial Pyramid Pooling Fast (SoftPool-SPPF) module ensures precise characteristic information preservation. Z-YOLOv8s improves mean average precision (mAP)@0.5 on the Berkeley Deep Drive 100 K (BDD100K) and Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) datasets by 7.3 % and 3.8 %, respectively. It also achieves accuracy increases of 5.7 % and 6.5 % in Average Precision (AP)-Small, and a real-time detection speed of 78.41 frames per second (FPS) on the BDD100K. Z-YOLOv8s balances detection precision and processing speed more effectively than other detectors, as demonstrated by experimental results and comparisons. |
| first_indexed | 2025-11-15T14:16:36Z |
| format | Article |
| id | upm-113306 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:16:36Z |
| publishDate | 2024 |
| publisher | Elsevier |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1133062024-11-20T05:59:57Z http://psasir.upm.edu.my/id/eprint/113306/ Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios Zhao, Ruixin Tang, Sai Hong Supeni, Eris Elianddy Abdul Rahim, Sharafiz Fan, Luxin Object detection in road scenarios is crucial for intelligent transport systems and autonomous driving, but complex traffic conditions pose significant challenges. This paper introduces Z-You Only Look Once version 8 small (Z-YOLOv8s), designed to improve both accuracy and real-time efficiency under real-world uncertainties. By incorporating Revisiting Perspective Vision Transformer (RepViT) and C2f into the YOLOv8s framework, and integrating the Large Selective Kernel Network (LSKNet), the model enhances spatial feature extraction. Additionally, the YOLOv8s backbone is optimized with Space-to-Depth Convolution (SPD-Conv) for better small object detection. The Softpool-Spatial Pyramid Pooling Fast (SoftPool-SPPF) module ensures precise characteristic information preservation. Z-YOLOv8s improves mean average precision (mAP)@0.5 on the Berkeley Deep Drive 100 K (BDD100K) and Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) datasets by 7.3 % and 3.8 %, respectively. It also achieves accuracy increases of 5.7 % and 6.5 % in Average Precision (AP)-Small, and a real-time detection speed of 78.41 frames per second (FPS) on the BDD100K. Z-YOLOv8s balances detection precision and processing speed more effectively than other detectors, as demonstrated by experimental results and comparisons. Elsevier 2024-11 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/113306/1/113306.pdf Zhao, Ruixin and Tang, Sai Hong and Supeni, Eris Elianddy and Abdul Rahim, Sharafiz and Fan, Luxin (2024) Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios. Alexandria Engineering Journal, 106. pp. 298-311. ISSN 1110-0168 https://www.sciencedirect.com/science/article/pii/S1110016824007300 10.1016/j.aej.2024.07.011 |
| spellingShingle | Zhao, Ruixin Tang, Sai Hong Supeni, Eris Elianddy Abdul Rahim, Sharafiz Fan, Luxin Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios |
| title | Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios |
| title_full | Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios |
| title_fullStr | Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios |
| title_full_unstemmed | Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios |
| title_short | Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios |
| title_sort | z-yolov8s-based approach for road object recognition in complex traffic scenarios |
| url | http://psasir.upm.edu.my/id/eprint/113306/ http://psasir.upm.edu.my/id/eprint/113306/ http://psasir.upm.edu.my/id/eprint/113306/ http://psasir.upm.edu.my/id/eprint/113306/1/113306.pdf |