Truck scale systems are often located in complex industrial environments, and existing inspection methods based on the appearance of an entire vehicle are difficult to accurately locate trucks in space-constrained scenarios. This study proposes GSP-YOLO, a tire detection algorithm for truck scale scenarios based on an improved YOLOv8n, that assists in locating trucks on the scale by detecting tires and enhances the detection performance in industrial environments. GSP-YOLO incorporates a global-to-local spatial aggregation module into the neck structure to improve the perception of tires on small scales. A shared detail-enhanced convolutional detection head is designed in the detection head to enhance its ability to recognize complex features while reducing the computational cost. The model also replaces conventional convolution with poly-scale convolution to enhance object recognition capability and reduce feature loss. Additionally, the wise-intersection over union loss function is employed as the bounding box regression loss to suppress competition among high-quality anchors and reduce the impact of low-quality samples, thereby improving detection performance. The experimental results demonstrated that GSP-YOLO achieves an mAP50 of 89.3% on the dataset, representing a 2.0% improvement over the baseline model, and an increase of 0.9% in mAP50–95. This model significantly enhances the detection capability within truck scale systems and ensures reliable performance in complex industrial environments.

1. [1] R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” 2014 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 580-587, 2014. https://doi.org/10.1109/CVPR.2014.81
2. [2] R. Girshick, “Fast R-CNN,” 2015 IEEE Int. Conf. on Computer Vision, pp. 1440-1448, 2015. https://doi.org/10.1109/ICCV.2015.169
3. [3] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.39, No.6, pp. 1137-1149, 2017. https://doi.org/10.1109/TPAMI.2016.2577031
4. [4] K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” 2017 IEEE Int. Conf. on Computer Vision, pp. 2980-2988, 2017. https://doi.org/10.1109/ICCV.2017.322
5. [5] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” 2017 IEEE Int. Conf. on Computer Vision, pp. 2999-3007, 2017. https://doi.org/10.1109/ICCV.2017.324
6. [6] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” 2016 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 779-788, 2016. https://doi.org/10.1109/CVPR.2016.91
7. [7] J. Redmon and A. Farhadi, “YOLO9000: Better, faster, stronger,” 2017 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 6517-6525, 2017. https://doi.org/10.1109/CVPR.2017.690
8. [8] J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv:1804.02767, 2018. https://doi.org/10.48550/arXiv.1804.02767
9. [9] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv:2004.10934, 2020. https://doi.org/10.48550/arXiv.2004.10934
10. [10] C. Li et al., “YOLOv6: A single-stage object detection framework for industrial applications,” arXiv:2209.02976, 2022. https://doi.org/10.48550/arXiv.2209.02976
11. [11] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” 2023 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 7464-7475, 2023. https://doi.org/10.1109/CVPR52729.2023.00721
12. [12] W. Liu et al., “SSD: Single shot multibox detector,” Proc. of the 14th European Conf. on Computer Vision, Part 1, pp. 21-37, 2016. https://doi.org/10.1007/978-3-319-46448-0_2
13. [13] F. Tang et al., “DuAT: Dual-aggregation transformer network for medical image segmentation,” Proc. of the 6th Chinese Conf. on Pattern Recognition and Computer Vision, Part 5, pp. 343-356, 2023. https://doi.org/10.1007/978-981-99-8469-5_27
14. [14] D. Li, A. Yao, and Q. Chen, “PSConv: Squeezing feature pyramid into one compact poly-scale convolutional layer,” Proc. of the 16th European Conf. on Computer Vision, Part 21, pp. 615-632, 2020. https://doi.org/10.1007/978-3-030-58589-1_37
15. [15] Z. Tong, Y. Chen, Z. Xu, and R. Yu, “Wise-IoU: Bounding box regression loss with dynamic focusing mechanism,” arXiv:2301.10051, 2023. https://doi.org/10.48550/arXiv.2301.10051
16. [16] K. He, X. Zhang, S. Ren, and J. Sun, “Spatial pyramid pooling in deep convolutional networks for visual recognition,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.37, No.9, pp. 1904-1916, 2015. https://doi.org/10.1109/TPAMI.2015.2389824
17. [17] T.-Y. Lin et al., “Feature pyramid networks for object detection,” 2017 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 936-944, 2017. https://doi.org/10.1109/CVPR.2017.106
18. [18] S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, “Path aggregation network for instance segmentation,” 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 8759-8768, 2018. https://doi.org/10.1109/CVPR.2018.00913
19. [19] X.-Y. Li, Z.-X. Wei, and Y.-L. Yang, “Research on the application of HOG and SVM for wheel recognition in weigh-in-motion,” J. of Highway and Transportation Research and Development (English Edition), Vol.15, No.3, pp. 102-110, 2021. https://doi.org/10.1061/JHTRCQ.0000793
20. [20] E. J. OBrien, C. C. Caprani, S. Blacoe, D. Guo, and A. Malekjafarian, “Detection of vehicle wheels from images using a pseudo-wavelet filter for analysis of congested traffic,” IET Image Processing, Vol.12, No.12, pp. 2222-2228, 2018. https://doi.org/10.1049/iet-ipr.2018.5369
21. [21] Y.-S. Ruan, I.-C. Chang, and H.-Y. Yeh, “Vehicle detection based on wheel part detection,” 2017 IEEE Int. Conf. on Consumer Electronics – Taiwan, pp. 187-188, 2017. https://doi.org/10.1109/ICCE-China.2017.7991058
22. [22] S. Ghanem and R. A. Kerekes, “Robust wheel detection for vehicle re-identification,” Sensors, Vol.23, No.1, Article No.393, 2023. https://doi.org/10.3390/s23010393
23. [23] M. Shenoda, “Lighting and rotation invariant real-time vehicle wheel detector based on YOLOv5,” arXiv:2305.17785, 2023. https://doi.org/10.48550/arXiv.2305.17785
24. [24] Z. Chen, Z. He, and Z.-M. Lu, “DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention,” IEEE Trans. on Image Processing, Vol.33, pp. 1002-1015, 2024. https://doi.org/10.1109/TIP.2024.3354108
25. [25] Y. Wu and K. He, “Group normalization,” Proc. of the 15th European Conf. on Computer Vision, Part 13, pp. 3-19, 2018. https://doi.org/10.1007/978-3-030-01261-8_1
26. [26] Z. Zheng et al., “Enhancing geometric factors in model learning and inference for object detection and instance segmentation,” IEEE Trans. on Cybernetics, Vol.52, No.8, pp. 8574-8586, 2022. https://doi.org/10.1109/TCYB.2021.3095305
27. [27] X. Dai et al., “Dynamic head: Unifying object detection heads with attentions,” 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 7369-7378, 2021. https://doi.org/10.1109/CVPR46437.2021.00729
28. [28] Z. Yu et al., “YOLO-FaceV2: A scale and occlusion aware face detector,” Pattern Recognition, Vol.155, Article No.110714, 2024. https://doi.org/10.1016/j.patcog.2024.110714
29. [29] Z. Zheng et al., “Distance-IoU loss: Faster and better learning for bounding box regression,” Proc. of the AAAI Conf. on Artificial Intelligence, Vol.34, No.7, pp. 12993-13000, 2020. https://doi.org/10.1609/aaai.v34i07.6999
30. [30] Z. Gevorgyan, “SIoU loss: More powerful learning for bounding box regression,” arXiv:2205.12740, 2022. https://doi.org/10.48550/arXiv.2205.12740
31. [31] H. Rezatofighi et al., “Generalized intersection over union: A metric and a loss for bounding box regression,” 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 658-666, 2019. https://doi.org/10.1109/CVPR.2019.00075
32. [32] R. L. Draelos and L. Carin, “Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks,” arXiv:2011.08891, 2020. https://doi.org/10.48550/arXiv.2011.08891