This paper proposes a lightweight traffic sign detection system based on you only look once (YOLO). Firstly, the classification to fusion (C2f) structure is integrated into the backbone network, employing deformable convolution and bi-directional feature pyramid network (BiFPN)_Concat to improve the adaptability of the network. Secondly, the simple attention module (SimAm) is embedded to prioritize key features and reduce the complexity of the model after the C2f layer at the end of the backbone network. Next, the focal efficient intersection over union (EIoU) is introduced to adjust the weights of challenging samples. Finally, we accomplish the design and deployment for the mobile app. The results demonstrate improvements, with the F1 score of 0.898 7, mean average precision (mAP)@0.5 of 98.8%, mAP@0.5: 0.95 of 75.6%, and the detection speed of 50 frames per second (FPS).
| [1] |
Fištrek T, Lončarić S. Traffic sign detection and recognition using neural networks and histogram based selection of segmentation method[C]. Proceedings of ELMAR-2011, September 14–16, 2011, Zadar, Croatia. 2011, New York, IEEE: 5154
|
| [2] |
Shopa P, Sumitha N, Patra P S K. Traffic sign detection and recognition using OpenCV[C]. Proceedings of International Conference on Information Communication and Embedded Systems (ICICES 2014), February 27–28, 2014, Chennai, India. 2014, New York, IEEE: 16
|
| [3] |
Miu X D, Li S M, Shen X, et al. . Traffic sign detection method based on visual adversarial color[J]. Journal of instrumentation. 2012, 33(01): 56-61
|
| [4] |
Zhang J, Lv Y, Tao J, et al. . A robust real-time anchor-free traffic sign detector with one-level feature[J]. IEEE transactions on emerging topics in computational intelligence. 2024
|
| [5] |
Bhatt N, Laldas P, Lobo V B. A real-time traffic sign detection and recognition system on hybrid dataset using CNN[C]. Proceedings of 2022 7th International Conference on Communication and Electronics Systems (ICCES), July 28–30, 2022, Coimbatore, India. 2022, New York, IEEE: 13541358
|
| [6] |
Girshick R, Donahue J, Darrell T, et al. . Rich feature hierarchies for accurate object detection and semantic segmentation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 23–28, 2014, Columbus, OH, USA. 2014, New York, IEEE: 580587
|
| [7] |
CUI H, WANG Y, LI Y, et al. An improved combination of faster R-CNN and U-Net network for accurate multi-modality whole heart segmentation[J]. IEEE journal of biomedical and health informatics, 2023.
|
| [8] |
Girshick R. Fast R-CNN[C]. Proceedings of the IEEE International Conference on Computer Vision (ICCV), December 11–18, 2015, Santiago, Chile. 2015, New York, IEEE: 14401448
|
| [9] |
Liu W, Anguelov D, Erhan D, et al. . SSD: single shot multibox detector[C]. Proceedings of Computer Vision-ECCV 2016: 14th European Conference, October 11–14, 2016, Amsterdam, The Netherlands. 2016, Heidelberg, Springer International Publishing: 2137
|
| [10] |
Zhang G, Wang Y M, Peng C L. Traffic sign detection algorithm based on lightweight SSD[J]. Experimental technology and management. 2024, 41(01): 63-69
|
| [11] |
Zhu N K, Zhang S D, Wang H W, et al. . Traffic sign detection based on multi-scale YOLOv5[J]. Radio engineering. 2024, 54(03): 623-632
|
| [12] |
Li Y W, Fu R, Liu F, et al. . Lightweight traffic sign detection algorithm based on improved YOLOv7[J]. Journal of Taiyuan University of Technology. 2024, 55(01): 195-203(in Chinese)
|
| [13] |
Zhang L J, Fang J J, Liu Y X, et al. . CR-YOLOv8: multiscale object detection in traffic sign images[J]. IEEE access. 2023, 12: 219-228
|
| [14] |
Tian P, Mao L. Improved road traffic sign object detection algorithm based on YOLOv8[J]. Computer engineering and applications. 2024114
|
| [15] |
Dai J, Qi H, Xiong Y, et al. . Deformable convolutional networks[C]. Proceedings of the IEEE International Conference on Computer Vision (ICCV), October 22–29, 2017, Venice, Italy. 2017, New York, IEEE: 764773
|
| [16] |
Tan M, Pang R, Le Q V. EfficientDet: scalable and efficient object detection[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 14–19, 2020, Seattle, WA, USA. 2020, New York, IEEE: 1078110790
|
| [17] |
Yang L, Zhang R Y, Li L, et al. . SimAM: a simple, parameter-free attention module for convolutional neural networks[C]. Proceedings of the International Conference on Machine Learning (ICML), July 18–24, 2021, Virtual. PMLR. 20211186311874
|
| [18] |
Zhang Y F, Ren W, Zhang Z, et al. . Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing. 2022, 506: 146-157
|
| [19] |
Liu H B, Zhang Y B, Zhou K, et al. . Traffic sign detection algorithm based on improved YOLOv5-S[J]. Journal of computer engineering & applications. 2024, 60(5): 200-209
|
| [20] |
Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 18–22, 2023, Vancouver, BC, Canada. 2023, New York, IEEE: 74647475
|
RIGHTS & PERMISSIONS
Tianjin University of Technology
PDF
