TCTP-YOLO：盲人出行的典型障碍物及交通标志检测方法

doi:10.3778/j.issn.1673-9418.2411076

摘要/Abstract

摘要： 针对机器导盲犬在行进过程中面临的红绿灯等小目标和斑马线等边缘特征不清晰样本目标的检测难题，以及背景多变导致的漏检、错检和重复检测问题，提出一种改进的YOLOv8盲人出行的典型障碍物及交通标志检测方法。在YOLOv8的主干网络中引入Triplet Attention注意力机制，通过加强捕捉序列中的时序关系和强化局部区域的相关性，显著提升模型对复杂环境中关键目标的识别能力。此外，算法融合CSFF模块和TFE模块，结合局部和全局特征信息，获得更加精确的特征表示，从而提高检测的准确性。为了进一步提升对小目标的检测能力，算法结合小目标检测头P2，通过提取较低分辨率的特征来帮助识别红绿灯等小目标，增强模型的多尺度检测能力。同时，采用Focaler-WIoU损失函数，有效减小样本产生的有害梯度，进一步优化模型的训练过程。通过特征蒸馏技术对改进后的算法进行精度提升，确保模型在实际应用中的高效性和鲁棒性。实验结果表明，改进后的算法在参数量减少17.2%的情况下，平均准确率达到了93.5%，查准率为92.8%。这一改进不仅显著提升机器导盲犬在复杂环境中的目标检测能力，还为后续的局部路径规划研究提供更为准确的检测信息，具有重要的实际应用价值。

关键词: 深度学习, 障碍物检测, 交通标志检测, 注意力机制, 知识蒸馏

Abstract: In response to the challenges faced by machine guide dogs in detecting small targets such as traffic lights and unclear edge features like zebra crossings during navigation, as well as issues of missed detection, false detection, and repeated detection caused by varying backgrounds, this paper proposes an improved YOLOv8-based method for detecting typical obstacles and traffic signs for blind pedestrians. The method introduces the Triplet Attention mechanism into the backbone network of YOLOv8, significantly enhancing the model??s ability to recognize key targets in complex environments by strengthening the capture of temporal relationships in sequences and reinforcing the correlation of local regions. Additionally, the algorithm integrates the CSFF (cross scale feature fusion) module and the TFE (triple feature encoding) module, combining local and global feature information to obtain more precise feature representations, thereby improving detection accuracy. To further enhance the detection capability for small targets, this algorithm incorporates a small target detection head P2, which assists in identifying small targets such as traffic lights by extracting lower-resolution features, thereby enhancing the model??s multi-scale detection ability. At the same time, the Focaler-WIoU loss function is adopted to effectively reduce harmful gradients generated by samples, further optimizing the model??s training process. Finally, feature distillation technology is employed to improve the accuracy of the enhanced algorithm, ensuring the model??s efficiency and robustness in practical applications. Experimental results demonstrate that the improved algorithm achieves an average accuracy of 93.5% and a precision rate of 92.8% while reducing the number of parameters by 17.2%. This improvement not only significantly enhances the target detection capability of machine guide dogs in complex environments but also provides more accurate detection information for subsequent research on local path planning, holding significant practical value.

Key words: deep learning, obstacle detection, traffic sign detection, attention mechanism, knowledge distillation

李云飞, 魏霞, 蔡鑫, 吕明昱, 罗相涵. TCTP-YOLO：盲人出行的典型障碍物及交通标志检测方法[J]. 计算机科学与探索, 2025, 19(6): 1540-1552.

LI Yunfei, WEI Xia, CAI Xin, LYU Mingyu, LUO Xianghan. TCTP-YOLO: Typical Obstacles and Traffic Sign Detection Methods for Blind Pedestrians[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(6): 1540-1552.

参考文献

[1] 武曌晗, 荣学文, 范永. 导盲机器人研究现状综述[J]. 计算机工程与应用, 2020, 56(14): 1-13.
WU Z H, RONG X W, FAN Y. Survey on research status of blind-guiding robots[J]. Computer Engineering and Applications, 2020, 56(14): 1-13.
[2] BEN ATITALLAH A, SAID Y, BEN ATITALLAH M A, et al. An effective obstacle detection system using deep learning advantages to aid blind and visually impaired navigation[J]. Ain Shams Engineering Journal, 2024, 15(2): 102387.
[3] 刘源, 张荣芬, 刘宇红, 等. 基于CE-YOLOX的导盲系统障碍物检测方法[J]. 液晶与显示, 2023, 38(9): 1281-1292.
LIU Y, ZHANG R F, LIU Y H, et al. Obstacle detection method for guide system based on CE-YOLOX[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(9): 1281-1292.
[4] VIOLA P, JONES M. Robust real-time face detection[C]// Proceedings of the 8th IEEE International Conference on Computer Vision. Piscataway: IEEE, 2001: 747.
[5] VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2001.
[6] WANG X Y, YANG M, ZHU S H, et al. Regionlets for generic object detection[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 17-24.
[7] FELZENSZWALB P, MCALLESTER D, RAMANAN D. A discriminatively trained, multiscale, deformable part model[C]//Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2008: 1-8.
[8] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587.
[9] ANTUN V, RENNA F, POON C, et al. On instabilities of deep learning in image reconstruction and the potential costs of AI[J]. Proceedings of the National Academy of Sciences of the United States of America, 2020, 117(48): 30088-30095.
[10] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788.
[11] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6517-6525.
[12] FARHADI A, REDMON J. YOLOv3: an incremental improvement[EB/OL]. [2024-09-15]. https://arxiv.org/abs/1804. 02767.
[13] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 1-17.
[14] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Proceedings of the 14th European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
[15] 古佳欣, 陈高华, 张春美. YOLOv8-DEL:基于改进YOLOv8n的实时车辆检测算法研究[J]. 计算机工程与应用, 2025, 61(1): 142-152.
GU J X, CHEN G H, ZHANG C M. YOLOv8-DEL: research on real-time vehicle detection algorithm based on improved YOLOv8n[J]. Computer Engineering and Applications, 2025, 61(1): 142-152.
[16] 张小艳, 王苗. 改进的YOLOv8n轻量化景区行人检测方法研究[J]. 计算机工程与应用, 2025, 61(2): 84-96.
ZHANG X Y, WANG M. Research on improved YOLOv8n light-weight pedestrian detection method in scenic spots[J]. Computer Engineering and Applications, 2025, 61(2): 84-96.
[17] 赵磊, 李栋. PMM-YOLO: 多尺度特征融合的交通标志检测算法[J]. 计算机工程与应用, 2025, 61(4): 262-271.
ZHAO L, LI D. PMM-YOLO: traffic sign detection algorithm with multi-scale feature fusion[J]. Computer Engineering and Applications, 2025, 61(4): 262-271.
[18] LINDEBERG T. Scale-space theory in computer vision[M]. Boston: Springer US, 1994.
[19] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[20] TRAN D, BOURDEV L, FERGUS R, et al. Learning spatio-temporal features with 3D convolutional networks[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 4489-4497.
[21] PARK H J, KANG J W, KIM B G. ssFPN: scale sequence (S2) feature-based feature pyramid network for object detection[J]. Sensors, 2023, 23(9): 4432.
[22] RUKUNDO O, CAO H Q. Nearest neighbor value interpolation[EB/OL]. [2024-09-15]. https://arxiv.org/abs/1211.1768.
[23] ELFWING S, UCHIBE E, DOYA K. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning[J]. Neural Networks, 2018, 107: 3-11.
[24] TONG Z J, CHEN Y H, XU Z W, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[EB/OL]. [2024-09-15]. https://arxiv.org/abs/2301.10051.
[25] ZHANG H, ZHANG S J. Focaler-IoU: more focused intersection over union loss[EB/OL]. [2024-09-15]. https://arxiv.org/abs/2401.10525.
[26] SHU C Y, LIU Y F, GAO J F, et al. Channel-wise knowledge distillation for dense prediction[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 5291-5300.
[27] KANG M, TING C M, TING F F, et al. ASF-YOLO: a novel YOLO model with attentional scale sequence fusion for cell instance segmentation[J]. Image and Vision Computing, 2024, 147: 105057.
[28] WAN D H, LU R S, SHEN S Y, et al. Mixed local channel attention for object detection[J]. Engineering Applications of Artificial Intelligence, 2023, 123: 106442.
[29] XIA Z F, PAN X R, SONG S J, et al. Vision transformer with deformable attention[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 4784-4793.
[30] DA M, JIANG L, TAO Y F, et al. Infrared target detection algorithm based on multipath coordinate attention mechanism[J]. Measurement Science and Technology, 2025, 36(1): 015208.
[31] HUANG H J, CHEN Z G, ZOU Y, et al. Channel prior convolutional attention for medical image segmentation[J]. Computers in Biology and Medicine, 2024, 178: 108784.
[32] OUYANG D L, HE S, ZHANG G Z, et al. Efficient multi-scale attention module with cross-spatial learning[C]//Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2023: 1-5.
[33] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE/CVF Conference on Com-puter Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141.