Research on Obstacle Detection and Distance Measurement for the Blind based on Improved YOLOv7-Tiny

Wei Shen; Liang Yang; Yuan Tao; Wanjun Yao

doi:10.6919/ICJE.202605_12(5).0013

Authors

Wei Shen
Liang Yang
Yuan Tao
Wanjun Yao

DOI:

https://doi.org/10.6919/ICJE.202605_12(5).0013

Keywords:

YOLOv7-Tiny; SimAM; Monocular Distance Measurement.

Abstract

In the daily walking process of visually impaired individuals, the accuracy of obstacle detection and distance measurement is crucial to their safety. This paper proposes an improved obstacle detection and recognition algorithm based on YOLOv7-Tiny. The algorithm adds a three-dimensional attention mechanism module, SimAM, to the Neck-to-Head part of the lightweight YOLOv7-Tiny network to enhance obstacle category features and improve the recognition accuracy of obstacle categories. At the same time, a monocular ranging method is incorporated during obstacle detection, allowing the distance of the detected obstacles to be determined simultaneously. Experimental results show that the improved model achieves an mAP@0.5 value of 91.4% in evaluation metrics, which is 2% higher than before improvement, with shorter detection time and faster detection speed. The improved model demonstrates better detection and recognition performance, validating its effectiveness.

Downloads

Download data is not yet available.

References

[1] Lecun Y., Bottou L.. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324..

[2] Russakovsky O., Deng J., Su H.,et al. Imagenet large scale visual recognition challenge[A]. International Journal of Conflict and Violence[C]. 2015:211–252.

[3] SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]. Proceedings of the International Conference on Learning Representations, 2015.

[4] Huang G , Liu Z , Maaten L V D ,et al.Densely Connected Convolutional Networks[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 2017:4700-4708.

[5] HE K, ZHANG X, REN S,et al ,Deep residual learning for image recognition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:770–778.

[6] He Yu. Research on Texture Surface Defect Classification and Detection Methods under Limited Sample Conditions [D]. Dongbei: Northeastern University, 2020.

[7] Dong Li. Automatic Detection System for Lung Nodules in CT Images Based on Deep Learning [D]. Shanghai: East China Normal University, 2022.

[8] Zhang Mengzhen. Research on the Application of Deep Learning-Based Face Recognition Technology in Smart Home [J]. Information and Computers, 2025, 37(13):5-7.

[9] Cheng P , Tang X , Liang W ,et al.Tiny-YOLOv7: Tiny Object Detection Model forDrone Imagery[C]. International Conference on Image and Graphics. Cham: Springer Nature Switzerland, 2023:53-65.

[10] YANG L, ZHANG R Y, LI L, et al. Simam: a simple, parameter⁃free attention module for convolu⁃tional neural networks[C]. Proceedings of the Inter⁃national Conference on Machine Learning, 2021:11863⁃11874.

[11] Liu S , Qi L , Qin H ,et al.Path Aggregation Network for Instance Segmentation[J]. Proceedings of the IEEE conference on computer vision and pattern recognition, 2018:8759-8768.

[12] Lin T. Y., Dollár P., Girshick R., et al. Feature pyramid networks for object detection[A]. Conference on computer vision and pattern recognition[C]. IEEE, 2017:2117-2125.