Improved YOLOv5-Based Lightweight Object Detection Algorithm for People with Visual Impairment to Detect Buses
Source abstract
Abstract
Object detection is crucial for individuals with visual impairment, especially when waiting for a bus. In this study, we propose a lightweight and highly accurate bus detection model based on an improved version of the YOLOv5 model. We propose integrating the GhostConv and C3Ghost Modules into the YOLOv5 network to reduce the number of parameters and floating-point operations per second (FLOPs), ensuring detection accuracy while reducing the model parameters. Following that, we added the SimSPPF module to replace the SPPF in the YOLOv5 backbone for increased computational efficiency and accurate object detection capabilities. Finally, we developed a Slim scale detection model by modifying the original YOLOv5 structure in order to make the model more efficient and faster, which is critical for real-time object detection applications. According to the experimental results, the Improved-YOLOv5 outperforms the original YOLOv5 in terms of the precision, recall, and mAP@0.5. Further analysis of the model complexity reveals that the Improved-YOLOv5 is more efficient due to fewer FLOPS, with fewer parameters, less memory usage, and faster inference time capabilities. The proposed model is smaller and more feasible to implement in resource-constrained mobile devices and a promising option for bus detection systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Retinal Imaging and Analysis · Visual Attention and Saliency Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, 2-4 Hibikino, Wakamatsu-ku, Kitakyushu 808-0196, Japan
Funding
Ministry of Education, Culture, Sports, Science and Technology of Japan (MEXT)
References (33)
Show source-provided references
1. World Health Organization (WHO) (2023, February 22). Blindness and Vision Impairment. Available online: https://www.who.int/news-room/fact-sheets/detail/blindness-and-visual-impairment.
2. Transportation: An electronic survey of persons who are blind or visually impaired10.1177/0145482X1510900603 ↗
3. Azenkot, S., Prasain, S., Borning, A., Fortuna, E., Ladner, R.E., and Wobbrock, J.O. (2011, January 7–12). Enhancing independence and safety for blind and deaf-blind public transit riders. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Vancouver, BC, Canada.10.1145/1978942.1979424 ↗
4. El Alamy, L., Lhaddad, S., Maalal, S., Taybi, Y., and Salih-Alj, Y. (2012, January 12–14). Bus identification system for visually impaired person. Proceedings of the 2012 Sixth International Conference on Next Generation Mobile Applications, Services and Technologies, Paris, France.10.1109/NGMAST.2012.22 ↗
5. RFID-based automatic bus ticketing: Features and trends10.1088/1757-899X/114/1/012146 ↗
6. Al Kalbani, J., Suwailam, R.B., Al Yafai, A., Al Abri, D., and Awadalla, M. (2015, January 1–4). Bus detection system for blind people using RFID. Proceedings of the 2015 IEEE 8th GCC Conference & Exhibition, Muscat, Oman.10.1109/IEEEGCC.2015.7060038 ↗
7. Abdullah, S., Noor, N.M., and Ghazali, M.Z. (2014, January 24–26). Mobility recognition system for the visually impaired. Proceedings of the 2014 IEEE 2nd International Symposium on Telecommunication Technologies (ISTT), Langkawi, Malaysia.10.1109/ISTT.2014.7238236 ↗
8. Raj, J.T., and Sankar, J. (2017, January 21–23). IoT based smart school bus monitoring and notification system. Proceedings of the 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Dhaka, Bangladesh.10.1109/R10-HTC.2017.8288913 ↗
9. Yelamarthi, K., Haas, D., Nielsen, D., and Mothersell, S. (2010, January 1–4). RFID and GPS integrated navigation system for the visually impaired. Proceedings of the 2010 53rd IEEE International Midwest Symposium on Circuits and Systems, Seattle, WA, USA.10.1109/MWSCAS.2010.5548863 ↗
10. Shah, S., and Singh, B. (2016, January 6–8). RFID based school bus tracking and security system. Proceedings of the 2016 International Conference on Communication and Signal Processing (ICCSP), Melmaruvathur, India.10.1109/ICCSP.2016.7754404 ↗
11. Modeling RFID signal reflection for contact-free activity recognition
12. A Deep Learning Model for Transportation Mode Detection Based on Smartphone Sensing Data10.1109/TITS.2019.2951165 ↗
13. Espinosa, J.E., Velastin, S.A., and Branch, J.W. (2017, January 28–30). Vehicle detection using alex net and faster R-CNN deep learning models: A comparative study. Proceedings of the Advances in Visual Informatics: 5th International Visual Informatics Conference, IVIC 2017, Bangi, Malaysia. Proceedings 5.
14. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2013). Rich feature hierarchies for accurate object detection and semantic segmentation. arXiv.10.1109/CVPR.2014.81 ↗
15. Girshick, R. (2015). Fast R-CNN. arXiv.10.1109/ICCV.2015.169 ↗
16. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv.
17. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition10.1109/TPAMI.2015.2389824 ↗
18. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2015). You Only Look Once: Unified, Real-Time Object Detection. arXiv.10.1109/CVPR.2016.91 ↗
19. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). SSD: Single Shot MultiBox Detector. Proceedings of the Computer Vision—ECCV 2016, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
20. Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017). Focal Loss for Dense Object Detection. arXiv.10.1109/ICCV.2017.324 ↗
21. Tian, Z., Shen, C., Chen, H., and He, T. (2019). FCOS: Fully Convolutional One-Stage Object Detection. arXiv.10.1109/ICCV.2019.00972 ↗
22. A Lightweight Vehicles Detection Network Model Based on YOLOv510.1016/j.engappai.2022.104914 ↗
23. Nikkath Bushra, S., Shobana, G., Uma Maheswari, K., and Subramanian, N. (2022, January 22–23). Smart Video Survillance Based Weapon Identification Using Yolov5. Proceedings of the 2022 International Conference on Electronic Systems and Intelligent Computing (ICESIC), Chennai, India.10.1109/ICESIC53714.2022.9783499 ↗
24. Zhaoxin, G., Han, L., Zhijiang, Z., and Libo, P. (2022, January 22–24). Design a Robot System for Tomato Picking Based on YOLO v5. Proceedings of the 16th IFAC Symposium on Large Scale Complex Systems: Theory and Applications LSS 2022, Xi’an, China. IFAC-PapersOnLine.10.1016/j.ifacol.2022.05.029 ↗
25. Small-object detection based on YOLOv5 in autonomous driving systems10.1016/j.patrec.2023.03.009 ↗
26. Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2019). GhostNet: More Features from Cheap Operations. arXiv.10.1109/CVPR42600.2020.00165 ↗
27. Wang, C.Y., Liao, H.Y.M., Yeh, I.H., Wu, Y.H., Chen, P.Y., and Hsieh, J.W. (2019). CSPNet: A New Backbone that can Enhance Learning Capability of CNN. arXiv.10.1109/CVPRW50498.2020.00203 ↗
28. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2016). Feature Pyramid Networks for Object Detection. arXiv.10.1109/CVPR.2017.106 ↗
29. Wang, W., Xie, E., Song, X., Zang, Y., Wang, W., Lu, T., Yu, G., and Shen, C. (2019). Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network. arXiv.10.1109/ICCV.2019.00853 ↗
30. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. (2019). Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. arXiv.10.1609/aaai.v34i07.6999 ↗
31. Hosang, J., Benenson, R., and Schiele, B. (2017). Learning non-maximum suppression. arXiv.10.1109/CVPR.2017.685 ↗
32. Li, C., Li, L., Geng, Y., Jiang, H., Cheng, M., Zhang, B., Ke, Z., Xu, X., and Chu, X. (2023). YOLOv6 v3.0: A Full-Scale Reloading. arXiv.
33. Zhou, Q., Liu, H., Qiu, Y., and Zheng, W. (2023). Object Detection for Construction Waste Based on an Improved YOLOv5 Model. Sustainability, 15.10.3390/su15010681 ↗