International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

Real-Time Comprehensive Assistance for Visually Impaired Navigation

  • Received : 2024.05.05
  • Published : 2024.05.30
Download PDF
⟨ Previous Next ⟩

Abstract

Individuals with visual impairments face numerous challenges in their daily lives, with navigating streets and public spaces being particularly daunting. The inability to identify safe crossing locations and assess the feasibility of crossing significantly restricts their mobility and independence. Globally, an estimated 285 million people suffer from visual impairment, with 39 million categorized as blind and 246 million as visually impaired, according to the World Health Organization. In Saudi Arabia alone, there are approximately 159 thousand blind individuals, as per unofficial statistics. The profound impact of visual impairments on daily activities underscores the urgent need for solutions to improve mobility and enhance safety. This study aims to address this pressing issue by leveraging computer vision and deep learning techniques to enhance object detection capabilities. Two models were trained to detect objects: one focused on street crossing obstacles, and the other aimed to search for objects. The first model was trained on a dataset comprising 5283 images of road obstacles and traffic signals, annotated to create a labeled dataset. Subsequently, it was trained using the YOLOv8 and YOLOv5 models, with YOLOv5 achieving a satisfactory accuracy of 84%. The second model was trained on the COCO dataset using YOLOv5, yielding an impressive accuracy of 94%. By improving object detection capabilities through advanced technology, this research seeks to empower individuals with visual impairments, enhancing their mobility, independence, and overall quality of life.

Keywords

References

  1. Coughlan, J., & Manduchi, R. (2009). Functional Assessment of a Camera Phone-Based Wayfinding System Operated by Blind and Visually Impaired Users. International Journal of Artificial Intelligence Tools, 18(3), 379-397. doi:10.1142/S0218213009000196. PMID: 19960101;PMCID: PMC2786081. Retrieved from https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2786081/
  2. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2014). ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems (pp. 1097-1105). https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
  3. Girshick, R. (2015). "Fast R-CNN." In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 1440-1448. https://openaccess.thecvf.com/content_iccv_2015/papers/Gi rshick_Fast_R-CNN_ICCV_2015_paper.pdf
  4. Caldini, A., Fanfani, M., & Colombo, C. (2015). SmartphoneBased Obstacle Detection for the Visually Impaired. In V. Murino & E. Puppo (Eds.), ICIAP 2015, Part I, LNCS 9279, pp. 480-488. Springer International Publishing. DOI:10.1007/978-3-319-23231-7 43 https://www.researchgate.net/publication/283558670_Smar tphoneBased_Obstacle_Detection_for_the_Visually_Impaired
  5. Khenkar, S., Alsulaiman, H., Ismail, S., Fairaq, A., Jarraya, S. K., and Ben-Abdallah, H. (2016) 'ENVISION: Assisted Navigation of Visually Impaired Smartphone Users', Procedia Computer Science, 100, pp. 128-135. doi: 10.1016/j.procs.2016.09.132. https://www.sciencedirect.com/science/article/pii/S1877050916323006
  6. Bai, J., Liu, D., Su, G., & Fu, Z. (2017). A Cloud and Visionbased Navigation System Used for Blind People. In Proceedings of the 2017 International Conference on Artificial Intelligence, Automation and Control Technologies (AIACT '17) (pp. 1-6). New York, NY, USA: Association for Computing Machinery. DOI:10.1145/3080845.3080867. https://dl.acm.org/doi/abs/10.1145/3080845.3080867
  7. Ghilardi, M. C., Simoes, G., Wehrmann, J., Manssour, I. H., & Barros, R.C. (2018). Real-Time Detection of Pedestrian Traffic Lights for Visually-Impaired People. In Proceedings of the 2018 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1-10). IEEE. DOI:10.1109/CVPR.2023.00001. Available at: https://ieeexplore.ieee.org/document/8489516
  8. Abdul Muhsin, M., Alkhalid, F. F., & Oleiwi, B. K. (2019). Online Blind Assistive System using Object Recognition. International Research Journal of Innovations in Engineering and Technology (IRJIET), 3(12), 47-51. Retrieved from https://irjiet.com/common_src/article_file/1576904071_76a2f481c3_3_irjiet.pdf
  9. Karmarkar, R. R., & Honmane, V. N. (2021). "Object Detection System for the Blind with Voice Guidance." International Journal of Engineering Applied Sciences and Technology, 6(2), 67-70. https://scholar.google.com/scholar?hl=ar&as_sdt=0%2C5&q=OBJECT+DETECTION+SYSTEM+FOR+THE+BLIND+WITH+VOICEGUIDANCE&btnG=#d=gs_qabs&t=1703018590732&u=%23p%3DY1nCU4aqqekJ
  10. Granquist, C., Sun, S. Y., Montezuma, S. R., Tran, T. M., Gage, R., & Legge, G. E. (2021). Evaluation and Comparison of Artificial Intelligence Vision Aids: Orcam MyEye 1 and Seeing AI. Journal of Visual Impairment & Blindness, 115(4), 277-285. Available at: https://journals.sagepub.com/doi/abs/10.1177/0145482X211027492
  11. Senjam, S. S., Manna, S., & Bascaran, C. (2021). Smartphones-Based Assistive Technology: Accessibility Features and Apps for People with Visual Impairment, and its Usage, Challenges, and Usability Testing. Clinical Optometry, 13, 311-322. DOI: 10.2147/OPTO.S336361. Available at: https://www.tandfonline.com/doi/full/10.2147/OPTO.S336361
  12. Salunkhe, A., Raut, M., Santra, S., & Bhagwat, S. (2021). Android-based object recognition application for visually impaired. *ITM Web of Conferences*, 40, 03001. [Online]. Available: https://doi.org/10.1051/itmconf/20214003001
  13. See, A. R., Sasing, B. G., & Advincula, W. D. (2022). A Smartphone-Based Mobility Assistant Using Depth Imaging for Visually Impaired and Blind. *Applied Sciences*, 12(6), 2802. [Online]. Available: https://doi.org/10.3390/app12062802.
  14. Patil, R., Modi, R., Parandekar, A., & Deone, J. B. (2022). Designing mobile application for Visually Impaired and Blind Persons. SSRN. [Online] Available at: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4108763.
  15. Birambole, A., Bhagat, P., Mhatre, B., & Abhyankar, A. (2022). "Blind Person Assistant: Object Detection." International Journal for Research in Applied Science & Engineering Technology (IJRASET), 10(3). Retrieved from blind-person-assistant-object-detection (ijraset.com)
  16. Busaeed, S., Mehmood, R., & Katib, I. (2022). Requirements, Challenges, and Use of Digital Devices and Apps for Blind and Visually Impaired. NOT PEERREVIEWED. Preprints [Online]. Available at: https://www.preprints.org/manuscript/202207.0068/v1
  17. Kuriakose, B., Shrestha, R., & Sandnes, F. E. (2023). DeepNAVI: A deep learning-based smartphone navigation assistant for people with visual impairments. Expert Systems With Applications, 212, 118720. DOI:10.1016/j.eswa.2022.118720. Available at: https://www.sciencedirect.com/science/article/pii/S0957417422017432
  18. Sarmah, A. J., Bhagawati, K., Duwarah, K., Purkayastha, S. D., Boro, A., & Muchahary, D. (2023). "Object detection and conversion of text to speech for visually impaired." ADBU-Journal of Engineering Technology, 12(2), 0120204049 https://scholar.google.com/scholar?hl=ar&as_sdt=0%2C5&q=Object+detection+and+conversion+of+text+to+speech+for+visually+impaired&btnG=#d=gs_qabs&t=1703018313517&u=%23p%3DxYgBPUmyrzUJ
  19. COCO Consortium. COCO - Common Objects in Context. Retrieved from https://cocodataset.org/#home
  20. Roboflow. (n.d.). Roboflow. Retrieved from https://roboflow.com/
  21. Jiang, P., Ergu, D., Liu, F., Cai, Y., & Ma, B. (2022). A Review of Yolo Algorithm Developments. Procedia Computer Science, 199, 1066-1073. doi:10.1016/j.procs.2022.01.146
  22. Benjumea, A., Teeti, I., & Cuzzolin, F. (2022). YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles.
  23. Horvat, M. and Gledec, G. (2022) 'A comparative study of YOLOv5 models performance for image localization and classification', Proceedings of the Central European Conference on Information and Intelligent Systems, pp. 349-357
  24. Solawetz, J. (2020). Yolov5 new versionimprovements and evaluation. Roboflow. Seach date. Retrieved fromhttps://blog.roboflow.com/yolov5-improvementsand-evaluation/
  25. Roboflow. (n.d.). What's New in YOLOv8? Roboflow Blog. Retrieved from https://blog.roboflow.com/whats-new-inyolov8/#yolov8-architecture-a-deep-dive
  26. Viso AI. (n.d.). YOLOv8 Guide. Retrieved from https://viso.ai/deep-learning/yolov8-guide/
  27. YOLOv8 Architecture Overview. (n.d.). YOLOv8. Retrieved from https://yolov8.org/yolov8-architecture/#2_YOLOv8_Architecture_Overview
  28. R. Szeliski, Computer Vision: Algorithms and Applications. Cham, Switzerland: Springer International Publishing, 2022.