AbhiGyam: A Machine Learning Model-Driven Research Platform for Assessing Accessibility Infrastructure in Indian Cities

Year : 2024 | Volume :11 | Issue : 02 | Page : –
By

Shaily Malik,

Gagan Vats,

Abhishek Gupta,

Amit Kumar Thakur,

  1. Assistant Professor Department Of Computer Science, Maharaja Surajmal Institute Of Technology, New Delhi Delhi India
  2. Student Department Of Computer Science, Maharaja Surajmal Institute Of Technology, New Delhi Delhi India
  3. Student Department Of Computer Science, Maharaja Surajmal Institute Of Technology, New Delhi Delhi India
  4. Student Department Of Computer Science, Maharaja Surajmal Institute Of Technology, New Delhi Delhi India

Abstract

This work presents AbhiGyam, a machine learning-driven research platform designed to streamline and automate the assessment of accessibility infrastructure in Indian cities. AbhiGyam leverages the Google Maps API to transmit street view images to the backend, where computer vision techniques are implemented using OpenAI’s CLIP (Contrastive Language-Image Pre-training) model to identify objects such as ramps, sidewalks, crosswalks, and parking spaces. The accuracy of the model is validated using labeled data provided by the Scale Rapid API. Additionally, the ADA (Accessible Design) score for Indian cities is calculated, considering factors like the number of detected ramps, accessible parking spaces, crosswalks, and sidewalks, as well as accident data. AbhiGyam is a significant improvement over existing methods for assessing accessibility infrastructure, offering an automated, scalable, and more accurate solution. This work has the potential to make a significant impact on the field of accessibility research, providing a valuable tool for urban planners and government bodies, and contributing to a more accessible India.

Keywords: Accessibility, Machine Learning, CLIP Model, Urban Planning, Infrastructure Assessment, Neural networks, computer vision, accessibility, sidewalks, curb ramps, Google Street View

[This article belongs to Journal of Artificial Intelligence Research & Advances(joaira)]

How to cite this article: Shaily Malik, Gagan Vats, Abhishek Gupta, Amit Kumar Thakur. AbhiGyam: A Machine Learning Model-Driven Research Platform for Assessing Accessibility Infrastructure in Indian Cities. Journal of Artificial Intelligence Research & Advances. 2024; 11(02):-.
How to cite this URL: Shaily Malik, Gagan Vats, Abhishek Gupta, Amit Kumar Thakur. AbhiGyam: A Machine Learning Model-Driven Research Platform for Assessing Accessibility Infrastructure in Indian Cities. Journal of Artificial Intelligence Research & Advances. 2024; 11(02):-. Available from: https://journals.stmjournals.com/joaira/article=2024/view=155861

References

  1. Smith TF, Waterman MS. Identification of common molecular subsequences. Journal of molecular biology. 1981 Mar 25;147(1):195-7.
  2. Band SS, Ardabili S, Sookhak M, Chronopoulos AT, Elnaffar S, Moslehpour M, Csaba M, Torok B, Pai HT, Mosavi A. When smart cities get smarter via machine learning: An in-depth literature review. IEEE Access. 2022 Jun 9;10:60985-1015.
  3. Weld G, Jang E, Li A, Zeng A, Heimerl K, Froehlich JE. Deep learning for automatically detecting sidewalk accessibility problems using streetscape imagery. InProceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility 2019 Oct 24 (pp. 196-209).
  4. Abbott A, Deshowitz A, Murray D, Larson EC. WalkNet: A deep learning approach to improving sidewalk quality and accessibility. SMU Data Science Review. 2018;1(1):7.
  5. Kaneda K, Kamohara M, Shiku O, Kobayashi T. Wheelchair accessibility evaluation with deep learning using a sensing acceleration data-based spectrogram. In2020 IEEE 9th Global Conference on Consumer Electronics (GCCE) 2020 Oct 13 (pp. 205-207). IEEE.
  6. Xie X, Zhou Y, Xu Y, Hu Y, Wu C. OpenStreetMap data quality assessment via deep learning and remote sensing imagery. IEEE Access. 2019 Dec 5;7:176884-95.
  7. Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G. Learning transferable visual models from natural language supervision. InInternational conference on machine learning 2021 Jul 1 (pp. 8748-8763). PMLR.
  8. Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J. An image is worth 16×16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. 2020 Oct 22.
  9. He, Kaiming, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. “Momentum contrast for unsupervised visual representation learning.” In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 9729-9738. 2020.
  10. Dosovitskiy, Alexey, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani et al. “An image is worth 16×16 words: Transformers for image recognition at scale. arXiv 2020.” arXiv preprint arXiv:2010.11929 (2010).
  11. Prateek Rawat , Archana N. Mahajan. “ReactJS: A Modern Web Development Framework”. International Journal of Innovative Science and Research Technology ISSN No:-2456-2165.
  12. V’s SG. Comprehensive Analysis of React-Redux Development Framework. Int. J. Creat. Res. Thoughts www. ijcrt. org. 2020;8(4):4230.
  13. Gayathri .G. Comparative Study of ReactJS and NodeJS. Internatıonal Journal of Research In Electronıcs And Computer Engıneerıng. 2019;7(1):2095-2096.
  14. Kaur G, Kaur J. In-memory data processing using redis database. Int. J. Comput. Appl. 2018;180:26-31.
  15. D V Kornienko, S V Mishina, S V Shcherbatykh and M O Melnikov. “Principles of securing RESTful API web services developed with python frameworks”. Journal of Physics: Conference Series 2094 (2021) 032016.
  16. Zhang P, Xing L, Yang N, Tan G, Liu Q, Zhang C. Redis++: A high performance in-memory database based on segmented memory management and two-level hash index. In2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom) 2018 Dec 11 (pp. 840-847). IEEE.
  17. Bashari Rad, Babak & Bhatti, Harrison & Ahmadi, Mohammad. (2017). “An Introduction to Docker and Analysis of its Performance”. IJCSNS International Journal of Computer Science and Network Security. 173. 8.
  18. Khandhar MN, Shah MS. Docker-the future of virtualization. International Journal of Research and Analytical Reviews. 2019;6(2):164-7.
  19. Richardson L, Amundsen M, Ruby S. RESTful Web APIs: Services for a changing world. ” O’Reilly Media, Inc.”; 2013 Sep 12.
  20. Fielding RT. Architectural styles and the design of network-based software architectures. University of California, Irvine; 2000.
  21. Blischak JD, Davenport ER, Wilson G. A quick introduction to version control with Git and GitHub. PLoS computational biology. 2016 Jan 19;12(1):e1004668.
  22. Majumdar R, Jain R, Barthwal S, Choudhary C. Source code management using version control system. In2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions)(ICRITO) 2017 Sep 20 (pp. 278-281). IEEE.
  23. Window: postMessage() method – Web APIs | MDN. MDN Web Docs. 2024. Available from: https://developer.mozilla.org/en-US/docs/Web/API/Window/postMessage
  24. Vatare AS, Adkar P. Review Paper on Centralized and Distributed Version Control System. 2019;2(11):150-158.
  25. Hillar GC. Django RESTful Web Services: The Easiest Way to Build Python RESTful APIs and Web Services with Django. Packt Publishing Ltd; 2018 Jan 25.
  26. Najafizadeh L, Froehlich JE. A feasibility study of using Google street view and computer vision to track the evolution of urban accessibility. InProceedings of the 20th international ACM SIGACCESS conference on computers and accessibility 2018 Oct 8 (pp. 340-342).
  27. Vincent WS. Django for APIs: Build web APIs with Python and Django. WelcomeToCode; 2022 Feb 23.
  28. Hara K, Le V, Froehlich J. Combining crowdsourcing and google street view to identify street-level accessibility problems. InProceedings of the SIGCHI conference on human factors in computing systems 2013 Apr 27 (pp. 631-640).
  29. Rayhan A, Kinzler R. Unleashing the Power of Advanced Python Programming. Available from https://www.researchgate.net/publication/373217154_Unleashing_the_Power_of_Advanced_Python_Programming
  30. Dincer A, Uraz B. Google Maps JavaScript API Cookbook. Packt Publishing Ltd; 2013 Dec 26.
Regular Issue Subscription Review Article
Volume 11
Issue 02
Received May 24, 2024
Accepted June 20, 2024
Published July 10, 2024
Views: 21