Cyclist Safety Enhancement: A Multi-Modal Hazard Detection System

Year : 2024 | Volume :01 | Issue : 02 | Page : 35-83
By

Naval Joshi

Vaishnavi Bhutada

Manaswini Chittepu

  1. Student University of Petroleum and Energy studies Uttarakhand India
  2. Student Bharati Vidyapeeth’s College of Engineering for Women, Pune Maharashtra India
  3. Student Amrita Vishwa Vidyapeetham Hyderabad India

Abstract

This study presents a multi-modal hazard detection system to enhance cyclist safety in urban environments. Lever- aging a combination of computer vision, object tracking, and predictive modeling, the system offers a comprehensive approach to identifying and mitigating potential risks. Key contributions include improved depth estimation through object size priors, multi-class tracking utilizing KCF and Brisk, and a novel recurrent neural network architecture for predicting bicycle movement. The system’s collision detection module evaluates the likelihood of collisions by analyzing future object and cyclist positions, incorporating uncertainties. While real-time implementation remains challenging due to hardware limitations, the modular design allows for future optimizations and integration with faster technologies. This research represents a valuable step toward safeguarding cyclists and paves the way for more effective hazard detection systems in the future

Keywords: KCF, cyclist safety, urban environments, SLAM, RCNN

[This article belongs to International Journal of Machine Systems and Manufacturing Technology(ijmsmt)]

How to cite this article: Naval Joshi, Vaishnavi Bhutada, Manaswini Chittepu. Cyclist Safety Enhancement: A Multi-Modal Hazard Detection System. International Journal of Machine Systems and Manufacturing Technology. 2024; 01(02):35-83.
How to cite this URL: Naval Joshi, Vaishnavi Bhutada, Manaswini Chittepu. Cyclist Safety Enhancement: A Multi-Modal Hazard Detection System. International Journal of Machine Systems and Manufacturing Technology. 2024; 01(02):35-83. Available from: https://journals.stmjournals.com/ijmsmt/article=2024/view=145711


Browse Figures

References

  1. F. Transport, “Table ras30001: Reported road casualties by road user type and severity, great britain, 2016,” Dft, Report, 2016. pages 1
  2. “Ras50001: Contributory factors in reported accidents by severity, great britain, 2016,” Dft, Report, 2016. pages 1
  3. “Focus on cycling in ‘reported road casualties great britain 2013,” Dft, Report, 2013. pages 1
  4. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” vol. 25, 01 2012. pages 2
  5. Karpathy. (2017) Networks. [Online]. Available:http://cs231n. github.io/convolutional-networks/pages 2
  6. Li, H., Guo, X., Ouyang, B. D., & Wang, X. (2018). Neural network encapsulation. In Proceedings of the European conference on computer vision (ECCV) (pp. 252-267).
  7. Paik, I., Kwak, T., & Kim, I. (2019, October). Capsule networks need an improved routing algorithm. In Asian Conference on Machine Learning (pp. 489-502). PMLR.
  8. Sabour, N. Frosst, and G. E. Hinton, “Dynamic routing between capsules,” CoRR, vol. abs/1710.09829, 2017. [Online]. Available: http://arxiv.org/abs/1710.09829pages 2
  9. B. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” CoRR, vol. abs/1311.2524, 2013. [Online]. Available: http://arxiv.org/abs/1311.2524pages 2, 3
  10. Redmon, S. K. Divvala, R. B. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” CoRR, vol. abs/1506.02640, 2015. [Online]. Available:http://arxiv.org/abs/1506. 02640pages 2, 23
  11. R. R. ”Uijlings, K. E. A. van de Sande, T. Gevers, and A. W. M. Smeulders, “”selective search for object recognition”,” ”International Journal of Computer Vision”, ”2013”. pages 3
  12. F. ”Felzenszwalb and D. P. Huttenlocher, “”efficient graph-based image segmentation”,” ”International Journal of Computer Vision”, ”2004”. pages 3
  13. B. Girshick, “Fast R-CNN,” CoRR, vol. abs/1504.08083, 2015. [Online]. Available:http://arxiv.org/abs/1504.08083pages 3, 4
  14. He, X. Zhang, S. Ren, and J. Sun, “Spatial pyramid pooling in deep convolutional networks for visual recognition,” CoRR, vol. abs/1406.4729, 2014. [Online]. Available:http://arxiv.org/abs/1406.4729 pages 3
  15. Ren, K. He, R. B. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” CoRR, vol. abs/1506.01497, 2015. [Online]. Available:http://arxiv.org/abs/1506. 01497pages 3, 5
  16. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” CoRR, vol. abs/1411.4038, 2014. [Online]. Available: http://arxiv.org/abs/1411.4038pages 4, 5
  17. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler,R. Benenson, U. Franke, S. Roth, and B. Schiele, “The cityscapes dataset for semantic urban scene understanding,” CoRR, vol. abs/1604.01685, 2016. [Online]. Available:http://arxiv.org/abs/1604.01685pages 4
  18. Wan, M. Zeiler, S. Zhang, Y. LeCun, and R. Fergus, “Regularization of neural networks using dropconnect,” in Proceedings of the 30th International Conference on International Conference on Machine Learning – Volume 28, ser. ICML’13. JMLR.org, 2013, pp. III– 1058–III–1066. [Online]. Available:http://dl.acm.org/citation.cfm?id= 3042817.3043055pages 4
  19. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, pp. 1929–1958, 2014. [Online]. Available: http://jmlr.org/papers/v15/srivastava14a.htmlpages 5
  20. M. Bishop, Pattern Recognition and Machine Learning (Information Science and Statistics). Berlin, Heidelberg: Springer-Verlag, 2006. pages 5
  21. He, G. Gkioxari, P. Doll a´r, and R. B. Girshick, “Mask R-CNN,” CoRR, vol. abs/1703.06870, 2017. [Online]. Available: http://arxiv.org/abs/1703.06870pages 5
  22. Olah, “Understanding lstms blog.” [Online]. Available:http://colah.github.io/posts/2015-08-Understanding-LSTMs/pages 5, 6
  23. Deisenroth, “Gaussian processes and bayesian optimisation,” 2018.pages 7
  24. Srinivas, A. Krause, S. Kakade, and M. Seeger, “Gaussian process optimization in the bandit setting: No regret and experimental design,” 2010. pages 6
  25. docs. (2012) Images. [Online]. Available:https://docs.opencv.org/2. 4/modules/calib3d/doc/camera calibration and 3d reconstruction.html pages 8
  26. Leutenegger, S. Lynen, M. Bosse, R. Siegwart, and P. Furgale, “Keyframe-based visual–inertial odometry using nonlinear optimiza- tion,” The International Journal of Robotics Research, vol. 34, no. 3, pp. 314–334, 2015. pages 9, 10, 11
  27. F. Durrant-Whyte, “Uncertain geometry in robotics,” vol. 4, pp. 23– 31, 03 1988. pages 10
  28. Bailey and H. Durrant-Whyte, “Simultaneous localization and map- ping (slam): Part i,” 10 2006. pages 10
  29. Leutenegger, M. Chli, and R. Y. Siegwart, “Brisk: Binary robust invariant scalable keypoints,” in 2011 International Conference on Computer Vision, Nov 2011, pp. 2548–2555. pages 10, 11
  30. docs. (2012) Images. [Online]. Available:http://opencv-python-tutroals.readthedocs.io/en/latest/py tutorials/ py feature2d/py features harris/py features harris.htmlpages 11
  31. F. Henriques, R. Caseiro, P. Martins, and J. Batista, “High-speed tracking with kernelized correlation filters,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 3, pp. 583–596,March 2015. pages 11, 12
  32. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” CoRR, vol. abs/1412.6980, 2014. [Online]. Available: http://arxiv.org/abs/1412.6980pages 19
  33. Eisele. (2016) Circle intersection. [Online]. Available:https://www. xarg.org/2016/07/calculate-the-intersection-points-of-two-circles/pages 21
  34. (2016) Circle intersection. [Online]. Available:https://www.xarg. org/2016/07/calculate-the-intersection-area-of-two-circles/pages 21
Regular Issue Subscription Original Research
Volume 01
Issue 02
Received March 14, 2024
Accepted March 20, 2024
Published May 9, 2024
Views: 22