Zebra Crossing Detection and Time Scheduling Accuracy, Enhancement Optimization Using Artificial Intelligence
DOI:
https://doi.org/10.32628/IJSRST218478Keywords:
Visually Impaire, LYTNet Convolutional Neural Network, Machine Learning, Board Office M.P Nagar (BHOPAL)Abstract
Zebra crossing detection is a fundamental function of the electronic travel aid. It can locate the zebra crossing and estimate its direction to help the visually impaired to cross the road safely. In contrast to the conventional methods, a regression approach is adopted to detect zebra crossing based on convolutional neural networks. Specifically, a fixed‐size window slides across the image captured at the intersection. The image patches are sequentially fed to the logistic regression model to identify the zebra crossing. Then the image patch of zebra crossing is fed to the regression model to predict the direction. The parameters of models are optimized by the ANN back propagation algorithm before predictions. Compared with existing methods, the proposed method can improve the precision‐recall performance of the zebra crossing identification and reduce the root mean square error of predicted directions.
References
- S. Wang, H. Pan, C. Zhang, C. and Y. Tian, “RGB-D image-based detection of stairs, pedestrian crosswalks and traffic signs,” In Journal of Visual Communication and Image Representation, Vol. 25, No. 2, pp. 263-272, 2014.
- S. Sichelschmidt, A. Haselhoff, A. Kummert, M.Roehder, B. Elias, and K. Berns, “Pedestrian crossing detecting as a part of an urban pedestrian safety system," in proc. Intelligent Vehicles Symposium (IV), pp. 840-844, IEEE, 2010.
- C. Yuzhen, C. Lushi, and J. Shuo, “An image based detection of pedestrian crossing,” in proc. 2nd International Congress on Image and Signal Processing (CISP'09), pp. 1-5, IEEE, October, 2009.
- M. S. Uddin, T. Shioyama, “Detection of Pedestrian Crossing Using Bipolarity Feature- An Image-Based Technique”, IEEE Transactions on Intelligent Systems, vol.6, No.4, pp. 439–445, December 2005.
- D. Ahmetovic, C. Bernareggi, A. Gerino, and S. Mascetti, “Zebra Recognizer: efficient andprecise localization of pedestrian crossings”. In 22nd International Conference on Pattern Recognition, Stockholm, Sweden, pp. 2566–2571 (2014)
- M. Khaliluzzaman and K. Deb, "Zebra-crossing detection based on geometric feature and vertical vanishing point" in proc. 3rd International Conference on Electrical Engineering and Information & Communication Technology (iCEEiCT), MIST, Dhaka, Bangladesh, September 2016.
- S. Se, "Zebra-crossing detection for the partially sighted." in proc. IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, 2000.
- D. Herumurti , K. Uchimura , G. Koutaki , T. Uemura, “Urban Road Network Extraction Based on Zebra Crossing Detection from a Very High Resolution RGB Aerial Image and DSM Data” In 2013 International Conference on Signal-Image Technology & Internet-Based Systems, Japan, December 2013.
- Z. S. Chen and D. F. Zhang, “An Effective Detection Algorithm of Zebra-Crossing” in proc. of the 3rd International Conference on Electrical and Information Technologies for Rail Transportation (EITRT), Springer, 2017.
- W. Czajewski, P. Dąbkowski and P. Olszewski, “Innovate solutions for improving safety at pedestrian crossings,” Arch. Transp. Syst. Telemat, Vol. 6, No.2, pp.16–22, 2013.
- T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Transactions on pattern analysis and machine intelligence, vol. 24, no. 7, pp.971-987, 2002.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRST
This work is licensed under a Creative Commons Attribution 4.0 International License.