Lane and Curve Detection Using Deep Learning for Autonomous Vehicles
Abstract
To drive autonomously, vehicles must be able to traverse streets, stop at stop signs and traffic lights, and avoid colliding with things such as other cars and people. Based on the difficulties that autonomous cars have in recognizing objects, an effort has been undertaken to demonstrate lane detection using the OpenCV library. The rationale for utilizing grayscale rather than color, identifying edges in an image, selecting a region of interest, performing the Hough Transform, and using polar coordinates rather than Cartesian coordinates have all been discussed.References
Ansari, M., Kurchaniya, D., & Dixit, M. (2017). A Comprehensive Analysis of Image Edge Detection Techniques. International Journal of Multimedia and Ubiquitous Engineering, 12(11), 1-12. doi: 10.14257/ijmue.2017.12.11.01
Chan, Y.-H., Xu, Z.-X., & Lun, P.-K. (2019). A Framework of Reversible Color-to-Grayscale Conversion With Watermarking Feature. IEEE Transactions on Image Processing, PP(99), 1-1. doi:10.1109/TIP.2019.2936097
Chauhan, M. S., Singh, A., & Khemka, M. (2019). Embedded CNN based vehicle classification and counting in non-laned road traffic. International Conference on Information and Communication Technologies and Development, 1-11. doi:10.1145/3287098.3287118
Deng, G., & Wu, Y. (2018). Double Lane Line Edge Detection Method Based on Constraint Conditions Hough Transform. International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES) (pp. 107-110). IEEE. doi:10.1109/DCABES.2018.00037
Huang, Q., & Liu, J. (2021). Practical limitations of lane detection algorithm based on Hough transform in challenging scenarios. International Journal of Advanced Robotic Systems, 18(2). doi:10.1177/17298814211008752
Jung, J., Shin, Y., & Kwon, Y. (2018). Extension of Convolutional Neural Network with General Image Processing Kernels. doi:10.1109/TENCON.2018.8650542
Kim, J.-H., Kim, S.-K., Lee, S.-H., Lee, T.-M., & Lim, J. (2018). Lane recognition algorithm using lane shape and color features for vehicle black box. International Conference on Electronics, Information, and Communication (ICEIC), (pp. 1-2). doi:10.23919/ELINFOCOM.2018.8330549
Liu, R., & Mao, J. (2018). Research on Improved Canny Edge Detection Algorithm. MATEC Web Conf., 232, 1-4. doi:10.1051/matecconf/201823203053
Mahamkali, N., & Ayyasamy, V. (2015). OpenCV for Computer Vision Applications. Proceedings of National Conference on Big Data and Cloud Computing (pp. 52-56). Tirichy: Research Gate.
R, R., Saklani, N., & Verma, V. (2019). A Review on Edge detection Technique “Canny Edge Detection”. International Journal of Computer Applications, 178(10), 28-30. doi:10.5120/ijca2019918828
Rathore, A. S. (2019). Lane detection for autonomous vehicles using OpenCV Library. International Research Journal of Engineering and Technology (IRJET), 6(1), 1326-1332.
Sekehravani, E. A., Babulak, E., & Masoodi, M. (2021). Implementing canny edge detection algorithm for noisy image. Bulletin of Electrical Engineering and Informatics , 9(4), 1404-1410. doi:10.11591/eei.v9i4.1837
Singhal, P., Verma, A., & Garg, A. (2017). A study in finding effectiveness of Gaussian blur filter over bilateral filter in natural scenes for graph based image segmentation. International Conference on Advanced Computing (pp. 1-6). IEEE. doi:0.1109/ICACCS.2017.8014612
Wang, R., Li, W., Qin, R., & Wu, J. (2017). Blur image classification based on deep learning. International Conference on Imaging Systems and Techniques (IST) (pp. 1-6). IEEE. doi:10.1109/IST.2017.8261503
Wei, X., Zhang, Z., Chai, Z., & Feng, W. (2018). Research on Lane Detection and Tracking Algorithm Based on Improved Hough Transform. IEEE International Conference of Intelligent Robotic and Control Engineering (IRCE). doi:10.1109/IRCE.2018.8492932
