Measuring the distance to cars by means of a side view camera without using road markings

Malashin, R.O.

Full text «Opticheskii Zhurnal»

Full text on elibrary.ru

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Малашин Р.О. Измерение дальности до автомобилей с помощью камеры бокового вида без использования дорожной разметки // Оптический журнал. 2019. Т. 86. № 11. С. 51–58. http://doi.org/10.17586/1023-5086-2019-86-11-51-58

Malashin R.O. Measuring the distance to cars by means of a side view camera without using road markings [in Russian] // Opticheskii Zhurnal. 2019. V. 86. № 11. P. 51–58. http://doi.org/10.17586/1023-5086-2019-86-11-51-58

For citation (Journal of Optical Technology):

R. O. Malashin, "Measuring the distance to cars by means of a side view camera without using road markings," Journal of Optical Technology. 86(11), 716-722 (2019). https://doi.org/10.1364/JOT.86.000716

Abstract:

The problem of determining the distance to cars in the side blind zone using a side view camera is considered. An analytical solution to the problem of reconstructing the three-dimensional coordinates of a “pursuing” vehicle is presented by detecting the point of contact of the car with the road in the image. In addition, methods for obtaining and clarifying the orientation of the camera are considered. A neural network was trained to detect the point of contact. The results of an experimental verification of the developed algorithms confirming the efficiency of the proposed method are presented.

Keywords:

self-driving, measuring distance to cars, objects detection

OCIS codes: 150.6910, 150.5670, 100.4996

References:

1. V. Tram and M. Yoo, “Vehicle-to-vehicle distance estimation using a low-resolution camera based on visible light communications,” IEEE Access 6, 4521–4527 (2018).
2. E. Dagan, O. Mano, and G. Stein, “Forward collision warning with a single camera,” in Intelligent Vehicles Symposium (2004), pp. 37–42.
3. W. Wang, S. Yang, Y. Li, and W. Ding, “A rough vehicle distance measurement method using monocular vision and license plate,” in IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), Shenyang, China, June 8–12, 2015, pp. 426–430.
4. CarND-Advanced-Lane-Lines, https://github.com/ajsmilutin/CarND-Advanced-Lane-Lines/blob/master/README.md.
5. D. Tseng, “Blind-spot vehicle detection using motion and static features,” Int. J. Mach. Learn. Comput. 4(6), 516–521 (2014).
6. A. Ali and H. Hussein, “Distance estimation and vehicle position detection based on monocular camera,” in AIC-MICSTA (2016), pp. 1–4.
7. B. F. Wei, H. Huang, C. Chen, Y. Chen, C. Chang, and Y. Chen, “A vision-based blind spot warning system for daytime and nighttime driver assistance,” Comput. Electr. Eng. 39, 846–862 (2013).
8. S. Qi, J. Li, Z. Sun, J. Zhang, and Y. Sun, “Distance estimation of monocular based on vehicle pose information,” J. Phys.: Conf. Ser. 1168, 032040 (2019).
9. J. Redmon and A. Farhadi, “YOLO9000: better, faster, stronger,” IEEE Conference on CVPR, Honolulu, USA, July 21–26, 2017, pp. 6517–6525.
10. The Kitti vision benchmark suite, http://www.cvlibs.net/datasets/kitti.
11. Udacity self-driving car dataset, https://github.com/udacity/self-driving-car/tree/master/datasets.
12. The Cityscapes Dataset, https://www.cityscapes-dataset.com/.
13. Open computer vision library, https://opencv.org/.
14. R. O. Malashin and A. B. Kadykov, “Investigation of the generalizing capabilities of convolutional neural networks in forming rotation-invariant attributes,” J. Opt. Technol. 82(8), 509–515 (2015) [Opt. Zh. 82(8), 24-32 (2015)].