COMPUTER VISION ALGORITHMS FOR SIGNALING ENTITIES ANALYSIS AT ROAD SCENE

K.I. Kiy
PhD in Physics and Mathematics, Keldysh Institute of Applied Mathematics, Senior Research Scientist, 4, Miusskaya pl., Moscow, 125047, Russia, tel.: +7(499)978-13-14, This email address is being protected from spambots. You need JavaScript enabled to view it.

Received 10 November 2017

Abstract
The task of signaling entities detection in the road scene images is considered, and algorithms for its solution on the base of the geometrized histogram method are suggested. Principles of software complex on the base of presented algorithms are described. Application for definition of external dimensions zones and speed-slackening signals of surrounding automobiles during robotic car roading is reviewed. Developed methods' implementation for detection of helicopters' warning lights is proposed.

Key words
Image segmentation, image-understanding systems, video sequence analysis, road scene analysis, autonomous robot navigation.

Bibliographic description
Kiy, K. (2018). Computer vision algorithms for signaling entities analysis at road scene. Robotics and Technical Cybernetics, 1(18), pp.26-33.

UDC identifier:
519.722

References

1. Waymo. (n.d.). We're building the world's most experienced driver. [online] Available at: https://www.google.com/selfdrivingcar/ [Accessed 28 Dec. 2017]
2. Kiy, K. (2010). A new real-time method for description and generalized segmentation of color images. Pattern Recognition and Image Analysis, 20(2), pp.169-178.
3. Kiy, K. (2015). Segmentation and detection of contrast objects and their application in robot navigation. Pattern Recognition and Image Analysis, 25(2), pp.338-346.
4. Kiy, K. (2015). A New Real-Time Method of Contextual Image Description and Its Application in Robot Navigation and Intelligent Control. Computer Vision in Control Systems-2, 75(5), pp.109-133.
5. Kiy, K. (n.d.). Moyo video [My video]. [online] Video.mail.ru. Available at: http://video.mail.ru/mail/kikip_46/_myvideo/ [Accessed 28 Dec. 2017].
6. Kiy, K. (2016). Sistema kompleksnogo analiza dorozhnoy stseny dlya navigatsii avtonomnogo robota na doroge [System of complex analysis of road scene for autonomous robot navigation on the road]. In: Trudy mezhdunarodnoy nauchno-tekhnicheskoy konferentsii «Ekstremal'naya robototekhnika ER-2016» [Proceedings of International Scientific and Technical Conference on Extreme Robotics - ER-2016].
7. Hedau, V., Arora, H. and Ahuja, N. (2008). Matching images under unstable segmentation results. In: Proceedings of Int. IEEE Conf. on Comp. Vis. CVPR'2008. pp.1614-1628.
8. Kiy, K. (n.d.). Adjacency graphs for contrast objects – global scene understanding, and their application in robot navigation. Pattern Recognition and Image Analysis, in press.