Article

Article title IMAGE PROCESSING TO IDENTIFY THE GROUND SITUATION FOR MOBILE ROBOTIC SYSTEMS
Authors V.A. Barhotkin, V.F. Petrov, M.P. Kochetkov, D.N. Korolkov
Section SECTION II. GROUND ROBOTICS
Month, Year 03, 2014 @en
Index UDC 004.93.1
DOI
Abstract Increased autonomy of mobile robotic systems involves solving the problem of identification of ground situation. The article investigates the methods of image processing three-dimensional ground targets The paper discusses the stages and investigated methods of image processing ground facilities under ill-defined external environment. Pattern recognition problem can be easily solved by man, but it is not solved fully for robots operating in a undetermined environment due to the number of reasons. Images can have different scale. Objects which are perceived by the person as similar can have different areas for different images. Object of interest may also be in different areas of the image. Complexity of the tasks involves the construction of learning recognition systems. Education is an integral part of a recognition process in conditions of high uncertainty of the environment and has as ultimate goal the formation of the standard descriptions of classes, the form of which is determined by the rules their use. Proposed a method of statistical identification of objects using parametric learning to compensate for the distortion of images.

Download PDF

Keywords Algorithm; image processing; mobile robotic systems; model; object.
References 1. Cetto J.A., Filipe J., Ferrier J-L. (Eds.) Informatics in Control Automation and Robotics, Springer, 2011. – 538 p.
2. Cook G. Mobile Robots: Navigation, Control and Remote Sensing Wiley-IEEE Press, 2011. – 319 p.
3. Dutta A. Robotic Systems - Applications, Control and Programming InTech, 2012. –628 p.
4. Gacovski Z. (ed.) Mobile Robots - Current Trends InTech, 2011. – 414 p.
5. Чернов В. Роботы на тропе войны // Армейский сборник. – 2011. – № 10. – С. 34-37.
6. Гонсалес Р, Вудс Р. Цифровая обработка изображений. – М.: Техносфера, 2006. – 1072 c.
7. Duda R., Hart P., Stork D. Pattern Classification, Wiley-Interscience 2nd edition, 2000. – 654 p.

Comments are closed.