CONTOUR METHOD FOR POSITIONING OBJECTS IN MOBILE COMPUTER VISION SYSTEMS

The paper considers the possibility of solving problem improving quality technical vision using contour method, which is used to position objects in mobile computer systems. hardware part object positioning system includes two video cameras, a Raspberry Pi 3 microcomputer, depth map screen, and motor control unit. codes programs based on OpenCV library, algorithm examples implementation method are given. developed technique selection contours frames stereopair, removal all open contours, calculation moment (center mass) each closed contour, determination displacement along x-axis moments corresponding filling with points brightness inversely proportional moments. presence screen provides stereoscopic panoramic "vision", that is, ability determine their distance, as well get an overall picture "field view" system. engine unit allows devices avoid obstacles. Based analysis research results, it was found proposed increase decrease required computing resource, gives significant power consumption ensures autonomy