AUTOMATIC CONTROL OF CAMERA OPTICAL AXIS BASED ON VISION SYSTEM USING THE METHOD OF OBJECT RECOGNITION BY COLOR

Abstract

Machine vision systems are used for the treatment and recognition of different images obtained from a camera. A vision system is a means of tracking, monitoring and automatic decision-making in certain situations.This work is dedicated to the development of a new system of automatic control pilotless vehicle using a machine vision system, namely its landing offline on a special sign / symbol, posted on the ground.The practical application of such systems: pilotless vehicle specified by coordinates reaches the final destination, using the camera (machine vision system) finds an appropriate symbol in place of the final position, recognizes it and goes to land; everything goes offline.Object detection and segmentation is the most important and challenging fundamental task of a computer (machine) vision. It is a critical part in many applications such as image search, scene understanding, etc. However, it is still an open problem due to the variety and complexity of object classes and backgrounds.The optimal way to detect and segment an object from an image is the color-based method. The object and the background should have a significant color difference in order to successfully segment objects using color based methods. This work for object detection based on color with using software Python 3, OpenCV 3, Web Camera, and microcontroller Raspberry Pi 2.On the microcontroller Raspberry Pi 2, we run a web server written in Python that provides a web interface, and which listens for commands over the WebSockets protocol. When it gets commands, it sends them onto the Mini Driver via serial USB. This is a custom Raspberry Pi camera program we’ve written that streams JPEG images over the network. It can also stream reduced size images (160×120) for computer vision.The efficiency of the system is confirmed by tests on the laboratory bench.