Research On Image Matching Arithmetic For Tomato Based On Machine Vision Technology

At present, farm products are harvested mainly by manual in China. However, with the impetus of technology such as information, computer and automation, agricultural mechanization has completely been achieved in developed countries, and it has been changing to automatization and intelligence, where agriculture is on the way of achieving precise and efficient production. Agricultural robot, a means of achieving agricultural modernization, is being emphastically researched in many countries. Research on mobile harvesting robot mainly includes three parts: design of body structure, autonomous navigation and recognition, location registration and harvesting of the objects. Vision system, a means of achieving recognition and location of the objects, is especially important. At present, the technology of machine vision has been applied in agricultural automation in many developed countries. However, research on agricultural robot in China is at the beginning, and there is still a big step behind developed countries. Hence, the research of agricultural robot that is a representive of the new agricultural machinery is of significance to hold the opportunity of world scientific and technological revolution in agriculture and promote the development of automation, intelligence of agricultural machinery of China.The objective of this research was to study vision system of tomato harvesting robot. The ripe tomato was the research object and the matching of tomato fruits were the aims. Several main points in our research were as follows:1 Based on the realizing condition for machine vision in agriculture production, the binocular vision hardware system of the harvest robot was built up.2 The theory of machine vision was analyzed respectively. The model of camera was discussed and the results of calibration of the camera were provided. The parallel model of stereo vision was selected according to the existing devices of lab. The appropriate measuring distance between cameras was 60mm and the appropriate measuring distance range was from 126mm to 800mm;3 Based on the gray-level and color characteristics of eggplant age, after converting the obtained RGB image into HIS image. The coordinate values of the tomato centroid were calculated after the vacancy being filled. The centers of gravity of single tomato and several tomatoes were extracted and later analyzed ,the result showed that the errors was about 0.5% ,the method was valid for discriminating the individual mature tomatoes in natural outdoor scenes.4 The matching algorithms in the machine vision at present were analyzed. area matching and Fourier transform matching in the application of tomato image were introduced, then proposing a matching method based on benchmarks which was experimental demonstrated in the laboratory and nature(greenhouse) environment, and the result indicated that this arithmetic was valid proving ,whose accuracy ratio of matching reached higher 94.5%, as well as the the algorithm speed had been improved ,which would satisfy the need for robot picking up tomatoes in the fields.