Lotus seedpod target image recognition method for picking robot

Abstract

The invention discloses a lotus seedpod target image recognition method for a picking robot. The method includes the steps of designing a super green Gaussian filter through the method that image Gaussian filtering and the super green index method are combined, and removing the complex background; separating and cutting the overlapped portion of an image with the overlapping phenomenon through the improved morphology watershed segmentation algorithm; improving the Hu invariant moment algorithm, calculating invariant moments an of lotus seedpods, lotus leaves, lotuses and stems, conducting linear combination on the calculated n orders of invariant moments, and obtaining invariant moment principle components zm representing different shape characteristics of the lotus seedpods, the lotus leaves, the lotuses and the stems; conducting image target recognition, wherein the invariant moment principle components zm of images of the lotus seedpods, the lotus leaves, the lotuses and the stems are classified through the K-Means clustering algorithm. The connected components, closest to the lotus seedpod clustering center, of the principle components are the lotus seedpods. By means of the method, the lotus seedpods, the lotus leaves, the lotuses and the stems can be effectively distinguished and recognized, and the method is the core algorithm technology of a vision system of the lotus seedpod picking robot.

Description

technical field [0001] The invention belongs to the field of agricultural machinery, and relates to a lotus pod target image recognition method for a picking robot. Background technique [0002] The development and development of picking robots began in the United States in 1968. There are mainly mechanical shaking and pneumatic shaking, but both of them are more harmful to the fruit. With the development of intelligence, automation, and industrialization, the development of foreign picking robots has advanced by leaps and bounds. Japan, the Netherlands, France, the United Kingdom and other countries have successfully tested many picking robots, such as tomato picking robots, grape picking robots, cucumber picking robots, watermelon picking robots, etc. Picking robots, cabbage picking robots, mushroom picking robots, etc. In China, the research on fruit and vegetable picking robots has just started. Lu Huaimin of Northeastern University successfully tested a forest fruit ba...

AI Technical Summary

Problems solved by technology

[0002] The development and development of picking robots began in the United States in 1968. There are mainly mechanical shaking and pneumatic shaking, but both of them are more harmful to the fruit.

Images