Potato image acquisition device based on RGB-D cameras and method for identifying and locating bud eye

Abstract

The invention relates to a potato image acquisition device based on RGB-D cameras and a method for identifying and locating a bud eye. The image acquisition device consists of three RGB-D cameras thatacquire the color maps and the depth maps of a potato sample from three different angles. The image processing part comprises obtaining a potato target image by preprocessing the color maps and performing a mask-based target extraction method; then training a classifier by using an Adaboost algorithm and a Haar-like feature, identifying a bud eye area, and obtaining the two-dimensional coordinates of the bud eye area; calibrating the RGB-D cameras to obtain the internal parameters and the external parameters of respective RGB-D cameras, and generating point cloud in combination with the depthmaps and the color maps acquired by the corresponding cameras; successively registering the three groups of point cloud by using an iterative nearest neighbor algorithm to obtain the three-dimensional model of the potato sample; then converting the obtained two-dimensional coordinates of the bud eye into coordinates in a three-dimensional space where the three-dimensional model of the potato sample is located, so as to achieve the three-dimensional positioning of the potato bud eye and lay a foundation for realizing the automation of the potato seed dicing.

Description

technical field [0001] The invention relates to a potato image processing method, in particular to a potato image acquisition device based on a multi-view RGB-D camera and a bud eye identification and positioning method. Background technique [0002] Potatoes are the fourth largest food crop in the world after wheat, corn and rice. In China, in order to vigorously promote the process of potato as a staple food, a large number of measures have been taken in the production process to increase the planting area, yield level and total output of potatoes, and promote the mechanization and automation of the cultivation and harvesting stages in the whole process of potato production. development, but the level of automation in the pre-sowing treatment stage of seed potatoes is not yet high enough. [0003] In potato planting, high-quality seed potatoes are the basic guarantee for high yield. According to the research, the seed potato used for sowing can obtain higher output when ...

AI Technical Summary

Problems solved by technology

[0014] In this study, a depth camera was used to collect images of potatoes, and the preliminary simulation and size calculation of the three-dimensional surface structure of potatoes was realized. However, this method manually flips the sample to collect images of both sides, which cannot ensure that all surface features of the potato are fully covered. In addition, The resolution of the depth image is low, and the sample is far away from the lens, so that the proportion of the area occupied by the sample in the field of view of the depth camera is very small, which cannot be used for the analysis of the detailed features of the sample surface (such as bud eyes)

Therefore, this study is not sufficient as a basis for the identification and location of potato bud eyes

Images