A method and a device reconstructing three-dimensional surfaces of potatoes by using fixed-axis rotation profile diagrams

Abstract

The invention provides a method and a device reconstructing three-dimensional surfaces of potatoes by using fixed-axis rotation profile diagrams. The method comprises the steps of collecting side images of a potato sample via a camera; acquiring three-dimensional skeleton data of the potato sample via image processing; further forming the curved surface of the model surface of the potato sample through further processing of the three-dimensional skeleton data of the potato sample to finish the reconstruction of the three-dimensional surface. The device comprises an annular light source, a camera, a rotary table controller and an electric rotary table; a potato sample is installed on an output shaft of the electric rotary table; the electric rotary table is connected with the rotary table controller; the camera faces right downward and captures the side images of the potato sample; the rotary table controller and the camera are connected with a computer via cables; the annular light source is installed between the potato sample and the camera. The three-dimensional surface is reconstructed based on multiple profile diagrams collected when a potato rotates around a fixed axis, so that the accuracy of potato shape detection is improved. The detection apparatus is simple.

Description

technical field [0001] The invention relates to a method and a device for reconstructing a three-dimensional surface, in particular to a method and a device for reconstructing a three-dimensional surface of a potato by using a fixed-axis rotation contour map. Background technique [0002] Potato shape is one of the grading indicators stipulated in the grading standard of "China Agricultural Standard Potato Grade Specifications (NY / T1066-2006)". In order to use machine vision technology to detect the potato shape of potatoes, domestic and foreign scholars have carried out a lot of research. [0003] Fourier descriptor method: Tao Y et al. (Tao Y., Morrow C L Heinemann P H, eta1.Fourier-based separation technique for shape grading of potatoes using machine vision[J].Transactions of the ASAE, 1 995, 38(3) :949-957) proposed a machine vision method for detecting and classifying potatoes using Fourier descriptors. The shape information is extracted and compressed from the norma...

AI Technical Summary

Problems solved by technology

[0008] In order to solve the problem that the two-dimensional image method detects the potato shape and calculates the surface area with the change of the camera angle of view, the result difference is too large, the purpose of the present invention is to propose a method and device for reconstructing the three-dimensional surface of the potato using the fixed-axis rotation contour map

Images