Grassland recognition method based on geometrical relationship of optical imaging

Abstract

The invention discloses a grassland recognition method based on a geometrical relationship of optical imaging. A motion platform, and a camera and a point light source installed at the bottom of the motion platform are arranged. The point light source emits light beams with specific shapes and colors; the optical axis of the camera vertically points to the ground, the optical axis of the point light source and the optical axis of the camera intersect on the ground, a processor is arranged in the motion platform, and an intelligent grassland recognition algorithm is arranged in the processor. The method comprises the steps that (1) the processor controls the point light source to project linear light beams and collects an image f(x, y) output by the camera; (2) in an image f(x, y), a point(M/2, N/2) is taken as a center, a square range with a side length of L is taken as a feature recognition area, a feature matrix R[L, L] is established, R[m, n] of a projection area of a feature shapeis set as 1, otherwise, R[m, n] is set to be equal to 0; (3) binarization processing is carried out on the image f(x, y) to obtain a binary function f1(x, y); (4) pixel multiplication is carried outon the R[L, L] and the f1(x, y) feature recognition area, and summing is conducted to obtain a projection amount SUM; and (5) if SUM is less than K, being the grassland is judged, otherwise, being notgrassland is judged.

Description

technical field [0001] This patent relates to a grassland recognition method based on the geometric relationship of optical imaging, which belongs to the technical field of mobile robots. Background technique [0002] Computer vision is a simulation of biological vision using computers and related equipment. Its main task is to obtain the information of the corresponding scene by processing the collected pictures or videos. Computer vision has been successfully applied in many fields, such as manufacturing, transportation, smart city, medical diagnosis and military. Computer vision is to use various imaging systems instead of biological visual organs as input sensitive means, and the computer replaces the brain to complete processing and interpretation. [0003] In the field of lawn mowing robot research, environmental scene recognition is a key difficulty. The mowing robot must work on the lawn, otherwise it will pose a danger to itself and the flowers and trees around t...

AI Technical Summary

Problems solved by technology

However, this method cannot solve the impact of changes in lighting conditions on image quality.

Images