Intelligent agricultural machinery navigation system and method based on machine vision

Abstract

The invention discloses an intelligent agricultural machine navigation system based on machine vision. The system comprises an image sensing module for acquiring a farmland image on a navigation path, an image processing module for preprocessing the farmland image, extracting a seedling line and a navigation line from the farmland image, calculating a transverse deviation value and a course angle deviation value of an agricultural machine and the navigation line, and judging the reliability of a calculation result, an agricultural machine path planning module for carrying out field operation path planning according to the navigation line, and an agricultural machine steering system for calculating a correct steering wheel angle of the agricultural machine according to the field operation path planning and carrying out steering control on a steering wheel of the agricultural machine. According to the system, the navigation line can be rapidly and accurately detected in a complex farmland environment, and a detection result can be verified and processed.

Description

technical field [0001] The invention relates to the field of autonomous motion navigation and control of intelligent agricultural machinery, in particular to an intelligent agricultural machinery navigation system and method based on machine vision. Background technique [0002] Smart agricultural machinery navigation is mostly based on the GPS system. However, relying solely on GPS navigation is difficult to obtain the relative position of seedlings and ridges in the farmland scene, resulting in problems such as agricultural machinery rolling over and crop damage. Solutions based on machine vision can effectively solve this problem, but current methods are often based on Manually selecting features has disadvantages such as constant adjustment of feature thresholds in different scenarios and low image data processing efficiency; and most current methods do not have a verification mechanism for detection results. If a few consecutive frames of detection errors are likely to l...

AI Technical Summary

Problems solved by technology

[0002] Smart agricultural machinery navigation is mostly based on the GPS system. However, relying solely on GPS navigation is difficult to obtain the relative position of seedlings and ridges in the farmland scene, resulting in problems such as agricultural machinery rolling over and crop damage. Solutions based on machine vision can effectively solve this problem, but current methods are often based on Manual selection of features has disadvantages such as constant adjustment of feature thresholds in different scenarios and low image data processing efficiency; and most of the current methods do not have a verification mechanism for detection results. If a few consecutive frames of detection errors are likely to lead to a serious decline in navigation accuracy, resulting in farmland Destroyed, it is difficult for agricultural operations to achieve the desired results

Images