Grassland Boundary Recognition Method and Intelligent Mowing Device Using It

Abstract

A grassland boundary recognition method and an intelligent mowing device using the method, which determines the eigenvalue range of the grassland according to the brightness of the working environment, and screens the pixels in the acquired external scene image according to the eigenvalue range, and compares them with the external scene image after statistical screening. Connected pixels at the lower edge of the scene image to determine whether the intelligent mowing device is within the boundary of the grass. The invention realizes the identification and judgment of the grass boundary by simply screening and counting the pixel values ​​of the image itself, and the calculation and processing of the image is relatively simple, thus effectively reducing the hardware cost and calculation overhead of the intelligent mowing device. The invention can improve the recognition efficiency of the grass boundary under the premise of ensuring the recognition accuracy.

Description

technical field [0001] The invention relates to garden tools, in particular to an intelligent mowing device. Background technique [0002] Intelligent mowing equipment mainly includes a mowing unit, a control unit and a self-propelled unit. When working, the relevant data of the external environment of the intelligent mowing equipment is sensed through various devices that sense the external environment, and the control unit controls the self-propelled unit to switch between different self-propelled modes according to the relevant data of the external environment, so as to realize braking, turning and cruising etc., and simultaneously control the mowing unit to operate accordingly. [0003] At present, most of the common intelligent lawn mowing equipment or intelligent lawn mowing robots rely on electromagnetic boundary lines to limit the working area, or rely on D-GPS, UWB and other positioning technologies to limit the working area. The electromagnetic boundary needs to ...

AI Technical Summary

Problems solved by technology

However, most of these solutions are difficult to promote on a large scale due to their complex algorithms and high requirements for hardware computing power.

Or, because the existing computer image recognition technology is sensitive to lighting conditions, the success rate of grassland color recognition varies greatly under different lighting conditions, so it cannot be put into commercial application.

Images