Crop height online measurement method suitable for rice combine harvester

Abstract

The invention provides a crop height online measurement method suitable for a rice combine harvester, and belongs to the technical field of agricultural image processing. According to the method, three-dimensional coordinates of a measured object are acquired by using a binocular camera, an operation real-time ground plane is calculated through an IMU, and the three-dimensional coordinates are converted into an actual height corresponding to the object according to the distance from the point to the plane; a clustering algorithm isprovided to classify height data, a class with the maximum mean value in a height data clustering result is used as a crop height calculation candidate region, and AND operation is carried out on the candidate region and a crop target region to obtain a common target region, so that the crop height is expressed. The method is suitable for real-time on-line measurement of the height of crops before cutting for the rice combine harvester, and can provide a basis for unmanned self-adaptive regulation and control of the harvester.

Description

technical field [0001] The invention belongs to the technical field of agricultural image processing, and in particular relates to an online crop height measurement method suitable for a rice combine harvester. Background technique [0002] Unmanned agricultural machinery can reduce labor demand and improve the accuracy and efficiency of agricultural machinery operations. Rice is the main food crop in my country, so the research on unmanned driving technology based on rice combine harvester is particularly important. Traditional combine harvester unmanned driving technology is mainly based on satellite navigation signals to realize vehicle autonomous walking, but lacks the monitoring of the state of the crop itself. Real-time adjustment of reel height according to crop height is a basic operation in the harvesting process and an important factor affecting harvest quality. Therefore, real-time online monitoring of crop height is required to provide a basis for real-time regu...

AI Technical Summary

Problems solved by technology

In the prior art, the distance between the crop and the sensor is measured by a fixed-height ultrasonic sensor, but due to the limitation of the characteristics of the ultrasonic sensor itself, the error of the measurement result is relatively large; the prior art is based on a photoelectric sensor array that scans from top to bottom Judging the range of reflected signals to measure crop height, but this method has low resolution and the effective measurement distance of photoelectric sensors is relatively short in outdoor environments; in the prior art, visual processing is used to analyze the relative height of fixed marker sticks and rice in the rice field to obtain the actual rice Height, this method is static measurement and is easily affected by the weather; the existing technology uses the disparity map of the binocular stereo camera to realize the calculation of crop height, but it needs to detect the bottom point and apex of the crop at the same time

The above-mentioned crop height measurement method is difficult to apply in the actual harvesting scene of rice crops

Images