Crop seedling stage height detection method based on RGB-D depth camera

A depth camera and height detection technology, applied in the field of agricultural plant protection, can solve the problems of not being able to effectively resist interference, affecting the accuracy of measurement results, affecting crop height measurement, etc., to achieve the effect of eliminating tilt errors and avoiding interference

Pending Publication Date: 2021-11-12
HENAN AGRICULTURAL UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the measurement data of the existing method is based on the known installation height of the sensor. In the actual field measurement, H will fluctuate with the movement of the tool, which will affect the accuracy of the measurement results.
Moreover, when the implement tilts in a certain direction, in addition to the actual height H of the sensor will change, the distance L measured by the sensor will also change due to the inclination angle between its direction and the vertical ground normal. This method cannot effectively resist Interference, affecting crop height measurement

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Crop seedling stage height detection method based on RGB-D depth camera
  • Crop seedling stage height detection method based on RGB-D depth camera
  • Crop seedling stage height detection method based on RGB-D depth camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Embodiment 1: This embodiment provides a method for detecting the height of crops at the seedling stage (when bare land can be observed) based on an RGB-D depth camera. The detection method includes the following steps.

[0057] Step 1. Sensor data acquisition

[0058]When the distance between the crop canopy, the ground plane and the depth camera is within the effective range of the camera, the depth camera and the IMU attitude sensor are installed as vertically as possible to look down on the ground, and the following is obtained: figure 1 The original image IMG is shown. While ensuring that the time frames of each data are consistent and the registration relationship between the depth image and the RGB image pixels, so that the pixel position and size of the same object in the two images are the same, the depth image and RGB image are obtained from the attitude sensor through the data channel. and gesture.

[0059] Step 2. Find the crop position based on the RGB im...

Embodiment 2

[0098] Embodiment 2: The similarities between this embodiment and Embodiment 1 will not be described in detail. The difference is that when correcting the attitude, in addition to the method of Embodiment 1, it can also be corrected by means of point clouds. The method is as follows .

[0099] (1) Obtain a point cloud from the original depth image, and perform a rotation operation on the point cloud;

[0100] (2) Take the rotated point cloud as a top-view ortho image.

[0101] (3) Register (align) the ortho image with the RGB image to obtain the corrected depth image D1.

Embodiment 3

[0102] Embodiment 3: The similarities between this embodiment and Embodiment 1 will not be repeated, and the difference is that when the crop height is calculated, the crop range can also be directly filtered, and the minimum value Dmin in the area is taken, Use the difference between the ground depth G and Dmin, and take the absolute value to obtain the crop height H at this position, H=|G-Dmin|.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the technical field of agricultural plant protection, and particularly relates to a crop seedling stage height detection method based on an RGB-D depth camera. According to the method, the crop height is measured by sequentially carrying out the steps of crop position searching, attitude correction, elevation image obtaining, crop height calculation according to the elevation image and the like through an obtained original image, the method does not depend on the position of a camera, and the tilt error of the camera on a motion platform can be eliminated; the target height is extracted through the relative height difference, and interference can be effectively resisted.

Description

technical field [0001] The invention belongs to the technical field of agricultural plant protection, and in particular relates to a method for detecting crop seedling height based on an RGB-D depth camera. Background technique [0002] Crop growth detection at the seedling stage is one of the important basis for crop fine plant protection operations, and it is of great significance to ensure crop yield. Using machine vision technology to quickly and accurately obtain crop seedling height information is one of the important research contents of crop seedling growth monitoring. Traditional crop seedling height measurement methods include visual estimation method and relative position method. The visual estimation method is faster, but the accuracy is low, and absolute height data cannot be obtained, and the estimation range is small. The relative position method uses the sensor to measure the relative distance of the seedling canopy at a overlooking angle, and its accuracy i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G01B11/06G06T7/00G06T7/62G06T7/11G06T7/155G06T5/00G06T3/60
CPCG01B11/0608G06T7/0016G06T7/62G06T7/11G06T7/155G06T3/608G06T2207/10024G06T2207/10028G06T2207/30188G06T5/70
Inventor 李赫赵弋秋徐一高柴嘉君郭长乐程上上牛潇潇张开飞丁力
Owner HENAN AGRICULTURAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap