Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Pose Estimation Method of Corn Image Based on Gradient Information and Search Strategy

A gradient information and attitude estimation technology, which is applied in the field of data processing to achieve the effect of simple estimation method, high accuracy, and real-time processing.

Active Publication Date: 2020-08-04
AGRI INFORMATION INST OF CAS
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The object of the present invention is to provide a kind of corn image pose estimation method based on gradient information and search strategy, thus solve the aforementioned problems existing in the prior art

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
  • Pose Estimation Method of Corn Image Based on Gradient Information and Search Strategy
  • Pose Estimation Method of Corn Image Based on Gradient Information and Search Strategy
  • Pose Estimation Method of Corn Image Based on Gradient Information and Search Strategy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0067] Experimental data: It is difficult to directly mark the attitude angle of corn images with attitude, so 400 images without attitude are selected from the corn images collected in the field, and then the final experimental data of 2000 pieces is obtained by artificially adding angle perturbation method image. Add a random angle disturbance within 20 degrees to each image, perform 4 times on each image, add the original image, and finally get 2000 images to be detected.

[0068] Estimation of pose angle: Use the estimation method described in this application to obtain the pose angle of each image to be detected, and set the search range of the pose angle to 30 degrees. In the range of -30 degrees and 30 degrees, with a step size of 1 degree, the attitude angle of the image to be detected is gradually changed, and the gradient image corresponding to the angle is calculated, and the discriminant feature Fnorm of the angle is calculated.

[0069] The attitude angle discrim...

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 discloses a corn image attitude estimation method based on gradient information and search strategy and relates to the field of data processing. The estimation method comprises steps asfollows: acquiring corn images requiring estimation of attitude angles in real time, sequentially rotating the corn images requiring estimation of attitude angles at a certain angle interval in a preset searching range of attitude angle judgment, and calculating a gradient information set of the corn image corresponding to each rotating angle; calculating judgment characteristics of each rotatingangle on the basis of the gradient information set corresponding to each rotating angle, obtaining the maximum judgment characteristic by comparison, and acquiring the rotating angle corresponding tothe maximum judgment characteristic, wherein the rotating angle is the attitude angel of the corn images requiring estimation of attitude angles. The estimation method is simple, smaller in calculatedamount and high in accuracy and can basically meet the real-time processing requirement.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a method for estimating the pose of a corn image based on gradient information and a search strategy. Background technique [0002] With the development of computer vision technology and the development requirements of modern agriculture, machine vision has been widely used in agricultural production and management. Although visual analysis technology has the advantage of convenient data collection, due to the limitation of the collection environment, the obtained data images often contain certain interference factors, which affect the further analysis of crops. [0003] Corn is one of the most widely planted crops in my country. Many researchers have applied machine vision to corn production and management, such as corn harvesting robot path recognition [1,2] , analysis of corn canopy [3] , The positioning of corn stalks [4] etc. It should be pointed out that the above-mentione...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/13G06T7/73
CPCG06T7/13G06T7/73G06T2207/10004G06T2207/10024G06T2207/30004
Inventor 郭秀明刘升平诸叶平刘海龙
Owner AGRI INFORMATION INST OF CAS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products