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

Segmentation and localization method for two overlapped fruits based on chromatic aberration

A positioning method and fruit technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of large amount of calculation, unfavorable robot picking efficiency, slow operation speed, etc., to ensure accurate division, reduce the amount of calculation, and improve the calculation. effect of speed

Inactive Publication Date: 2017-06-20
CHONGQING UNIV OF TECH
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There is no segmentation and positioning method specifically for overlapping two fruits in the prior art. Using the identification and positioning method of overlapping fruits in the prior art to perform segmentation and positioning of two overlapping fruits has the disadvantages of large amount of calculation and slow operation speed. Conducive to improving the picking efficiency of robots

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
  • Segmentation and localization method for two overlapped fruits based on chromatic aberration
  • Segmentation and localization method for two overlapped fruits based on chromatic aberration
  • Segmentation and localization method for two overlapped fruits based on chromatic aberration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] This embodiment is used for citrus picking

[0053] A method for segmentation and positioning of two overlapping fruits based on color difference, such as figure 1 shown, including the following steps:

[0054] Step 1: The input is only the original image I where two fruits overlap each other o , for the original image I o Perform binarization, such as figure 2 As shown, the binary image I with the fruit area as the target area and the branch and leaf area as the background area is obtained S ; The binary image I S The gray value of each pixel in the target area is 255; the gray value of each pixel in the background area is 0;

[0055] Step 2: Select the binary image I by frame S The minimum circumscribed affine rectangle of the target area, so that all the pixels in the target area fall within the minimum circumscribed affine rectangle;

[0056] Step 3: If image 3 As shown, the length and width of the minimum circumscribed affine rectangle in step 2 are respe...

Embodiment 2

[0077] The present embodiment is used for apple picking, and the difference from embodiment 1 is:

[0078] In step 3, the length and width of the minimum circumscribed affine rectangle are respectively reduced to 75% of the original length to obtain the target rectangle.

[0079] The segmentation threshold in step 202 is [210,255];

[0080] Step 203: traverse each pixel in the H component map according to the following formula, and perform binarization on the H component map:

[0081] Among them, T is the gray value of the i-th pixel in the binarized H component image.

[0082] The final effect diagram of this embodiment is as follows Figure 9 As shown, the segmentation and positioning of two overlapping fruits are completed.

Embodiment 3

[0084] The present embodiment is used for citrus picking, and the difference from embodiment 1 is:

[0085] In this embodiment, the original image I in step 1 o is an RGB image, the binary image I S Follow the steps below to generate:

[0086] Step 501: traverse the original image I o Calculate the color difference value of each pixel, wherein, the color difference value C of the i-th pixel, according to the following formula: C=2.0R-G-B, wherein, R, G and B represent that the pixel is in the red channel, green channel and blue channel respectively. The grayscale value under the color channel;

[0087] Step 502: traverse the original image I according to the following formula o For each pixel in the original image I o Do binarization:

[0088] Among them, T is the original image I after binarization o The gray value of the i-th pixel in ;

[0089] Step 503: For the binarized original image I o Perform morphological filtering to eliminate noise, holes and burrs in th...

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 relates to a segmentation and localization method for two mutually overlapped fruits in picking the fruits, and is particularly suitable for the quasi-circular fruits of which the fruit color and the background color have large chromatic aberration. The segmentation and localization method for the two overlapped fruits based on chromatic aberration comprises the steps that an original image Io of only two fruits are mutually overlapped is inputted and binarization is performed so that a binary image IS with the fruit area acting as a target area is obtained, then the minimum external affine rectangle of the target area, a target rectangle and two ROI subareas are successively selected on the binary image IS, a segmentation line dividing the target rectangle into two quadrilateral areas is obtained by connecting the central points of the two ROI subareas, and then the positions of the two fruits are determined by determining the centers of gravity of the two quadrilateral areas; and finally a circle is drawn with the centers of gravity of the two quadrilateral areas acting as the centers of circle and the distance from the two centers of gravity to any one intersection point of the segmentation line and the target rectangle acting as the radius, and the two circular areas are judged as the areas of the two fruits.

Description

technical field [0001] The invention relates to a method for segmenting and positioning two overlapping fruits when picking fruits, and is especially suitable for round fruits with large color difference between the fruit color and the background color. Background technique [0002] With the substantial reduction of fruit picking labor force in recent years, the cost of manual fruit picking is getting higher and higher. Therefore, the demand for fruit picking robots is increasing, and the requirements for fruit picking robots are also getting higher and higher. The key factor that determines the picking efficiency of the picking robot is the location of the fruit picking point. Since the fruits often overlap each other, the picking robot will treat the overlapping fruits as one fruit when positioning the fruit picking point, which is prone to large positioning deviations, and the fruit cannot be grabbed, which eventually leads to picking failure. In the prior art, the foll...

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 Applications(China)
IPC IPC(8): G06T7/136G06T3/00G06T7/66G06T5/00
CPCG06T2207/10024G06T2207/10004G06T2207/30188G06T3/147G06T5/70
Inventor 杨长辉李扬胡友呈王毅刘洒
Owner CHONGQING UNIV OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com