Method for identifying bunch-type fruit mother branch based on monocular camera and binocular camera

A binocular camera and camera technology, applied in character and pattern recognition, computer parts, instruments, etc., can solve the problems of inability to accurately find string-shaped fruit mother branches, fruit strings that are easy to grow in random distribution, and difficult to identify fruit strings.

Active Publication Date: 2021-05-11
CHONGQING UNIV OF ARTS & SCI
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the growth characteristics of the bunch-shaped fruit itself, the whole fruit bunch is very easy to grow randomly, which makes it difficult to identify the fruit bunch, the identificati

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
  • Method for identifying bunch-type fruit mother branch based on monocular camera and binocular camera
  • Method for identifying bunch-type fruit mother branch based on monocular camera and binocular camera
  • Method for identifying bunch-type fruit mother branch based on monocular camera and binocular camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] Such as Figure 1~2 As shown, taking lychee string fruit as an example, a method for identifying the mother branch of string fruit based on a monocular camera and a binocular camera is characterized in that:

[0041] S001, using a monocular CCD camera to randomly acquire multiple color images together with features such as string-shaped fruits, leaves and branches;

[0042] S002. Select and divide a plurality of fruit objects and non-fruit objects in the color image, and respectively extract texture feature values ​​and color feature values ​​of the fruit objects and non-fruit objects as positive and negative samples;

[0043] S003. Use the support vector machine SVM to train the positive and negative samples to generate multiple weak classifiers; then use the AdaBoost algorithm to construct a strong classifier, use the strong classifier to segment the color image obtained by the monocular CCD camera, and identify the The fruit target is stored separately as a color im...

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 provides a method for identifying a bunch-type fruit mother branch based on a monocular camera and a binocular camera. The method comprises: firstly, acquiring a color image of bunch-type fruit characteristics including fruits, leaves and branches by adopting the monocular camera; training, segmenting, identifying and extracting the color image by using a support vector machine and an AdaBoost algorithm to obtain color images of fruits, leaves and branches then; classifying single-fruit bunches, double-fruit bunches and multi-fruit bunches of the fruits by utilizing a fruit bunch classification principle, and then identifying fruit bunch mother branches through perpendicular bisectors of upper and lower bottoms of outlines of fruit bunches, which are externally tangent to rectangles; and finally, obtaining a binocular stereo image of the mother branch of the fruit bunch by adopting a binocular camera, realizing feature matching of the left image and the right image by utilizing a normalized cross-correlation function, and finally obtaining the space coordinate of the mother branch. According to the method, the fruit bunches can be accurately and effectively identified, the mother branches of the fruit bunches can be positioned, intelligent picking of bunch type fruits is achieved, the picking efficiency is high, and the labor cost is effectively reduced.

Description

technical field [0001] The invention relates to the technical field of fruit intelligent picking, in particular to a method for identifying string-shaped fruit branches based on a monocular camera and a binocular camera. Background technique [0002] my country is the main producer of longan, grape, lychee and other bunch-shaped fruits. The total planting and production volume ranks among the top in the world, and has huge economic potential; for example, litchi, as a typical subtropical bunch-shaped fruit, is planted in South China It has become one of the important economic pillars for farmers to get rid of poverty and become rich. [0003] At present, picking string-shaped fruits is basically carried out manually, which is labor-intensive and expensive, and wastes a lot of manpower and material resources. With the advancement of science and technology and the development of intelligence level, there are more and more researches and applications of picking robots, which br...

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): G06K9/00G06K9/62
CPCG06V20/10G06V20/68G06F18/2148G06F18/22G06F18/2411
Inventor 王成琳罗天洪柳苏纯王雅薇罗陆锋熊俊涛
Owner CHONGQING UNIV OF ARTS & SCI
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