Shatian pomelo image recognition method for picking robot
A picking robot, image recognition technology, applied in image enhancement, image analysis, image data processing and other directions, can solve problems such as laborious, time-consuming, and expensive, and achieve the effect of improving the recognition success rate, fast recognition speed, and efficient recognition.
Pending Publication Date: 2022-03-15
SOUTH CHINA AGRI UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The automated fruit picking robot solves the time-consuming, labor-intensive and costly problems in the traditional fruit picking process through mechanical automation.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0068] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.
[0069] see Figure 1-Figure 3 , the Shatian pomelo image recognition method for picking robot of the present invention, comprises the following steps:
[0070] (1), after obtaining the original image of Shatian pomelo, use the color histogram to grayscale the mature and immature Shatian pomelo using different color difference formulas to obtain a grayscale image;
[0071] (2), using the threshold segmentation method to grayscale Figure II value to obtain a binary image;
[0072] (3), perform morphological operations on the binary image, and process image noise;
[0073] (4) Mark the connected area of the image after image noise processing, use the seed filling method to mark the area, and then remove the area with pixels less than area, and finally use the seed fi...
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
Login to View More Abstract
The invention discloses a Shatian pomelo image recognition method for a picking robot. The method comprises the following steps: graying a Shatian pomelo image with a color difference component R / 4 + 3G / 4-B for immature Shatian pomelo and a color difference component 2R-G-B for mature Shatian pomelo; binarizing the grey-scale image by using a threshold segmentation method; morphological operation is carried out on the binary image, and image noise is processed; marking connected regions, marking the regions by adopting a seed filling method, removing regions with smaller pixel points, and dividing the regions for the second time by adopting the seed filling method; performing region filling by using a scanning line filling method; discrete edge points are obtained, then the discrete points are integrated into a point chain in sequence, and edge extraction is carried out; and respectively obtaining the shape of the body circle and the shape of the head circle of the Shatian pomelo according to an edge point estimation optimization algorithm, obtaining the overall contour information of the Shatian pomelo, and carrying out image fitting to obtain a final Shatian pomelo identification mark. The Shatian pomelo image recognition method is higher in detection precision, and can efficiently recognize the position and state of the Shatian pomelo.
Description
technical field [0001] The invention relates to the field of artificial intelligence, in particular to a Shatian pomelo image recognition method for a picking robot. Background technique [0002] As a fruit harvesting tool, fruit picking robots can effectively solve the problems of labor shortage and high labor costs. Through automated picking, not only can the hygienic conditions of fruit picking be improved, but also the labor intensity of workers can be reduced and labor efficiency can be improved. The automated fruit picking robot solves the time-consuming, labor-intensive and costly problems in the traditional fruit picking process through mechanical automation. Manipulators are used to replace manual operations. Among them, whether the information of fruit location and fruit shape can be successfully obtained is the key to fruit picking. [0003] In the agricultural machine vision system, the identification and positioning of Shatian pomelo is the key factor to deter...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T5/00G06T5/30G06T5/40G06T7/136G06T7/90
CPCG06T7/0002G06T7/90G06T7/136G06T5/30G06T5/40G06T2207/10024G06T5/70
Inventor 彭红星黄中毓李荆
Owner SOUTH CHINA AGRI UNIV