Visual Recognition System for Cotton Picking Robot

A visual recognition and visual system technology, applied in the field of image positioning and recognition, can solve problems such as difficulty, long mechanization road, and long cycle, and achieve the effect of low cost, strong versatility, and accurate extraction

Active Publication Date: 2021-09-07
NANJING INST OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, traditional mechanized high-efficiency harvesting devices are difficult to directly meet the requirements of such selective harvesting, and it is difficult to mechanize cotton picking and harvesting through agronomic means in the short term, and the cycle is long, which cannot be solved in a short time.
In other words, such a mechanized road is too long for the inland cotton-growing areas

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be further described below. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0025] In this vision system, a multi-eye stereo vision servo mechanism based on the combination of binocular stereo vision and monocular vision system is used. This kind of visual servo mechanism comes from: Zhou Jun, Liu Rui, etc., fruit picking robot system design based on stereo vision, agricultural machinery Journal of the Chinese Academy of Sciences, 2010, 41(6): 159-162.

[0026] In step 2), although the human eye is more sensitive to the details of the image, it is less sensitive to most flat areas. Therefore, we assume that the values ​​​​of pixels in the non-boundary area within a sliding window are basically equal ; while the value of pixels in the boundary area changes greatly. Under this premise, the 5×5 sliding window is cen...

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 visual recognition system suitable for a cotton picking robot, which is characterized in that it includes visual system setting, cotton image filtering, cotton image segmentation, cotton image target detection, edge extraction, feature extraction and maturity Classification. Image filtering adopts the image segmentation method of Unit-linking PCNN based on edge product mutual information; realizes cotton positioning based on improved adaptive genetic algorithm, and then uses fast multi-scale edge algorithm to realize image segmentation; through cotton image features, texture features, geometry Research on shape characteristics, and realize cotton maturity classification based on principal component analysis. The invention is a research on a cotton picking robot based on image vision, which has the characteristics of low cost, strong versatility and convenient use, and has good application prospects.

Description

technical field [0001] The invention relates to a visual recognition system suitable for a cotton picking robot, belonging to the technical field of image positioning and recognition. Background technique [0002] my country's cotton planting area is vast, and the hilly landforms in the south are relatively common. The cotton varieties and production scales are diversified. The mature opening period of cotton is inconsistent, and the length of fibers is different. At present, large-scale cotton pickers used both internationally and domestically require chemical The cooperation of interferon and other related equipment can play its function well, that is, after picking, it must go through complicated cleaning and separation links to separate the cotton wool from the branches and leaves, or it needs to rely on agronomy to improve varieties. Therefore, traditional mechanized high-efficiency harvesting devices are difficult to directly meet the requirements of such selective harv...

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): G06T7/00G06T7/62
CPCG06T2207/30188
Inventor 刘坤高金凤汪木兰刘娣
Owner NANJING INST OF TECH
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