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

Method for detecting fruit target in using apple pick-up robot based on deep learning

A picking robot and target detection technology, which is applied to instruments, computer components, character and pattern recognition, etc., can solve problems such as interference, image noise, machine vision system detection and difficulty in approaching fruits, etc. Effects of stickiness and generalization

Inactive Publication Date: 2018-01-26
ZHEJIANG UNIV OF TECH +1
View PDF1 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Over the years, a large number of scientific and technological workers at home and abroad have devoted themselves to the research of harvesting robot vision systems. However, due to the complex and changeable working environment of robots, and the complex and diverse growth states of work objects (fruits, leaves, branches), resulting in a lot of noise in the captured images and interference information, which makes it extremely difficult for the machine vision system to detect and approach the fruit

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 detecting fruit target in using apple pick-up robot based on deep learning
  • Method for detecting fruit target in using apple pick-up robot based on deep learning
  • Method for detecting fruit target in using apple pick-up robot based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The present invention will be further described below in conjunction with the accompanying drawings.

[0019] A kind of apple picking robot fruit target detection method based on deep learning of the present invention, specifically comprises the following steps:

[0020] Step 1 (sample data collection): Go to the apple plantation during the apple harvest season, use the camera carried by the mobile intelligent robot, select as many angles as possible, and take pictures of the fruit trees under the conditions of forward light and backlight respectively. Cut the apple fruit part in the picture into positive samples of uniform size, and crop the part without apple fruit into negative samples of uniform size. The number of positive samples and negative samples should be at least 5000.

[0021] Step 2 (extract fusion features): Use the image function in matlab to extract RGB or LUV color components, and extract the edge gradient information of the detection target through 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 discloses a method for detecting a fruit target in using an apple pick-up robot based on deep learning. The method includes the following steps: using a camera which is carried by an intelligent mobile robot to photograph sufficient apple tree and fruit images thereof, training classifiers of different sizes, performing sliding detection on a to-be-picked up image through a sliding window, determining the presence of a fruit window, and performing fruit detection by inputting the window to a convolutional neural network.

Description

technical field [0001] The invention relates to a method for realizing fruit target detection of an apple picking robot by using a deep learning target detection algorithm, in particular to a method for using a deep learning algorithm to identify and detect visual images of a picking robot and to calibrate the fruit area, belonging to the field of machine vision . Background technique [0002] China is a big apple producing country. The workload of picking apples is the largest in the production process, accounting for about 40% of the total labor. The quality of picking will have an impact on the storage, handling, processing and sales of fruits, etc. . Due to the high requirements of picking operations, most of the picking work is done by hand, but the cost of manual picking is high, and it takes a long time to meet the needs of large-scale planting. Therefore, in order to improve production efficiency and liberate farmers from heavy picking operations, fruit mechanical ...

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): G06K9/00G06K9/62
Inventor 王万良鞠振宇邱虹杨平应森亮郑建炜
Owner ZHEJIANG 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