Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Garbage classification and detection system and method based on computer vision

A computer vision and garbage classification technology, applied in the field of deep learning, can solve the problems of lack of classification and recycling links, complex operation, low precision, etc., to achieve the effect of saving manpower, high matching degree and improving work efficiency

Inactive Publication Date: 2020-11-24
东北大学秦皇岛分校
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most cities in my country still adopt the method of mixed collection and centralized sorting. The garbage disposal system is not yet perfect, and there is a lack of strong action in the classification and recycling link. Therefore, the new policy of garbage classification issued by Shanghai has encountered many problems in the implementation; at present , the intelligent trash can manufacturing industry is constantly developing and maturing, but the traditional machine vision-based garbage sorting technology has problems such as complex operation and low precision, so it is necessary to design a smarter and faster garbage sorting system, so automatic garbage detection and classification design Has a very wide range of application value and market prospects

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
  • Garbage classification and detection system and method based on computer vision
  • Garbage classification and detection system and method based on computer vision
  • Garbage classification and detection system and method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0042] On the one hand, the present invention provides a garbage sorting detection system based on computer vision, including a garbage picking robot and a garbage sorting detection device;

[0043] In this embodiment, the garbage picking robot such as figure 1As shown, the first upper computer module (1) adopts the low-power embedded development platform Nvidia Jetson Tx2, the laser radar (4) adopts Radium God N30101B, and the first lower computer module (2) adopts Arduino Mega 2560 single-chip microcomputer, and the motor drive The module (6) adopts L298N, and the wireless module (8) adopts NRF24L01. The first host computer module is connected to the binocular camera (3) and the laser radar (4), and is responsible for processing the multidimensional array calculation in the visual information, the laser radar information and the algorit...

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 garbage classification and detection system and method based on a computer vision and relates to robot technology application and deep learning in artificial intelligence. Thesystem comprises a garbage pickup robot and a garbage classification and detection device, wherein the garbage pickup robot is connected with a binocular camera, a laser radar and an ultrasonic sensor. A target detection algorithm SSD-Mobilenet and an SLAM technique are embedded. In a patrolling process, through sensing of surrounding environments, an incremental map is established, and obstaclesare avoided in real time. When garbage is detected, the robot moves and controls a manipulator to collect the garbage. A garbage classification algorithm based on a depth separable convolutional neural network is embedded into the detection device. Through cooperation with the robot, the garbage is thrown to an accurate position. The system is mainly applied to garbage detection and classification tasks in life. The detection time can be reduced to a great extent. The classification precision can be improved. The system have certain application value.

Description

technical field [0001] The invention relates to the technical field of deep learning in the application of robot technology and artificial intelligence, in particular to a computer vision-based garbage classification and detection system and method. Background technique [0002] China is a country with a large population. As the pace of urbanization is getting closer, people have new pursuits for green and civilized life, but the garbage generated in daily life is increasing, and most of the garbage has not been strictly classified. , so the issue of garbage placement and disposal has become more and more important, and garbage classification has emerged as the times require. To put it simply, garbage classification refers to storing, putting and transporting different types of garbage separately according to corresponding regulations or standards. The purpose is to improve the resource value and economic value of garbage, make the best use of it, and benefit sustainable dev...

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): B07C5/34G06K9/00G06K9/62G06N3/04
CPCB07C5/34B07C2501/0054G06V20/10G06N3/044G06N3/045G06F18/214
Inventor 刘浩强闫冬梅
Owner 东北大学秦皇岛分校
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
Eureka Blog
Learn More
PatSnap group products