Garbage classification and detection system and method based on computer vision

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...

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

Images