阅读说明：本技术 一种基于图像识别的智能分类垃圾桶控制系统 (Intelligent classification garbage bin control system based on image recognition ) 是由 郑水华 徐逸伦 林伟 于 2021-07-31 设计创作，主要内容包括：本发明公开一种基于图像识别的智能分类垃圾桶控制系统,其系统包括智能分类垃圾桶和图像识别服务器,所述智能分类垃圾桶和图像识别服务器以无线网络的方式进行连接。所述智能分类垃圾桶包括：多个用于存储不同类别垃圾的垃圾存储箱、安装于各个垃圾存储箱上的指示灯、摄像头、启动按钮、电子显示屏、垃圾存量监测模块和主控模块；所述摄像头用于采集用户投放垃圾的图像信息；所述启动按钮用于启动摄像头拍摄将要投放垃圾图像的功能；本发明能够采集用户所要投放垃圾的图像并进行垃圾类别识别,从而引导用户将垃圾投至对应类别的投放口,实现方便、快捷的智能垃圾分类,具有较好的用户体验。(The invention discloses an intelligent classification garbage can control system based on image recognition, which comprises an intelligent classification garbage can and an image recognition server, wherein the intelligent classification garbage can is connected with the image recognition server in a wireless network mode. The intelligent classification garbage bin includes: the garbage storage system comprises a plurality of garbage storage boxes for storing different types of garbage, indicator lamps, cameras, starting buttons, an electronic display screen, a garbage stock monitoring module and a main control module, wherein the indicator lamps, the cameras, the starting buttons, the electronic display screen, the garbage stock monitoring module and the main control module are arranged on the garbage storage boxes; the camera is used for collecting image information of garbage thrown by a user; the starting button is used for starting the function of shooting images of garbage to be thrown by the camera; the invention can collect images of the garbage to be thrown by the user and carry out garbage category identification, thereby guiding the user to throw the garbage to the throwing port with the corresponding category, realizing convenient and fast intelligent garbage classification and having better user experience.)

1. The utility model provides an intelligent classification garbage bin control system based on image recognition which characterized in that: the intelligent classification trash can comprises an intelligent classification trash can and an image recognition server, wherein the intelligent classification trash can and the image recognition server are connected in a wireless network mode; the intelligent classification garbage can comprises a plurality of garbage storage boxes for storing different types of garbage, indicator lamps, cameras, a starting button, an electronic display screen, a garbage stock monitoring module and a main control module, wherein the indicator lamps, the cameras, the starting button, the electronic display screen and the garbage stock monitoring module are arranged on the garbage storage boxes; the camera is used for collecting image information of garbage thrown by a user, the starting button is used for starting the function of shooting images of the garbage to be thrown by the camera, and when the user places the garbage to be thrown in front of the camera and presses the starting button, the camera starts the function of shooting the image information of the garbage and transmits the images to the main control module for subsequent processing; the main control module is responsible for determining the type of the garbage to be thrown in, displaying the analyzed type of the garbage on the electronic display screen, and controlling the indicator lights on the garbage storage boxes of the corresponding type to be turned on to guide a user to correctly throw the garbage; the indicating lamp can respectively display three colors of green, yellow and red according to the existing garbage stock monitored by the garbage stock monitoring module arranged on the inner wall of the garbage storage box from small to large, wherein the red represents that the garbage storage box is full and can not be used for continuously throwing garbage.

2. The intelligent classification garbage can control system based on image recognition according to claim 1, wherein: the main control module is responsible for determining the type process of the garbage to be thrown as follows: the main control module transmits the garbage images collected by the camera to the image recognition server through a wireless network, the image recognition server uses the deployed garbage classification recognition model to classify and recognize the garbage images to obtain recognition results, and the recognition results are transmitted to the main control module of the intelligent classification garbage can through the wireless network, so that the garbage classification is determined.

3. The intelligent classification garbage can control system based on image recognition according to claim 1, wherein: the main control module adopts a raspberry pi control chip.

4. The intelligent classification garbage can control system based on image recognition according to claim 1, wherein: the garbage classification recognition model deployed by the image recognition server is constructed on the basis of a Resnet-18 neural network, and is trained according to a large amount of garbage image data prepared in advance so as to improve the recognition accuracy of the model.

Technical Field

The invention relates to the field of intelligent control, in particular to an intelligent classification garbage can control system based on image recognition.

Background

Along with the rapid development of economy, the urbanization process of China is accelerated continuously, the living standard of people is improved continuously, and meanwhile, the urban domestic garbage is increased rapidly, so that the urban domestic garbage becomes a serious social problem. The traditional unreasonable garbage disposal methods such as incineration, landfill and the like can cause irreversible damage to the environment. Therefore, promotion of garbage classification is urgent. Although some regulations and regulations related to garbage classification have been developed at present, the classification of garbage is not smooth enough in urban communities, mainly because residents cannot know the classification of various types of garbage, the garbage classification brings great trouble to the residents, and people urgently need a system capable of automatically identifying the garbage classification. Therefore, the intelligent classification garbage can control system based on image recognition has great significance.

Disclosure of Invention

The invention aims to provide an intelligent classification garbage can control system based on image recognition, which can collect images of garbage to be thrown by a user and perform garbage category recognition, so that the user is guided to throw the garbage to a throwing port of a corresponding category, convenient and quick intelligent garbage classification is realized, and better user experience is achieved.

The invention realizes the purpose through the following technical scheme: the intelligent classification garbage can control system based on image recognition comprises an intelligent classification garbage can and an image recognition server, wherein the intelligent classification garbage can is connected with the image recognition server in a wireless network mode. The intelligent classification garbage bin includes: the garbage storage device comprises a plurality of garbage storage boxes for storing different types of garbage, and an indicating lamp, a camera, a starting button, an electronic display screen, a garbage stock monitoring module and a main control module which are arranged on the garbage storage boxes, wherein the indicating lamp, the camera, the starting button, the electronic display screen and the garbage stock monitoring module are connected with the main control module. The camera is used for collecting image information of garbage thrown by a user, the starting button is used for starting the function of shooting images of the garbage to be thrown by the camera, and when the user places the garbage to be thrown in front of the camera and presses the starting button, the camera starts the function of shooting the image information of the garbage and transmits the images to the main control module for subsequent processing; the main control module is responsible for determining the type of the garbage to be thrown in, displaying the analyzed type of the garbage on the electronic display screen, and controlling the indicator lights on the garbage storage boxes of the corresponding type to be turned on to guide a user to correctly throw the garbage; the indicating lamp can respectively display three colors of green, yellow and red according to the existing garbage stock monitored by the garbage stock monitoring module arranged on the inner wall of the garbage storage box from small to large, wherein the red represents that the garbage storage box is full and can not be used for continuously throwing garbage.

Furthermore, the main control module is responsible for determining the type of the garbage to be thrown in, the main control module transmits garbage images collected by the camera to the image recognition server through a wireless network, the image recognition server uses the deployed garbage classification recognition model to classify and recognize the garbage images to obtain recognition results, and the recognition results are sent to the main control module of the intelligent classification garbage can through the wireless network to determine the type of the garbage.

Furthermore, the main control module adopts a raspberry pi control chip.

Further, a garbage classification recognition model deployed by the image recognition server is constructed on the basis of the existing Resnet-18 neural network, and the garbage classification recognition model is trained according to a large amount of garbage image data prepared in advance so as to improve the recognition accuracy of the model.

The invention has the beneficial effects that:

1) according to the invention, the image information of the garbage to be thrown is acquired by using the camera, the garbage type is judged by combining with an image recognition algorithm model of a computer vision technology, the indicator light on the garbage storage box of the corresponding type is lightened according to the judgment result, and the user is guided to throw the garbage into the correct classified garbage throwing port, so that the intelligent recognition and the rapid and accurate classification of the garbage are realized, and the efficiency is higher.

2) The invention utilizes the garbage stock monitoring module to monitor the garbage stock in the garbage storage box, and when the garbage is nearly full, the indicating lamp arranged outside the garbage storage box can be controlled to display red light to prompt a user that the garbage throwing-in opening can not be used for throwing the garbage any more, and special sanitation workers need to wait for emptying the garbage storage box.

3) The invention uses the remote image recognition server to judge and process the garbage image category, can deploy, update and maintain the garbage image recognition algorithm model at the server end, shares the image recognition calculation work for the garbage can terminal equipment of the intelligent classification garbage can control system, and saves the energy consumption of the garbage can terminal equipment.

Drawings

FIG. 1 is a system framework diagram of the present invention;

fig. 2 is a functional flow diagram of the present invention.

Detailed Description

The invention is further described below with reference to the accompanying drawings:

as shown in fig. 1-2, an intelligent classification trash can control system based on image recognition includes an intelligent classification trash can and an image recognition server, where the intelligent classification trash can and the image recognition server are connected in a wireless network manner.

Specifically, intelligent classification garbage bin includes: the garbage storage device comprises a plurality of garbage storage boxes for storing different types of garbage, and an indicating lamp, a camera, a starting button, an electronic display screen, a garbage stock monitoring module and a main control module which are arranged on the garbage storage boxes, wherein the indicating lamp, the camera, the starting button, the electronic display screen and the garbage stock monitoring module are connected with the main control module.

Specifically, the camera is used for collecting image information of garbage thrown by a user, the start button is used for starting a function of shooting images of the garbage to be thrown by the camera, and when the user places the garbage to be thrown in front of the camera and presses the start button, the camera starts the function of shooting the image information of the garbage and transmits the images to the main control module for subsequent processing;

specifically, the main control module is responsible for determining the type of the garbage to be thrown, displaying the analyzed type of the garbage on the electronic display screen, and controlling an indicator lamp on a garbage storage box of the corresponding type to be turned on to guide a user to correctly throw the garbage;

specifically, the indicating lamp can respectively display three colors of green, yellow and red from small to large according to the existing garbage amount monitored by the garbage amount monitoring module arranged on the inner wall of the garbage storage box, wherein the red represents that the garbage storage box is full and the garbage can not be continuously thrown in.

Specifically, when the main control module is responsible for determining the type of the garbage to be thrown in, the main control module transmits the garbage image collected by the camera to the image recognition server through a wireless network, the image recognition server uses the deployed garbage classification recognition model to classify and recognize the garbage image to obtain a recognition result, and the recognition result is sent to the main control module of the intelligent classification garbage can through the wireless network to determine the type of the garbage.

Specifically, the main control module adopts a raspberry pi control chip.

Specifically, a garbage classification recognition model deployed by an image recognition server is constructed on the basis of the existing Resnet-18 neural network, and the garbage classification recognition model is trained according to a large amount of garbage image data prepared in advance so as to improve the recognition accuracy of the model.

The above embodiments are only preferred embodiments of the present invention, and are not intended to limit the technical solutions of the present invention, so long as the technical solutions can be realized on the basis of the above embodiments without creative efforts, which should be considered to fall within the protection scope of the patent of the present invention.