Household garbage real-time detection method and device, electronic equipment and medium

A technology for real-time detection of domestic garbage, applied in the field of computer vision, can solve problems such as high proportion of organic waste, poor work quality, high water content, etc., and achieve the effect of improving detection accuracy, improving accuracy, and excellent detection accuracy

Pending Publication Date: 2022-05-13
XIAN UNIV OF POSTS & TELECOMM
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Domestic waste is mostly mixed raw waste, with high water content and a high proportion of organic waste, which cannot be effectively and quickly resolved by traditional domestic waste treatment methods.
The traditional domestic waste classification method has the characteristics of labor-intensive, low efficiency, and poor work quality.

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
  • Household garbage real-time detection method and device, electronic equipment and medium
  • Household garbage real-time detection method and device, electronic equipment and medium
  • Household garbage real-time detection method and device, electronic equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Such as figure 1 As shown, a real-time detection method for domestic garbage based on attention mechanism combination proposed in this embodiment includes the following steps:

[0048] S1: Obtain a garbage image detection data set, and divide the garbage image detection data set into a training set, a verification set and a test set;

[0049] In this embodiment, the garbage image detection data set is obtained by collecting garbage images online, capturing household garbage in videos, and taking photos, etc., and marking all household garbage in the images according to their product names to obtain a total of 13 types of garbage, and 13 is divided into four categories, namely: domestic garbage, recyclable garbage, hazardous garbage and other garbage, establish a garbage detection data set containing multiple categories, and divide the data set into training set, verification set and test set; Specific steps are as follows:

[0050] Step S1-1: define the type and size ...

Embodiment 2

[0076] The present invention also provides a cultural relic image color restoration device, which includes:

[0077] A preprocessing module, configured to obtain a garbage image detection data set, and divide the garbage image detection data set into a training set, a verification set and a test set;

[0078] The training module is used to input the rubbish images in the training set and the verification set into the improved YOLOv5s network model respectively and carry out iterative training through GPU, and obtain the optimal weight of the improved YOLOv5s network model after training; the improved YOLOv5s network model The YOLOv5s network model is improved on the YOLOv5s network model, specifically: a lightweight feedforward convolutional attention module CBAM is introduced after the front-end Focus module of the backbone network of the YOLOv5s network model, and SE- Net channel attention module;

[0079] The garbage detection module is used to load the optimal weight into...

Embodiment 3

[0091] The present invention also provides an electronic device, which is characterized in that the electronic device includes: at least one processor; and a memory connected in communication with the at least one processor; wherein, the memory stores Instructions that can be executed by the at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can execute the method for real-time detection of domestic waste based on the attention mechanism combination of Embodiment 1 .

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 household garbage real-time detection method based on attention mechanism combination, and the method comprises the following steps: obtaining a garbage image detection data set, inputting garbage images in the garbage image detection data set into an improved YOLOv5s network model, and carrying out the iterative training through a GPU, the optimal weight of the improved YOLOv5s network model is obtained through training; the optimal weight is loaded into the improved YOLOv5s network model, a junk image needing to be detected is input, a detection result is output, and the detection result comprises the position of the target junk on the image and the category of the target junk. The garbage image detection speed is higher, the precision is higher, the requirement for real-time detection of household garbage can be met, the calculated amount of a network model is reduced to a certain degree, the reasoning speed and the detection precision are improved, an efficient detection method is provided for garbage classification, the consumption of labor cost is reduced, and the development of garbage classification intelligence is accelerated.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a real-time detection method, device, electronic equipment and medium for domestic garbage based on attention mechanism combination. Background technique [0002] In recent years, with the rapid development of the global economy, the consumption level of residents has increased significantly, the scale of urban population has continued to expand, and the amount of domestic waste has gradually increased. As of 2020, the annual output of domestic waste in the world is close to 34 million tons, and the annual output of domestic waste in China is close to 20 million tons, ranking first in the world. Therefore, in 2017, the Ministry of Housing and Urban-Rural Development issued a notice on accelerating the classification of domestic waste in some key cities, clearly pointing out the acceleration of domestic waste classification. In 2019, the State Administration o...

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): G06K9/62G06N3/04G06N3/08G06Q50/26G06V10/774G06V10/82
CPCG06Q50/26G06N3/08G06N3/048G06N3/045G06F18/214
Inventor 江祥奎胡浩昌
Owner XIAN UNIV OF POSTS & TELECOMM
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap