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

Target detection method for identifying urban exposed garbage

A technology of target detection and garbage, applied in the field of target detection, can solve the problems of high cost, can not meet the urban governance and other problems, and achieve the effect of improving the city appearance.

Active Publication Date: 2021-03-26
中再云图技术有限公司
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: the existing technology uses pure human resources to identify exposed garbage, which is inefficient and expensive and cannot meet the needs of urban governance

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
  • Target detection method for identifying urban exposed garbage
  • Target detection method for identifying urban exposed garbage
  • Target detection method for identifying urban exposed garbage

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to illustrate the specific identification method of the present invention more clearly, the key content involved in S6 of the present invention will be described below with the help of drawings.

[0032] Such as Figure 4 As shown, the present invention provides a kind of identification method of urban exposed garbage, comprising the following steps:

[0033] S1: Prepare to expose the garbage source data set S, and send several staff members to visit various streets in the city, road intersections, garbage cans, etc. where garbage is easily discarded, and use mobile phones to take photos of the exposed garbage, and then summarize them as Expose source datasets for spam identification.

[0034] S2: Label the location and category of exposed garbage. The staff uses the labelImg data labeling tool to label the source data set of exposed garbage identification, frame the location of exposed garbage in the photo, and label the category of exposed garbage.

[0035]...

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 target detection method for identifying urban exposed garbage. The method mainly comprises the following steps: S1, shooting exposed garbage pictures distributed in a city byadopting a mobile phone, and arranging the exposed garbage pictures as a source data set S; S2, marking positions and types of exposed garbage; S3, converting a source data set S into a data set CS ina COCO format in combination with the xml data; S4, normalizing the CS data set in a zero-mean manner, and recording the normalized CS data set as a data set ZCS; S5, on the data set ZCS, selecting apart of the data set as a test set tes_ZCS, selecting a part of data in the remaining part of the data set as a verification set val_ZCS, and taking the remaining part of the data set as a training set tra_ZCS; S6, training an exposed garbage recognition model; and S7, judging whether exposed garbage exists or not by adopting the exposed garbage recognition model. The exposed garbage is detectedand recognized in a target detection mode, so that the urban exposed garbage is automatically recognized and treated in time, garbage exposure in the public view is reduced, the urban appearance is effectively improved, and the urban appearance is further improved in an intelligent civilized city.

Description

technical field [0001] The invention mainly relates to the field of image recognition of artificial intelligence, belongs to the field of environmental protection of intelligent cities, and specifically relates to a target detection method. Background technique [0002] Object detection is one of the core technologies of computer vision and digital image processing, and has broad application prospects in the fields of navigation, monitoring, detection, and recognition. Through the research of computer vision, object detection reduces the dependence on human resources and liberates manpower, which is of great significance to the modern technological society. Therefore, many scholars and researchers have worked hard to study and have achieved fruitful results in the research of target detection. Until today, the research on target detection is still moving forward. Due to the wide application of deep learning, the target detection algorithm has developed rapidly in a period 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): G06K9/00G06K9/62
CPCG06V20/38G06F18/214G06F18/24Y02W90/00
Inventor 孙德亮
Owner 中再云图技术有限公司
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