Method and system for detecting three packets in front of door based on deep learning

A deep learning and packet detection technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problems of high labor cost, difficult to maintain for a long time, etc., to reduce alarms, low false positive rate, and reduce manual labor Effect

Pending Publication Date: 2022-03-01
苏州折多山科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, the existing "three guarantees in front of the door" responsibility needs to be carried out by regular inspection or reporting by people, which requires a lot of labor costs and is difficult to maintain for a long time

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
  • Method and system for detecting three packets in front of door based on deep learning
  • Method and system for detecting three packets in front of door based on deep learning
  • Method and system for detecting three packets in front of door based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described below in conjunction with the accompanying drawings.

[0031] Such as figure 1 Shown is a detection method based on deep learning, including the following steps:

[0032] S1. Set up the three-package area in front of the door, install a camera, collect pictures of ideal cleaning conditions in the three-package area in front of the door in different scenarios, and set them as background pictures in different scenarios, and store all background pictures in the background library; set Ordinary object database, used to store ordinary object models, ordinary objects are abnormal objects that do not affect the ideal cleaning state of the three-package area in front of the door; set up a clutter database, used to store clutter models, and clutter are objects that affect the cleanliness of the three-package area in front of the door Abnormal objects in an ideal state; distinguishing between the database of ordinary objects and th...

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 method and a system for detecting three packets in front of a door based on deep learning. The system comprises a configuration module, an abnormal object detection module, a repeatability judgment module, a system early warning module and a manual processing module. A configuration module is used for setting three-package areas in front of a door, and a background library, a normal object database and a clutter object database are established; abnormal objects in a three-bag area in front of the door are detected through an abnormal object detection module; carrying out repetition degree judgment on the abnormal object through a repetition degree judgment module; through a system early warning module, early warning is carried out on abnormal objects meeting the repetition degree, and manual processing is notified; performing manual confirmation on the abnormal object through a manual processing module: if the abnormal object is confirmed to be a disordered object, issuing a work order for processing, and calling the disordered object to construct a model; and if it is confirmed that the object is a normal object, calling the normal object to construct a model. The system can replace manual work to efficiently and accurately complete door front three-bag detection, and then a good image of a city can be effectively maintained.

Description

technical field [0001] The invention relates to a method and system for detecting three packages in front of the door based on deep learning, which belongs to computer deep learning technology. Background technique [0002] The "Three Guarantees in front of the door" is an important measure to promote the construction of a civilized city, and it can completely rectify the stubborn urban diseases of "dirty, chaotic, and poor". The "Three Guarantees in front of the door" mainly include the following parts: [0003] (1) Package environmental sanitation: the ground should be free of rubbish and dirt such as melon peel cores, cigarette butts, paper scraps, and no accumulated water or snow; garbage should be sorted and bagged, and placed at fixed points and regularly; garbage, etc., should not be swept into the road , sewers, green areas and areas of responsibility of others. [0004] (2) Including landscaping and greening: the facade of the building (structure) should be clean ...

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): G06V20/52G06V10/25G06V10/82G06K9/62G06N3/04G06N3/08G06Q50/26
CPCG06N3/08G06Q50/26G06N3/045G06F18/22
Inventor 黄建鹏魏宝军
Owner 苏州折多山科技有限公司
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