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

Improved forbidden article detection method based on YOLOv5 optimizer

An item detection and optimizer technology, applied in the field of prohibited item detection, can solve the problem of "object detection" being inaccurate and so on

Pending Publication Date: 2021-05-07
NANJING UNIV OF INFORMATION SCI & TECH
View PDF4 Cites 2 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 to propose an improved detection method for prohibited items based on the YOLOv5 optimizer, which is used to solve the problem of inaccurate "object inspection" in the current public transportation security inspection process

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
  • Improved forbidden article detection method based on YOLOv5 optimizer
  • Improved forbidden article detection method based on YOLOv5 optimizer
  • Improved forbidden article detection method based on YOLOv5 optimizer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0027] This example works in the Ubuntu18.04.4LTS environment, and uses PyTorch as the framework. The main parameters are: the initial learning rate is 0.001, the momentum parameter is 0.937, the weight coefficient is 0.0005, the training threshold is 0.5, the imagesize is 896×896, and the epoch In addition, in order to improve the diversity of the data, data enhancement is performed on the pictures to improve the generalization ability of the model; data amplification uses color amplification, random expansion and random clipping, and each step chooses whether to use.

[0028] In this embodiment, a method for detecting prohibited items based on the YOLOv5 optimizer is improved, and the recognition training steps are as follows: figure 1 Shown:

[0029] Construct a sample X-ray image set. The images in the sample X-ray...

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 an improved prohibited article detection method based on a YOLOv5 optimizer, and relates to the field of optical engineering and artificial intelligence, and the method comprises the following steps: (1) obtaining luggage X-ray image data; (2) dividing luggage X-ray image samples; (3) performing feature extraction of the luggage X-ray image; and (4) constructing a contraband luggage identification model. According to the invention, the luggage contraband detection model is constructed by adopting the convolutional neural network PANet, the PANet model can extract more and more effective feature information, and the luggage of the passenger can be efficiently and accurately detected under the condition that the luggage and personal belongings do not need to be disassembled. Therefore, passengers are ensured to pass smoothly, and better guarantee is provided for travel safety of the public.

Description

technical field [0001] The invention relates to a method for detecting contraband improved based on a YOLOv5 optimizer, which belongs to the fields of optical engineering and artificial intelligence. Background technique [0002] With the rapid development of the economy and society, the technological level is constantly updated, and the rail transit has been developed rapidly. The subway has gradually become an indispensable part of urban travel. However, the metro bus system has the characteristics of a closed environment, a large flow of people, and difficulties in evacuation. In order to ensure the safety of the public, Beijing took the lead in launching the subway security check mode, which is the same as the airport security check mode, in 2008, and then it was launched in various parts of the country. [0003] At present, the security inspection process of the subway and the airport is the same, mainly consisting of two parts: "personal inspection" and "object inspec...

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
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V2201/07G06N3/045G06F18/241G06F18/253G06F18/214
Inventor 邓壮壮朱节中高志文王方召卢峥松王明
Owner NANJING UNIV OF INFORMATION SCI & TECH
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