Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

X-ray contraband package detection method and device based on feature map re-empowerment

A detection method and contraband technology, applied in the direction of neural learning methods, instruments, biological neural network models, etc., can solve problems such as large manpower and material resources, reduced work efficiency, missed detection and increased false detection

Active Publication Date: 2020-12-11
SOUTH CHINA UNIV OF TECH
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For safety reasons, traditionally, professional security inspectors are required to manually observe the X-ray image of each package next to the X-ray machine to confirm whether the package contains contraband, which requires a lot of manpower and material resources, and the work efficiency increases with the security personnel. The fatigue degree increases and decreases, and the cases of missed detection and false detection will increase accordingly
[0004] At present, the main method of identifying contraband in parcels is mainly to rely on manpower for security inspection, which usually requires several groups of staff to work in turn, and each group includes at least one professional security inspector and two sorting personnel, so that the traditional package detection scheme exists. The problem of low efficiency and high cost

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
  • X-ray contraband package detection method and device based on feature map re-empowerment
  • X-ray contraband package detection method and device based on feature map re-empowerment
  • X-ray contraband package detection method and device based on feature map re-empowerment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0050] Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiment...

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 an X-ray contraband package detection method and device based on feature map re-empowerment, and the method comprises the steps: building an X-ray contraband training set, sequentially obtaining an image feature map, a region-of-interest feature map and a class attention feature map, carrying out the re-empowerment of the region-of-interest feature map through the class attention feature map, and obtaining a single-dimensional feature vector; determining prediction categories of various contraband products, adjusting a feature extraction network, a meta-feature extractor and a classification regression network adopted in the next training process, and returning to execute the process of sequentially acquiring an image feature map, a region-of-interest feature map and a class attention feature map; and inputting the X-ray contraband training set into the adjusted feature extraction network again for iterative training until the number of training times is greaterthan or equal to a preset number of iterations, determining a contraband detector, and inputting the to-be-detected package into the contraband detector to obtain a contraband position and a contraband category output by the contraband detector, thereby achieving the effects of saving manpower and material resources and reducing the detection cost.

Description

technical field [0001] The invention relates to the technical field of intelligent detection, in particular to a method, device, computer equipment and storage medium for X-ray contraband package detection based on feature map reweighting. Background technique [0002] X-ray images are images obtained by X-rays penetrating the object to be detected and rendering different colors according to the different densities of the object. It is often used in security checks to identify contraband. Compared with ordinary images, X-ray images only have color and shape information, and it is more difficult to detect and identify objects. Therefore, X-ray contraband detection has always been a difficult problem to be solved. [0003] Especially in recent years, the development of the transportation industry and the fast industry has caused enormous pressure on luggage / express security checks. In order to ensure the safety of public areas, before taking a large vehicle, the items carried...

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): G06K9/32G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/25G06V10/40G06N3/045G06F18/2411
Inventor 高红霞廖宏宇林国远
Owner SOUTH CHINA UNIV OF TECH
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
Eureka Blog
Learn More
PatSnap group products