Intelligent hazardous article detection method and system based on X-ray image
A detection method and detection system technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problems of poor model generalization performance, poor model performance, inconsistent use requirements, etc., to improve the accuracy and convergence speed, The effect of overcoming overfitting and improving mining ability
Active Publication Date: 2020-04-10
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] At present, the automatic detection methods based on X-rays all have the following shortcomings: (1) The targeted optimization of X-ray images is insufficient, and the semantic utilization rate of X-ray images is low, resulting in poor model performance and difficult to be used in actual production
(2) Only a few types of objects can be recognized, and it is very cumbersome to increase item categories and expand data sets, which does not meet the needs of actual life.
(3) It is very sensitive to preset thresholds and parameters, the generalization performance of the model is poor, there is a relatively obvious response to some random noise and color changes, and the actual performance is unstable
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0045] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings.
[0046] X-ray images are different from ordinary images. X-rays are electromagnetic waves that can penetrate opaque objects such as wood, cardboard, and leather. The security detector can display images of different colors on the screen according to the degree of absorption of X-rays by the object. Generally speaking, X-ray imaging has the following characteristics: the angle determines the shape, the distance determines the shape, the brightness determines the density, and the color indicates the composition. In the color mode, organic matter is displayed in different shades of orange and yellow, inorganic matter is displayed in different shades of green, and high-density items are displayed in black and deep red.
[0047] In fact, when inspecting items, security personnel mainly rely on two aspects of color and hierarchi...
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
Login to View More Abstract
The invention relates to an intelligent hazardous article detection method and system based on an X-ray image. The intelligent hazardous article detection system comprises an X-ray security inspectionmachine, a streaming media server, a GPU server and a monitoring alarm terminal, wherein the X-ray security inspection machine emits X-rays to an object, generates an X-ray image video stream according to a ray transmittance, and transmits the X-ray image video stream to the monitoring alarm terminal and the streaming media server; the streaming media server encodes and compresses an X-ray videostream and transmits an encoded and compressed X-ray video stream to the GPU server through a network; the GPU server decodes the video stream, predicts a decoded video stream based on the intelligenthazardous article detection method of the X-ray image, generates a result tuple, and transmits the result tuple to the alarm terminal; and the alarm terminal acquires and displays the X-ray image video stream and the result tuple. According to the invention, aiming at the characteristics of the X-ray image, a plurality of data enhancement methods are added; a loss function and a non-maximum suppression function are improved; model performances are effectively improved; and real-time detection of X-ray image hazardous articles is realized.
Description
technical field [0001] The invention belongs to the field of artificial intelligence and computer graphics, and in particular relates to an X-ray image-based intelligent dangerous goods detection method and system. Background technique [0002] X-ray-based security inspection machines are widely used in airports, railway stations, subway stations, bus stations, government buildings, embassies, conference centers, exhibition centers, hotels, shopping malls, large-scale events, post offices, schools, logistics industry, industrial inspection, etc. . In the security inspection industry, X-rays are generally used to detect bags and luggage. The X-ray security inspection device sends the checked luggage into the X-ray inspection channel by means of a conveyor belt to complete the inspection; during the security inspection, the X-ray machine emits X-rays. After passing through the inspected bags, an X-ray perspective view is formed on the X-ray detection box, and the dangerous go...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06N3/04G01N23/10G01V5/00
CPCG06T7/0002G01N23/10G06T2207/10116G06T2207/20081G06T2207/30232G06N3/045G01V5/22
Inventor 石宇徐小龙
Owner NANJING UNIV OF POSTS & TELECOMM