Passive terahertz security check method and system and medium

Abstract

The invention provides a passive terahertz security check method and system and a medium, and the method comprises the steps: judging whether a collected terahertz image is a first strip-shaped background image or not, and obtaining a global mean line vector of the image; removing stripe interference information in the original image; performing gray histogram extraction; distinguishing the difference between the background and the foreground by adopting an image segmentation algorithm, and extracting a segmentation threshold; performing secondary threshold segmentation processing according tothe segmentation threshold, and removing background interference; performing histogram equalization operation on the pixels; performing morphological processing; performing weighting processing on the image to obtain a final image; and establishing a YOLOV3 framework based on deep learning, configuring an operation environment, taking a final image as input for detection, and outputting a final type of suspicious dangerous goods carried by a human body. The deep learning detection has a higher recognition rate and a more reliable classification result, and successfully solves the problem thathidden suspicious dangerous goods are difficult to accurately recognize in a terahertz image.

Description

technical field [0001] The present invention relates to the technical field of security inspection, in particular to a passive terahertz security inspection method, system and medium. In particular, it relates to a passive terahertz security inspection system based on image processing technology and YOLOV3 deep learning detection technology. Background technique [0002] In recent years, with the frequent occurrence of terrorist bombing attacks and other incidents, people have put forward higher requirements for anti-terrorism security. Especially in public places where people gather, how to realize rapid detection and early warning of hidden weapons such as knives, guns and explosives carried by terrorists in dense crowds is a difficult problem for public security. The mainstream security detectors on the market are X-ray scanners. However, due to the high energy of X-ray electrons, it is easy to cause ionization damage to the detected substances. Therefore, it is not suit...

AI Technical Summary

Problems solved by technology

[0007] However, there are still some deficiencies in the application of terahertz technology in the field of human security inspection, mainly affected by factors such as detection sensitivity and electrical noise. Terahertz imaging is still not up to the clarity and target recognition ability of infrared focal plane array imaging, which makes The resolution of terahertz imaging is relatively low; at the same time, due to the influence of light wave diffraction and interference, there are obvious fringe interference noises in the image; in addition, due to external environmental interference, such as the absorption of terahertz waves by moisture in the air and atmospheric attenuation, etc. Hertzian image contrast is relatively low, and the edge information of objects is relatively blurred

[0008] For the detection method of dangerous goods hidden in the human body in terahertz images, the suspicious dangerous goods are usually segmented by complex image processing technology, and the relatively obvious features of the suspicious dangerous goods are extracted by using the traditional artificial design feature method, but these features are not enough To characterize the differences between various types of dangerous goods, which makes the subsequent pattern recognition results often unsatisfactory

Images