Human body hidden object detection method based on a millimeter wave image

Abstract

The invention discloses a human body hidden object detection method based on a millimeter wave image. The method comprises the steps of traversing millimeter wave image data containing multiple anglesof a human body; respectively rotating the preprocessed millimeter wave image data at different angles to obtain training data; training the training data to obtain model parameters, sequentially performing preprocessing and rotation at different angles on the millimeter wave image to be detected to obtain test data, detecting the test data by utilizing the model parameters at the corresponding rotation angles to obtain a plurality of groups of detection results, and performing fusion to obtain a final detection result. According to the model network provided by the invention, the multi-viewcharacteristic of the millimeter wave image in the security check scene can be better utilized, the human body area is divided into multiple parts, only the characteristics of the normal human body area need to be remembered, the hidden object does not need to be directly recognized, diversity of the hidden object is well avoided, the generalization ability is high, and the detection accuracy of an existing millimeter wave image hidden object detection method is further improved.

Description

technical field [0001] The invention belongs to the field of millimeter-wave image target detection, and more specifically relates to a method for detecting human hidden objects based on millimeter-wave images. Background technique [0002] In order to prevent passengers from carrying drugs, guns, explosives and other prohibited objects, the deployment of human body security inspection equipment in areas with high traffic such as airports, subway stations, and high-speed rail stations has become an important means of protecting people's lives and property. The fact that it is harmless and can penetrate clothing makes it very promising. The traditional method of manually interpreting security inspection images not only has the problem of violating the privacy of the inspected personnel, but is also very susceptible to missed detection and false detection due to human factors. Therefore, an automatic detection method for hidden objects in millimeter wave images with high accur...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the defects of the prior art, the purpose of the present invention is to provide a method for detecting hidden human objects based on millimeter-wave images. For the problem of high diversity of hidden objects, use integrated learning methods to deal with the problem of poor generalization ability of millimeter wave image hidden object detection methods, and further improve the detection accuracy of existing millimeter wave image hidden object detection methods

Images