Abstract
The detection of objects concealed under people’s clothing is a very challenging task, which has crucial applications for security. When testing the human body for metal contraband, the concealed targets are usually small in size and are required to be detected within a few seconds. Focusing on weapon detection, this paper proposes using a real-time detection method for detecting concealed metallic weapons on the human body applied to passive millimeter wave (PMMW) imagery based on the You Only Look Once (YOLO) algorithm, YOLOv3, and a small sample dataset. The experimental results from YOLOv3-13, YOLOv3-53, and Single Shot MultiBox Detector (SSD) algorithm, SSD-VGG16, are compared ultimately, using the same PMMW dataset. For the perspective of detection accuracy, detection speed, and computation resource, it shows that the YOLOv3-53 model had a detection speed of 36 frames per second (FPS) and a mean average precision (mAP) of 95% on a GPU-1080Ti computer, more effective and feasible for the real-time detection of weapon contraband on human body for PMMW images, even with small sample data.
Highlights
The detection of concealed targets under people’s clothing is essential for public security
The YOLOv3-13 model uses a 13-layer convolution network with an 85% mean average precision (mAP) on the individual test set
Different from traditional metal security gates and X-ray detectors, non-contact and non-cooperative passive millimeter wave (PMMW) imagers have become a primary choice for security checks in large public places
Summary
The detection of concealed targets under people’s clothing is essential for public security. With the unique advantage of penetrating most materials, except for metal and water, millimeter wave imaging systems have been employed for concealed target visualization without privacy concerns [1]. Different from active modes, the millimeter sensor usually relies on its strong penetrability, and targets can be identified through their naturally emitted and reflected radiations, detected by using a Passive. Numerous image processing techniques, such as image denoising [7], image fusion [8], segmentation [9,10], classification [11,12], object detection and recognition [13,14,15,16] etc., have been developed and applied to PMMW imagery in the last few decades. The above methods of PMMW data processing are mainly used to perform filtering, threshold segmentation, Sensors 2020, 20, 1678; doi:10.3390/s20061678 www.mdpi.com/journal/sensors
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
