Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

An 8mm-band passive millimeter-wave imager BHU-2D has been developed by Beihang University. This imager is designed for detecting concealed weapons on human body. The imager adopts two-dimensional synthetic aperture interferometric radiometer (SAIR) technique which avoids the radiation risk to human body. Compared with scanning technique, SAIR technique could obtain images of a larger fleld of view (FOV) while achieving high imaging rate, which are necessary for security monitoring. In this paper, the imaging principle of SAIR is stated flrstly. Secondly, background cancellation method designed for BHU-2D is interpreted. The technique is used to reduce the complexity as well as the dimensional requirements of the receiving elements. Thirdly, system conflguration is illustrated in detail. Then external point source calibration method is introduced and discussed speciflcally for security check applications. Finally, imaging experiments on a person with concealed weapon are conducted by which the design and image calibration algorithms are verifled. To conclude, experimental results prove that BHU-2D could be employed in security check applications.

/pdf/a-passive-millimeter-wave-imager-used-for-concealed-weapon-1skjyf0910.pdf

A Passive Millimeter-Wave Imager Used for Concealed Weapon Detection

Millimeter wave (MMW) imaging is finding rapid adoption in security applications such as concealed object detection under clothing. A passive MMW imaging system can operate as a stand-off type sensor that scans people in both indoors and outdoors. However, the imaging system often suffers from the diffraction limit and the low signal level. Therefore, suitable intelligent image processing algorithms would be required for automatic detection and recognition of the concealed objects. This paper proposes real-time outdoor concealed-object detection and recognition with a radiometric imaging system. The concealed object region is extracted by the multi-level segmentation. A novel approach is proposed to measure similarity between two binary images. Principal component analysis (PCA) regularizes the shape in terms of translation and rotation. A geometric-based feature vector is composed of shape descriptors, which can achieve scale and orientation-invariant and distortion-tolerant property. Class is decided by minimum Euclidean distance between normalized feature vectors. Experiments confirm that the proposed methods provide fast and reliable recognition of the concealed object carried by a moving human subject.

Real-time concealed-object detection and recognition with passive millimeter wave imaging

A passive millimeter-wave imager BHU-2D-U has been developed by Beihang University. This imager is designed for detecting concealed weapons on human body. It is a subsequent model of BHU- 2D, which is also developed by the same group. In this paper, the improvements of BHU-2D-U over BHU-2D are introduced. Firstly, BHU-2D-U is used for whole body scan, which is difierent from BHU- 2D. Thus, the fleld of view (FOV) of the new imager is enlarged and a new antenna array type is adopted. Secondly, the enlarged FOV requires smaller antenna spacing and compact receiver arrays. In order to reduce the volume of the receivers, I/Q demodulators operating in double side band mode are adopted because it does not need the image-reject fllter, which is usually a bulky one. Thirdly, the quantity of the correlators increases because the number of receiving elements is doubled. To cope with the increase of the correlator quantity, a multiplexing technique is used in the FPGA internal layout of the correlator array unit. After a brief introduction, the system design and conflguration is illustrated in detail. Finally, imaging experiments on a person with concealed weapon are conducted, by which the design and image reconstruction algorithms are verifled. To conclude, initial results of BHU-2D-U have proved that the improvements are efiective.

/pdf/initial-results-of-a-passive-millimeter-wave-imager-used-for-4cjvusoup0.pdf

Initial results of a passive millimeter- wave imager used for concealed weapon detection bhu-2d-u

Passive millimeter and terahertz wave imaging has become a significant potential technique for human security check and scene monitoring. Due to the small difference of the brightness temperatures between human body and concealed objects, the temperature sensitivity and spatial resolution of radiometers are always the key performance indexes which are difficult to improve. Therefore, when the hardware performance is given, improving detectivity becomes a pressing need. In this paper, a physically-based concealed object enhancement method using multi-polarization information is presented. The polarization model and polarization property of human body and concealed objects have been analyzed. By fusing multiple polarization images, we can obtain a complete polarization image in which the contrast between human body and concealed objects is enhanced and stable. The experimental results of simulation and measurement demonstrate the enhancement performance, and Differential Signal Noise Ratio (DSNR) is obviously improved by using the proposed method.

Concealed object enhancement using multi-polarization information for passive millimeter and terahertz wave security screening.

Millimeter wave (MMW) readily penetrates fabrics, thus it can be used to detect objects concealed under clothing. A passive MMW ima- ging system can operate as a stand-off type sensor that scans people both indoors and outdoors. However, because of the diffraction limit and low signal level, the imaging system often suffers from low image quality. Therefore, suitable computational processing would be required for auto- matic analysis of the images. The authors present statistical and compu- tational algorithms and their implementations for real-time concealed object detection. The histogram of the image is modeled as a Gaussian mixture distribution, and hidden object areas are segmented by a multi- level scheme involving the expectation-maximization algorithm. The com- plete algorithm has been implemented in both MATLAB and C++. Experimental and simulation results confirm that the implemented system can achieve real-time detection of concealed objects. © 2012 Society of Photo- Optical Instrumentation Engineers (SPIE). (DOI: 10.1117/1.OE.51.7.071405)

Real-time computational processing and implementation for concealed object detection

In this paper, we developed and experimented of the W-band 1-D focal plane array (FPA) passive imaging radiometer which was called by Millimeter-wave Imaging Radiometer Equipment (MIRAE). This consists of quasi-optics including a dielectric aspheric lens and a metal mirror as a reflector, 30 channels FPA receiver based on the direct conversion type, scanner, image processor and displayer. To get 2-D radiometer image with 1 Hz frame rate, the radiometric 1-D FPA receiver is moved into one direction by the linear scanner. From the experiment results, it is certain that MIRAE system can get enough good outdoor radiometer images to detect concealed metal weapons under clothing in the short range application such as security, comparing with other commercial and competitive passive imaging radiometer systems at W-band.

System design of focal plane array based Millimeter-wave Imaging radiometer for concealed weapon detection

Millimeter wave (MMW) imaging is finding rapid adoption in security applications such as concealed object detection
under clothing. A passive MMW imaging system can operate as a stand-off type sensor that scans people in both indoors
and outdoors. However, the imaging system often suffers from the diffraction limit and the low signal level. This paper
discusses real-time concealed object recognition based on geometric descriptors. The concealed object region is
extracted by the multi-level segmentation method. A novel approach is proposed to measure similarity between a true
object model and segmented binary objects. Principal component analysis (PCA) regularizes the shape in terms of
translation and rotation. Size normalization provides scale-invariant property. A geometric feature vector is composed of
several shape descriptors. The feature vector is invariant to scale, rotation, and translation, and tolerant to distortion.
Classification is performed by means of measuring Euclidean distance between the mean feature vector of training
models and the feature vector of the segmented object. Experiments confirm that the proposed method provides fast and
reliable recognition of the concealed object carried by a moving human subject.

Concealed object recognition based on geometric feature descriptors

Millimeter wave (MMW) readily penetrates fabrics, thus it can be used to detect objects concealed under clothing. A passive MMW imaging system can operate as a stand-off type sensor that scans people in both indoors and outdoors. However, because of the diffraction limit and low signal level, the imaging system often suffers from low image quality. Therefore, suitable statistical analysis and computational processing would be required for automatic analysis of the images. In this paper, a real-time concealed object detection is addressed by means of the multi-level segmentation. The histogram of the image is modeled with a Gaussian mixture distribution, and hidden object areas are segmented by a multi-level scheme involving -means, the expectation-maximization algorithm, and a decision rule. The complete algorithm has been implemented in C++ environments on a standard computer for a real-time process. Experimental and simulation results confirm that the implemented system can achieve the real-time detection of concealed objects.

Mun-Kyo Lee

Papers

Real-time concealed-object detection and recognition with passive millimeter wave imaging

Real-time computational processing and implementation for concealed object detection

System design of focal plane array based Millimeter-wave Imaging radiometer for concealed weapon detection

Concealed object recognition based on geometric feature descriptors

Real-time passive millimeter wave image segmentation for concealed object detection