There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

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

Millimeter wave imaging is finding rapid adoption in security applications such as the detection of objects concealed under clothing. A passive imaging system can be realized as a stand-off type sensor that can operate in open spaces, both indoors and outdoors. In this paper, we address real-time outdoor concealed-object detection and segmentation with a radiometric imaging system operating in the W-band. The imaging system is equipped with a dielectric lens and a receiver array operating at around 94 GHz. Images are analyzed by multilevel segmentation to identify a concealed object. Each level of segmentation comprises vector quantization, expectation-maximization, and Bayesian decision making to cluster pixels on the basis of a Gaussian mixture model. In addition, we describe a faster process that adopts only vector quantization for the first level segmentation. Experiments confirm that the proposed methods provide fast and reliable detection and segmentation for a moving human subject carrying a concealed gun.

Real-time outdoor concealed-object detection with passive millimeter wave imaging

Millimeter-wave (MMW) imaging is a powerful tool for the detection of objects concealed under clothing. Several factors including difierent kinds of objects, variety of covering materials and their thickness, accurate imaging of near-fleld scattered data afiect the success of detection. To practice with such considerations, this paper presents the two-dimensional (2D) images of difierent targets hidden under various fabric sheets. The W-band inverse synthetic aperture radar (ISAR) data of various target-covering situations are acquired and imaged by applying both the focusing operator based inversion algorithm and the spherical back-projection algorithm. Results of these algorithms are demonstrated and compared to each other to assess the performance of the MMW imaging in detecting the concealed objects of both metallic and dielectric types.

/pdf/a-study-on-millimeter-wave-imaging-of-concealed-objects-105f2ykgit.pdf

A study on millimeter-wave imaging of concealed objects: application using back-projection algorithm

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

We address an image segmentation method to detect concealed objects captured by passive millimeter wave (MMW) imaging. Passive MMW imaging can create interpretable imagery on the objects concealed under clothing, which gives the great advantage to the security system. In this paper, we propose the multi-level expectation maximization (EM) method to separate the concealed objects from the other area in the image. We apply the EM method to obtain a Gaussian mixture model (GMM) of the acquired image. In the experiments, we evaluate the performance by the average probability of error. We will show that the consecutive EM processes separates the object area more accurately than the conventional EM method.

Automatic image segmentation for concealed object detection using the expectation-maximization algorithm

Millimeter waves can be used to detect concealed objects because they can penetrate clothing. Therefore, millimeter wave imaging draws increasing attention in security applications for the detection of objects under clothing. In such applications, it is critical to estimate the distances from objects concealed in open spaces. In this paper, we develop a segmentation-based stereo-matching method based on passive millimeter wave imaging to estimate the longitudinal distance from a concealed object. In this method, the concealed object area is segmented and extracted by a k-means algorithm with splitting initialization, which provides an iterative solution for unsupervised learning. The distance from a concealed object is estimated on the basis of discrepancy between corresponding centers of the segmented objects in the image pair. The conventional stereo-matching equation is modifled according to the scanning properties of the passive millimeter wave imaging system. We experimentally demonstrate that the proposed method can accurately estimate distances from concealed objects.

/pdf/distance-estimation-of-concealed-objects-with-stereoscopic-1eqorbi956.pdf

Distance estimation of concealed objects with stereoscopic passive millimeter-wave imaging

This paper addresses concealed object detection by passive millimeter wave (MMW) imaging. Passive MMW imaging penetrates into clothing to capture metal and man-made objects. In this paper, we propose a multi-level expectation maximization (EM) method to separate the concealed object from the body area. The performance is evaluated by the average probability of error. We will show that the proposed EM processes segments the object area more accurately than the conventional EM method.

Dong-Su Lee

Papers

Real-time outdoor concealed-object detection with passive millimeter wave imaging

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

Automatic image segmentation for concealed object detection using the expectation-maximization algorithm

Distance estimation of concealed objects with stereoscopic passive millimeter-wave imaging

Concealed object detection using passive millimeter wave imaging