Registration of scenes for the detection of concealed weapons

A number of technologies are being developed for concealed weapon detection (CWD), and use of the appropriate processing techniques will be very important to the success of such technologies. In this paper, signal processing procedures used t enhance the detection of weapons concealed underneath clothing are described and illustrated.

Application of passive terahertz imaging in concealed weapon detection has been looked at, such that the final result is the segmentation of the foreground concealed weapons from the rest of the background. For the same, a fully automatic and completely generic technique, without any learning, has been proposed. It was observed that a simple thresholding step, exploiting varied intensity bands of the tetrahertz images is not enough. Thus, an innovative method to isolate humans and thus improve the region of interest (ROI) has been proposed. Thereafter, saliency has been used to further improve ROI, as these images are quite noisy and the central focusing aspect of saliency could handle the noise around the concealed weapons. It was observed that this step could handle the noise around the concealed weapons but degraded the boundaries of the concealed weapons. To further improve boundary adherence, superpixels are used. Finally, results are evaluated both quantitatively and qualitatively and outperformed the traditional approach.

Millimeter-wave holographic imaging techniques have recently been developed for personnel surveillance applications at airports and other high-security checkpoints. Millimeter- wave imaging is useful for this application since millimeter-waves easily pass through common clothing materials yet are reflected from the human body and any items concealed by clothing. This allows a high-resolution imaging system to form an image revealing items concealed on the person imaged. A prototype imaging system developed at Pacific Northwest National Laboratory uses a scanned linear array of millimeter-wave antennas to capture wideband millimeter-wave data in approximately one second. This data is then mathematically reconstructed to form a high- resolution 3D image of the person being scanned. Millimeter- wave imaging has been demonstrated to be effective for detecting concealed weapons on personnel. Another imaging technique which could be applied to the weapon detection problem is acoustic imaging. Like millimeter-waves, ultrasonic acoustic waves can also penetrate clothing, and can be used to form relatively high-resolution images which can reveal concealed weapons on personnel. Acoustic imaging results have been obtained using wideband holographic imaging techniques nearly identical to the imaging techniques used for millimeter-wave imaging. Preliminary imaging results at 50 kHz indicate that acoustic imaging can be used to penetrate some types of common clothing materials. Hard clothing materials, such as leather on vinyl, are essentially opaque to acoustic waves at 50 kHz. In this paper, millimeter-wave and acoustic wave imaging techniques are compared for their effectiveness and suitability in weapon detection imaging systems. Experimental results from both imaging modalities are shown.

A novel cylindrical millimeter-wave imaging technique has been developed at the Pacific Northwest National Laboratory for the detection of metallic and non-metallic concealed weapons. This technique uses a vertical array of millimeter- wave antennas which is mechanically swept around a person in a cylindrical fashion. The wideband millimeter-wave data is mathematically reconstructed into a series of high- resolution images of the person being screened. Clothing is relatively transparent to millimeter-wave illumination,whereas the human body and concealed items are reflective at millimeter wavelengths. Differences in shape and reflectivity are revealed in the images and allow a human operator to detect and identify concealed weapons. A full 360 degree scan is necessary to fully inspect a person for concealed items. The millimeter-wave images can be formed into a video animation sequence in which the person appears to rotate in front of a fixed illumination source.This is s convenient method for presenting the 3D image data for analysis. This work has been fully sponsored by the FAA. An engineering prototype based on the cylindrical imaging technique is presently under development. The FAA is currently opposed to presenting the image data directly to the operator due to personal privacy concerns. A computer automated system is desired to address this problem by eliminating operator viewing of the imagery.

Security has been a major concern in our societies due to the rise in crime rate, most especially in a crowded area. Concealed weapons have been posing a significant threat to government, law enforcement, security agencies, and civilians. Existing weapons detection systems seem to be not culpable of detecting concealed weapons without the cooperation of the person being searched. There remains a need for a weapons detector that can detect and identify concealed weapons for security enhancement in Nigeria. For this purpose, computer vision methods and a deep learning approach were applied for the identification of a weapon from captured images downloaded from the internet as a prototype for the study. Recent work in deep learning and machine learning using convolutional neural networks has shown considerable progress in the areas of object detection and recognition. The CNN algorithms are trained on the collected datasets to identify and differentiate between weapons and non-weapons. We built a concealed weapon detection system prototype and conducted a series of experiments to test the system's accuracy, precision, and false positives. The models were compared by evaluating their average values of sensitivity, specificity, F1 score, accuracy, and the area under the receiver operating characteristic curve (AUC). The experimental findings clearly demonstrated that the ResNet-50 model performed better than the VGG-16 and Alex Net models in terms of sensitivity, specificity, and accuracy.

A novel edge detector has been developed that utilises statistical masks and neural networks for the optimal detection of edges over a wide range of image types. The failure of many common edge detection techniques has been observed when analysing concealed weapons X-ray images, biomedical images or images with significant levels of noise, clutter or texture. This novel technique is based on a statistical edge detection filter that uses a range of two-sample statistical tests to evaluate any local image texture differences and by applying a pixel region mask (or kernel) to the image analyse the statistical properties of that region. The range and type of tests has been greatly expanded from the previous work of Bowring et al.¹ This process is further enhanced by applying combined multiple scale pixel masks and multiple statistical tests, to Artificial Neural Networks (ANN) trained to classify different edge types. Through the use of Artificial Neural Networks (ANN) we can combine the output results of several statistical mask scales into one detector. Furthermore we can allow the combination of several two sample statistical tests of varying properties (for example; mean based, variance based and distribution based). This combination of both scales and tests allows the optimal response from a variety of statistical masks. From this we can produce the optimum edge detection output for a wide variety of images, and the results of this are presented.

The goal of this research is to develop a process, using current imaging hardware and without human intervention, that provides an accurate and timely detection alert of a concealed weapon and its location in the image of the luggage. There are several processes in existence that are able to highlight or otherwise outline a concealed weapon in baggage but so far those processes still require a highly trained operator to observe the resulting image and draw the correct conclusions. We attempted three different approaches in this project. The first approach uses edge detection combined with pattern matching to determine the existence of a concealed pistol. Rather than use the whole body of the weapon which varies significantly, the trigger guard was used since it is fairly consistent in dimensions. While the processes were reliable in detecting a pistol's presence, on any but the simplest of images, the computational time was excessive and a substantial number of false positives were generated. The second approach employed Daubechie wavelet transforms but the results have so far been inconclusive. A third approach involving an algorithm based on the scale invariant feature transform (SIFT) is proposed.

Wavelet transform based techniques were developed and investigated for isolation and enhancement of objects in images. The primary motivation is the development of image processing algorithms as part of an automatic system for the detection of concealed weapons under a person's clothing; a problem of considerable potential utility to the military in certain common types of deployment in the post cold war environment such as small unit operations. The issue has potential for other dual use purposes such as law enforcement applications. Wavelet decompositions of the currently available images in the Rome Laboratory database, namely, noisy, low contrast, infrared images, were studied in space-scale-amplitude space. An isolation technique for separating potential suspicious regions/objects from surrounding clutter has been proposed. Based on the images available, the study indicates that the technique is promising in providing the image enhancement necessary for further pattern detection and classification.

In light of increasing interest in detection of concealed metallic weapons, there is a great need to have robust and non-obtrusive metal detection systems with large coverage areas. Conventional systems based on electromagnetic induction or X- rays are effective, but have small coverage areas in addition to requiring costly infrastructure. In this paper, we explore the use of ubiquitously present WiFi signals for non-obtrusive detection of concealed metal objects. For the purpose, we build a prototype system consisting of a single- antenna commodity WiFi radio as a transmitter, and two multi-antenna radios as receivers placed in an indoor environment of approximately 42 ft by 39 ft. We conduct extensive experiments with subjects walking through the setup with (or without) a sheet of metal placed around their chests. We use the channel state-information collected from the receivers to train a deep convolutional neural network, and find that the proposed system can differentiate between the metal and non-metal cases with an average accuracy of 86.44.

In this day and age, increasingly easy access to firearms and other hand-held weapons has stirred up public violence concerns. Many of these weapons are comfortably concealed. The tremendous developments in technology can assure more security in public places by detecting such weapons in real-time and alerting the concerned authorities before any damage. In this paper, we propose using two state-of-the-art algorithms for performing real-time detection of concealed hand-held weapons. The algorithms used are Multi Contrast Convolutional Neural Networks (MC-CNN) and Faster Region-Based Convolutional Neural Networks (Faster R-CNN). Additionally, we present a comprehensive comparative analysis and evaluation of the Faster R-CNN and MC-CNN in detecting the weapons. This study has diverse industrial applications in real-time bank surveillance cameras and other public places, provided that they are under CCTV surveillance.

Summary form only given. Multisensor information fusion is one of the key technologies required to make significant advances in information processing and utilization in a distributed information environment. The data fusion process model proposed by the US Joint Directors of Laboratories (JDL) is accepted widely for military applications. There have been other models such as a three level model proposed by the Defense Evaluation and Research Agency (DERA) of the United Kingdom. There is an ongoing research and development program in the area of concealed weapons detection sponsored by Air Force Research Laboratory (AFRL) and National Institute of Justice (NIJ). The main objectives of this program are twofold: development of efficient sensors and signal processing technologies for the detection of civilian applications. Data collected by different sensors needs to be combined intelligently to enhance detection performance for concealed weapons. Toward this goal we have developed several novel image/signal processing algorithms. These include algorithms for image registration, image enhancement, image fusion, denoising, and object extraction. While great strides in the CWD program have been made, its relationship with the data fusion process models has not been investigated. The goal of this presentation is to examine this relationship.

Recent advances in millimeter-wave (MMW), microwave, and infrared (IR) technologies provide the means to detect concealed weapons remotely through clothing and in some cases through walls. Since the development of forward-looking infrared (FLIR) instruments, work has been ongoing in attempting to use these devices for concealed weapon detection based on temperature differences between metallic weapons and the background body temperature of the person carrying the weapon; however, the poor transmission properties of clothing in the infrared has led to the development of techniques based on lower frequencies. Focal plane arrays operating at MMW frequencies are becoming available which eliminate the need for a costly and slow mechanical scanner for generating images. These radiometric sensors also detect temperature differences between weapons and the human body background. Holographic imaging systems operating at both microwave and MMW frequencies have been developed which generate images of near photographic quality through clothing and through thin, non-metallic walls. Finally, a real-aperture radar is useful for observing people and detecting weapons through walls and in the field under reduced visibility conditions.

In recent years there has been a need to improvise the security of the general public as well as the safety of public assets like airports and buildings for which, the biggest hurdle is detection of weapons concealed underneath a person's clothing. It is desirable sometimes to be able to detect concealed weapons from a standoff distance, especially when it is impossible to arrange the flow of people through a controlled procedure. Therefore, we propose a novel algorithm to generate one multi exposed - multi modal image from a set of visual images with multiple exposures and a set of infrared images with multiple exposures. The method employs homomorphic filter, entropy of blocks and blending approach for image fusion. Experiments were performed on different sets of multi exposed images by varying the block size and the blending parameter which shows that the proposed method outperforms the results obtained without homomorphic filter.

THz imaging, also known as terahertz imaging, is a relatively new technology that utilizes the terahertz frequency range of the electromagnetic spectrum to generate images of various materials and biological samples. This technology has promising applications in a wide range of biomedical fields, including cancer detection, imaging of biological tissues, and drug development. THz imaging has also applications in security sector, including explosives detection and as well as detection of concealed weapons. THz TPI imaging technique is relatively new but it has great applications in dentistry. The THz imaging has great potential in revealing cancerous tissue. Several studies have already been done by various scientists using THz imaging in the healthcare sector, specially detecting different types of cancers. THz imaging has some added advantages in comparison to the other types of imaging techniques availlable to the healthcare industry. Overall, this review article aims to provide an overview of the biomedical applications of THz imaging and its potential applications for future advancements in the field of medical sciences.

This paper discusses the current state-of-the-art in millimeter-wave radiometric imagers being developed for law enforcement use within the United States. The most prevalent application at present is the detection of concealed weapons (guns, knives, etc.) with a secondary application involving the detection of drugs and explosives. Three main topics will be addressed: the phenomenology of concealed weapon detection at millimeter wavelengths, the promise and short comings of first generation radiometric imagers, and the characteristics of second generation systems currently under development.