Concealed Weapon Detection
- 1. A Seminar Report On CONCEALED WEAPON DETECTION USING DIGITAL IMAGE PROCESSING Subject: Seminar-2 Paper Code: ECE 892 University Institute of Technology The University of Burdwan By Srijan Kumar Jha Roll no.-2016-2002 Regn. No.-A5032 of 16-17 DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING UNIVERSITY INSTITUTE OF TECHNOLOGY THE UNIVERSITY OF BURDWAN GOLAPBAGH(NORTH),BURDWAN-713104,WB
- 2. CONTENT: 1. Abstract 2. Introduction 3. Image Processing 4. How it is done? 5. Imaging Sensors 6. Infrared Imagers 7. PMW Imaging Sensor 8. CWD Through Image Fusion 9. Imaging Processing Architecture 10. Purposed Method 11. Algorithm 12. Step By Step Concealed Weapon Detection 13. Advantage & Drawbacks 14. Conclusion
- 3. ABSTRACT: In the present scenario, bomb blasts are rampant all around the world. Bombs went off in buses and underground stations, killed many and left many injured. Bomb blasts cannot be predicted beforehand. This report is all about the technology which predicts the suicide bombers and explosion of weapons through IMAGING FOR CONCLEAD WEAPON DETECTION, the sensor improvements, how the imaging takes place and the challenges. And we also describe techniques for simultaneous noise suppression, object enhancement of video data and show some mathematical results. The detection of weapons concealed underneath a person’s clothing is very much important to the improvement of the security of the general public as well as the safety of public assets like airports, buildings, and railway stations etc. Manual screening procedures for detecting concealed weapons such as handguns, knives, and explosives are common in controlled access settings like airports, entrances to sensitive buildings and public events. 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.
- 4. INTRODUCTION: Till now the detection of concealed weapons is done by manual screening procedures. To control the explosives in some places like airports, sensitive buildings, famous constructions etc. But these manual screening procedures are not giving satisfactory results, because this type of manual screenings procedures screens the person when the person is near the screening machine and also sometimes it gives wrong alarm indications so we are need of a technology that almost detects the weapon by scanning. This can be achieved by imaging for concealed weapons. The goal is the eventual deployment of automatic detection and recognition of concealed weapons. it is a technological challenge that requires innovative solutions in sensor technologies and image processing. The problem also presents challenges in the legal arena; a number of sensors based on different phenomenology as well as image processing support are being developed to observe objects underneath people’s clothing.
- 5. IMAGE PROCESSING: The term digital image processing refers to scientific and technical pursuits. Processing of an image includes improvement in its appearance and efficient representation. Image processing is widely being used today. Interest in digital image processing stems from two principle applications areas: improvement of pictorial information for human interpretation, and processing of scenes data for autonomous machine perception. HOW IT IS DONE? This involves converting the visual informa-tion into discrete form suitable for computer processing. Computer processes discrete information of an image using various mathematical tools MORPHOLOGY is one of them, which offers a broad set of image processing operations that process images based on shapes. Morphological operations apply a structuring element to an input image, creating an output image of the same size. Manual screenings procedures screens the person when the person is near the screening machine and also some-times it gives wrong alarm indications so we are need of a technology that almost detects the weapon by scanning which achieved by imaging for concealed weapons. IMAGING SENSORS: These imaging sensors developed for CWD applications depending on their portability, proximity and whether they use active or passive illuminations. The different types of imaging sensors for CWD based areas be 1.)INFRARED IMAGERS: Infrared imagers utilize the temperature distribution information of the target to form an image. Normally they are used for a variety of night-vision applications, such as viewing vehicles and people. The underlying theory is that the infrared radiation emitted by the human body is absorbed by clothing and then re-emitted by it. As a result, infrared radiation can be used to show the image of a concealed weapon only
- 6. when the clothing is tight, thin, and stationary. For normally loose clothing, the emitted infrared radiation will be spread over a larger clothing area, thus decreasing the ability to image a weapon. 2.) PMW IMAGING SENSORS: FIRST GENERATION: Passive Millimeter Wave (PMW) sensors measure the apparent temperature through the energy that is emitted or reflected by sources. The output of the sensors is a function of the emissive of the objects in the MMW spectrum as measured by the receiver. Clothing penetration for concealed weapon detection is made possible by MMW sensors due to the low emissive and high reflectivity of objects like metallic guns. . SECOND GENERATION: Recent advances in MMW sensor technology have led to video-rate (30 frames/s) MMW cameras. One such camera is the pupil-plane array from Terex Enterprises. It is a 94-GHz radiometric pupil-plane imaging system that employs frequency scanning to achieve vertical resolution and uses an array of 32 individual wave-guide antennas for horizontal resolution. This system collects up to 30frames/s of MMW data. Following figure shows the visible and second-generation MMW images of an individual hiding a gun underneath his jacket. CWD THROUGH IMAGE FUSION: By fusing passive MMW image data and its corresponding infrared (IR) or electro-optical (EO) image, more complete information can be obtained. The information can then be utilized to facilitate concealed weapon detection. Fusion of an IR image revealing a concealed weapon and its corresponding MMW image has been shown to facilitate extraction of the concealed weapon. This is illustrated in the example given in following figure Shows an image taken from a regular CCD camera, and Figure shows a corresponding MMW image. If either one of these two images alone is presented to a human operator, it is difficult to recognize the weapon concealed underneath the rightmost person’s clothing. If a fused image as shown in Figure is presented, a human operator is able to respond with higher accuracy. This demonstrates the benefits of image fusion for the CWD application, which integrates complementary information from multiple types of sensors.
- 7. IMAGING PROCESSING ARCHITECTURE: Input Output Output to a Human Operator PREPROCESSING Automatic Weapon Detection Enhancement And/or Denoising Registration and Fusion Feature Extraction/ Description Weapon Recognition . . . . .
- 8. 1.)IMAGE DENOISING & ENHANCEMENT THROUGH WAVELETS: We describe a technique for simultaneous noise suppression and object enhancement of passive MMW video data. De-noising of the video sequences can be achieved temporally or spatially. First temporal de-noising is achieved by motion compensated filtering, which estimates the motion trajectory of each pixel by various algorithms and then conducts a 1-D filtering along the trajectory. This reduces the blurring effect that occurs when temporal filtering is performed without regard to object motion between frames 2.) REGISTRATION OF MULTI SENSOR IMAGES: Use of multiple sensors may increase the efficacy of a CWD system. The first step toward image fusion is a precise alignment of images (i.e., image registration).In registration approach images taken at the same time from different but nearly collocated (adjacent parallel) sensors based on the maximization of mutual information (MMI) criterion. MMI states that two images are registered when their mutual information (MI) reaches its maximum value. For the registration of IR images and the corresponding MMW images of the first generation. At the first stage, two human silhouette extraction algorithms were developed, followed by a binary correlation to coarsely register the two images. This provides an initial search point close to the final solution for the second stage of the registration algorithm based on the MMI criterion. In this manner, any local optimizer can be employed to maximize the MI measure 3.) IMAGE DECOMPOSITION: First, an image pyramid is constructed for each source image by applying the wavelet transform to the source images. This transform domain representation emphasizes important details of the source images at different scales, which is useful for choosing the best fusion rules. Then, using a feature Selection rule, a fused pyramid is formed for the composite image from the pyramid coefficients of
- 9. the source images. The simplest feature selection rule is choosing the maximum of the two corresponding transform values. This allows the integration of details into one image from two or more images. Finally, the composite image is obtained by taking an inverse pyramid transform of the composite wavelet representation. The process can be applied to fusion of multiple source imagery. This type of method has been used to fuse IR and MMW images for CWD application. 4.)AUTOMATIC WEAPON DETECTION: After preprocessing, the images /video sequences can be displayed for operator- assisted weapon detection or fed into a weapon detection module for automated weapon detection. Toward this aim, several steps are required, including object extraction, shape description, and weapon recognition. 5.)SEGMENTATION FOR OBJECT EXTRACTION: Object extraction is an important step towards automatic recognition of a weapon, regardless of whether or not the image fusion step is involved. It has been successfully used to extract the gun shape from the fused IR and MMW images. This could not be achieved using the original images alone. Segmented result from the fused IR and MMW image is shown in Figure 6.
- 10. Proposed Method: In the proposed technique for CWD we consider two types of image – a visual image and an IR image. Visual image is nothing but an RGB image which has three main colour components Red, Green and Blue. Since the human visual system is very sensitive to colours this image creates a natural perception of an object to human vision but not helps so much in the detection of concealed weapon. For this we consider IR image as second input. It basically depends on high thermal emissivity of the body. Basically the infrared radiation emitted by the body is absorbed by clothing and then reemitted by it, is sensed by the infrared sensors. Due to difference in thermal emissivity we can realize the hidden object but since the background is almost black this image cannot help in CWD alone. Resize two input images: Since these two input images are taken from two different image sensing devices so they are of different size. So we first resize these two types of images because the image fusion and other operations are not possible if the sizes are not same. Combine two images: Perform the addition operation between visual and IR (visual + IR) images to get the IvIR image. But the resultant image does not give enough information. Then we complement the IR image (IIRc) to remove the background darkness. IR image lies the intensity between 0 to 255 intensity thus complement means subtracting all matrix component from 255 and we get complemented form or reverse form of the IR image. Then add visual image and complemented IR image (visual + complemented IR) and get a resultant image which is denoted by IvIRc. Conversion of IR to HSV: Then we convert IR image into HSV colour model (IIR_HSV) because components of IR image are all correlated with the amount of light hitting the object, and therefore with each other, image descriptions in terms of those components make object discrimination difficult. Descriptions in terms of hue/lightness/saturation are often more relevant. Fused two images: After converting HSV model the image is now three components. Now we can use fusion technique because two images have the same dimension with same size and we use DWT fusion technique between HSV colour image (IIR_HSV) and combined image IvIRc. Processing for showing the weapon clearly in the visual image: Then this fused image converted into gray scale image. Now we use Otsu’s local thresholding technique for binarizing fused gray scale image. Then Extract the weapon portion by calculating all connected area component and remove too small component and also too large component according to the area values. To show the weapon in the actual RGB visual image we multiply the weapon’s binary images with three dimensional RGB image. Basically the element wise multiplication is performed between two matrices.
- 11. Now contour detection is used to detect edges of weapon from the weapon binary image and we use canny edge detector for detecting the edges. Then this binarizes contour image is divided into three components and multiply as before and we get contour with visual RGB image where we can detect the concealed weapon under the person’s clothes very clearly. Here below is the flow diagram of our proposed method is shown. ALGORITHM: Step 1: Take a visual image (basically, RGB image) and an infrared (IR) image as input. Step 2: Resize this two image so that they have same size. Step 3: Combine i.e. add resized Visual and IR image. Step 4: Complement the IR image. Step 5: Combine i.e. add resized Visual image and complemented IR image. Step 6: Convert the visual RGB image to its HSV format. Step 7: Perform DWT fusion on Step 5’s combined image and Step 6’s converted HSV image. Step 8: Convert the fused image into its gray scale format. Step 9: Binarize the Fused image. Step 10: Detect the weapon from that image. Step 11: Combine this detected weapon with visual image. Step 12: For detecting the weapon clearly we find out the contour of the weapon. Step 13: Then combine the contour of the weapon with visual image. Step 14: End
- 12. STEP BY STEP CONCEALED WEAPON DETECTION: Figure 1: RGB image Figure 2 : IR image Figure 3 : Gray image Figure 4: Combined image Figure 5: Complemented IR image Figure 6: Combined1 image
- 13. Figure 7: HSV image Figure 8: Fused image Figure 9: Fused gray image Fig 10: Weapon in binary image Fig 11: Weapon in visual image Fig 12 : Contour of the Weapon image
- 14. Figure 13: Contour with Visual Image ADVANTAGES: It will help the low enforcement to be able to detect and respond to weapons at a sufficient distance to allow officers to make decisions and take actions that deal safely with the situation. CHALLENGES: There are several challenges ahead. One critical issue is the challenge of performing detection at a distance with high probability of detection and low probability of false alarm. Yet another difficulty to be surmounted is forging portable multi-sensor instruments. Also, detection systems go hand in hand with subsequent response by the operator, and system development should take into account the overall context of deployment.
- 15. CONCLUSION: Imaging techniques based on a combination of sensor technologies and processing will potentially play a key role in addressing the concealed weapon detection problem. Recent advances in MMW sensor technology have led to video-rate (30 frames/s) MMW cameras. However, MMW cameras alone cannot provide useful information about the detail and location of the individual being monitored. To enhance the practical values of passive MMW cameras, sensor fusion approaches using MMW and IR, or MMW and EO cameras are being described. By integrating the complementary information from different sensors, a more effective CWD system is expected.
- 16. REFERENCES & BIBLIOGRAPHY: N.G.Paulter, “Guide to the technologies of concealed weapon imaging and detection,” NIJ Guide 602-00,2001 An Article from “IEEE SIGNAL PROCESSING MAGAZINE” March 2005 pp. 52-61 R. C. Gonzalez, R. E. Woods, “Digital Image Processing", Second Edition, Prentice Hall, New Jersey 2002.