Showing papers by "Mongi A. Abidi published in 2006"

Gray-level grouping (GLG): an automatic method for optimized image contrast Enhancement-part I: the basic method

Abstract: This is Part II of the paper, "Gray-Level Grouping (GLG): an Automatic Method for Optimized Image Contrast Enhancement". Part I of this paper introduced a new automatic contrast enhancement technique: gray-level grouping (GLG). GLG is a general and powerful technique, which can be conveniently applied to a broad variety of low-contrast images and outperforms conventional contrast enhancement techniques. However, the basic GLG method still has limitations and cannot enhance certain classes of low-contrast images well, e.g., images with a noisy background. The basic GLG also cannot fulfill certain special application purposes, e.g., enhancing only part of an image which corresponds to a certain segment of the image histogram. In order to break through these limitations, this paper introduces an extension of the basic GLG algorithm, selective gray-level grouping (SGLG), which groups the histogram components in different segments of the grayscale using different criteria and, hence, is able to enhance different parts of the histogram to various extents. This paper also introduces two new preprocessing methods to eliminate background noise in noisy low-contrast images so that such images can be properly enhanced by the (S)GLG technique. The extension of (S)GLG to color images is also discussed in this paper. SGLG and its variations extend the capability of the basic GLG to a larger variety of low-contrast images, and can fulfill special application requirements. SGLG and its variations not only produce results superior to conventional contrast enhancement techniques, but are also fully automatic under most circumstances, and are applicable to a broad variety of images.

An Overview of Color Constancy Algorithms

Abstract: Color constancy is one of the important research areas with a wide range of applications in the elds of color image processing and computer vision. One such application is video tracking. Color is used as one of the salient features and its robustness to illumination variation is essential to the adaptability of video tracking algorithms. Color constancy can be applied to discount the inuence of changing illuminations. In this paper, we present a review of established color constancy approaches. We also investigate whether these approaches in their present form of implementation can be applied to the video tracking problem. The approaches are grouped into two categories, namely, Pre-Calibrated and Data-driven approaches. The paper also talks about the ill-posedness of the color constancy problem, implementation assumptions of color constancy approaches, and problem statement for tracking. Publications on video tracking algorithms involving color correction or color compensation techniques are not included in this review.

Image Fusion and Enhancement via Empirical Mode Decomposition

Abstract: In this paper, we describe a novel technique for image fusion and enhancement, using Empirical Mode Decomposition (EMD). EMD is a non-parametric data-driven analysis tool that decomposes non-linear non-stationary signals into Intrinsic Mode Functions (IMFs). In this method, we decompose images, rather than signals, from different imaging modalities into their IMFs. Fusion is performed at the decomposition level and the fused IMFs are reconstructed to realize the fused image. We have devised weighting schemes which emphasize features from both modalities by decreasing the mutual information between IMFs, thereby increasing the information and visual content of the fused image. We demonstrate how the proposed method improves the interpretive information of the input images, by comparing it with widely used fusion schemes. Apart from comparing our method with some advanced techniques, we have also evaluated our method against pixelby-pixel averaging, a comparison, which incidentally, is not common in the literature.

Evaluation of sharpness measures and search algorithms for the auto focusing of high-magnification images

Abstract: Digital imaging systems with extreme zoom capabilities are traditionally found in astronomy and wild life monitoring. More recently, the need for such capabilities has extended to long range surveillance and wide area monitoring such as forest fires, airport perimeters, harbors, and waterways. Auto-focusing is an indispensable function for imaging systems designed for such applications. This paper studies the feasibility of an image based passive auto-focusing control for high magnification systems based on off-the-shelf telescopes and digital cameras/camcorders, with concentration on two associated elements: the cost function (usually the image sharpness measure) and the search strategy. An extensive review of existing sharpness measures and search algorithms is conducted and their performances compared. In addition, their applicability and adaptability to a wide range of high magnifications (50×~1500×) are addressed. This study builds up the foundation for the development of auto-focusing schemes with particular applications to high magnification systems.

Improving Weapon Detection in Single Energy X-Ray Images Through Pseudocoloring

Abstract: This paper describes a series of linear and nonlinear pseudocoloring maps designed and applied to single energy X-ray luggage scans to assist airport screeners in identifying and detecting threat items, particularly hard to see low-density weapons in luggage. Considerations of the psychological and physiological processing involved in the human perception of color as well as the effects of using various color models, such as the RGB and HSI models, were explored. Original grayscale data, various enhanced images, and segmented scenes were used as input to the various color mapping schemes designed in this research. A highly interactive user-friendly graphical interface and a portable test were developed and used in a performance evaluation study involving a population of actual federal airport screeners. The study proved the advantages of using color over gray level data and also allowed the ranking of color maps and selection of the best performing color schemes. Rate improvements in weapon detection of up to 97% were achieved through the use of color

Fusion of Visible and Infrared Images using Empirical Mode Decomposition to Improve Face Recognition

Abstract: In this effort, we propose a new image fusion technique, utilizing empirical mode decomposition (EMD), for improved face recognition. EMD is a non-parametric data-driven analysis tool that decomposes non-linear non-stationary signals into intrinsic mode functions (IMFs). In this method, we decompose images from different imaging modalities into their IMFs. Fusion is performed at the decomposition level and the fused IMFs are reconstructed to form the fused image. The effect of fusion on face recognition is measured by obtaining the cumulative match characteristics (CMCs) between galleries and probes. Apart from conducting face recognition tests on visible and infrared raw datasets, we use datasets fused by averaging, principal component (PCA) fusion, wavelet based fusion and our method, for comparison. The face recognition rate due to EMD fused images is higher than the face recognition rates due to raw visible, raw infrared and other fused images. Examples of the fused images and illustrative CMC comparison charts are shown.

An Indoor and Outdoor, Multimodal, Multispectral and Multi-Illuminant Database for Face Recognition

Abstract: In this effort, we describe a face database obtained by using an involved acquisition system for the collection of multimodal and multispectral image data under various illumination conditions. The database of facial images may aid in exploring new avenues in face recognition, especially when involving multi-band visible and thermal information. The database has applications in experimentation with human identification, authentication, and face modeling. We describe the abilities of the acquisition system wherein the imaging sensors, system considerations and registration are discussed. For each data record in the database, we have twenty five images spanning the visible spectrum, one visible RGB/monochromatic image, one thermal image and the spectral distribution of the illumination of the scene. The complete dataset has so far 2624 face images and the corresponding illumination information for each data record. Moreover, we present a multispectral data fusion approach for illumination adjustment. The database will be made public to the research community for perusal towards illumination invariant face related research.

Method of enhancing a digital image by gray-level grouping

Abstract: Methods for enhancing the quality of an electronic image, including automated methods for contrast enhancement and image noise reduction. In many embodiments the method provides for grouping the histogram components of a low-contrast image into the proper number of bins according to a criterion, then redistributing these bins uniformly over the grayscale, and finally ungrouping the previously grouped gray-levels. The technique is named gray-level grouping (GLG). An extension of GLG called Selective Gray-Level Grouping (SGLG), and various variations thereof are also provided. SGLG selectively groups and ungroups histogram components to achieve specific application purposes, such as eliminating background noise, enhancing a specific segment of the histogram, and so on. GLG techniques may be applied to both monochromatic grayscale images and to color images. Several preprocessing or postprocessing methods for image noise reduction are provided for use independently or for use with GLG techniques to both reduce or eliminate background noise and enhance the image contrast in noisy low-contrast images.

Digital Imaging with Extreme Zoom: System Design and Image Restoration

Abstract: Applications of digital imaging with extreme zoom are traditionally found in astronomy and wild life monitoring. More recently, the need for such capabilities has extended to wide area monitoring such as forest fires, harbors, and waterways. This paper presents a number of sensor arrangements for the acquisition of high magnification images. It also describes user interfaces developed for the system’s remote control and data acquisition and processing. Hardware and software considerations are addressed, focusing on optical setups and image de-blurring techniques. An image restoration algorithm tailored to such systems is developed, where an adaptive sharpness measure is employed as a cost function to guide the search for an optimal point spread function (PSF) for image de-blur. Experimental results demonstrate a considerably enhanced robustness to noise and ability to select the optimum PSF, producing much superior restored images.

A Moving Object Tracked by A Mobile Robot with Real-Time Obstacles Avoidance Capacity

Abstract: This paper describes a robotic application that tracks a moving object by utilizing a mobile robot with multiple sensors. The robotic platform uses a visual camera to sense the movement of the desired object and a range sensor to help the robot detect and then avoid obstacles in real time while continuing to track and follow the desired object. In terms of real-time obstacle avoidance capacity, this paper also presents a modified potential field algorithm called Dynamic Goal Potential Field algorithm (DGPF) for this robotic application specifically. Experimental results show that the robotic and intelligent system can fulfill the requirements of tracking an object and avoiding obstacles simultaneously when the object is moving.

Fusion of Omnidirectional and PTZ Cameras for Accurate Cooperative Tracking

Abstract: Dual camera systems (omnidirectional and slaved PTZ cameras) are widely used in public area monitoring and target tracking. However, due to their low and non-uniform resolution, omnidirectional cameras are only able to provide moderate accuracy in both motion/target detection and tracking. To overcome this disadvantage, two methods are proposed: geometry mapping based on a polynomial imaging model and closed loop cooperative tracking. Using a unified polynomial approximation [1], the geometry relationship between the omnidirectional and PTZ cameras can be formulated in a general solution from camera calibration with a fully automated model selection. Distributed Kalman filters are developed to exchange estimated trajectories among cameras forming closed loop sub-systems for individual cameras. The effectiveness of the proposed algorithms is illustrated via experiments and comparisons with existing systems.

Physics-based Fusion of Multispectral Data for Improved Face Recognition

Abstract: A novel physics-based fusion of multispectral images within the visual spectra is proposed for the purpose of improving face recognition under constant or varying illumination. Spectral images are fused according to the physics properties of the imaging system, including illumination, spectral response of the camera, and spectral reflectance of skin. The fused image is given as a probe to the recognition software Facelttrade which compares it to a gallery of images. The identification performance of our physics-based fusion method is compared to the performance of principle component analysis and average fusion methods. The results show that the proposed fusion yields a higher identification rate. A method of illumination adjustment is proposed when the probe and gallery images are acquired under different illumination conditions. The results show that the identification rate is higher than that of unadjusted gray-level images

Shape Measure for Identifying Perceptually Informative Parts of 3D Objects

Abstract: We propose a mathematical approach for quantifying shape complexity of 3D surfaces based on perceptual principles of visual saliency. Our curvature variation measure (CVM), as a 3D feature, combines surface curvature and information theory by leveraging bandwidth-optimized kernel density estimators. Using a part decomposition algorithm for digitized 3D objects, represented as triangle meshes, we apply our shape measure to transform the low level mesh representation into a perceptually informative form. Further, we analyze the effects of noise, sensitivity to digitization, occlusions, and descriptiveness to demonstrate our shape measure on laser-scanned real world 3D objects.

Estimating Illumination Chromaticity via Kernel Regression

Abstract: We propose a simple nonparametric linear regression tool, known as kernel regression (KR), to estimate the illumination chromaticity. We design a Gaussian kernel whose bandwidth is selected empirically. Previously, nonlinear techniques like neural networks (NN) and support vector machines (SVM) are applied to estimate the illumination chromaticity. However, neither of the techniques was compared with linear regression tools. We show that the proposed method performs better chromaticity estimation compared to NN, SVM, and linear ridge regression (RR) approach on the same data set.

Multi-sensor integration for unmanned terrain modeling

Abstract: State-of-the-art unmanned ground vehicles are capable of understanding and adapting to arbitrary road terrain for navigation. The robotic mobility platforms mounted with sensors detect and report security concerns for subsequent action. Often, the information based on the localization of the unmanned vehicle is not sufficient for deploying army resources. In such a scenario, a three dimensional (3D) map of the area that the ground vehicle has surveyed in its trajectory would provide apriori spatial knowledge for directing resources in an efficient manner. To that end, we propose a mobile, modular imaging system that incorporates multi-modal sensors for mapping unstructured arbitrary terrain. Our proposed system leverages 3D laser-range sensors, video cameras, global positioning systems (GPS) and inertial measurement units (IMU) towards the generation of photo-realistic, geometrically accurate, geo-referenced 3D terrain models. Based on the summary of the state-of-the-art systems, we address the need and hence several challenges in the real-time deployment, integration and visualization of data from multiple sensors. We document design issues concerning each of these sensors and present a simple temporal alignment method to integrate multi-sensor data into textured 3D models. These 3D models, in addition to serving as apriori for path planning, can also be used in simulators that study vehicle-terrain interaction. Furthermore, we show our 3D models possessing the required accuracy even for crack detection towards road surface inspection in airfields and highways.

Ridge-valley path planning for 3D terrains

Abstract: This paper presents a tactical path planning algorithm for following ridges or valleys across a 3D terrain. The intent is to generate a path that enables an unmanned vehicle to surveil with maximum observability by traversing the ridges of a terrain or to operate with maximum covertness by navigating the valleys. The input to the algorithm is a 3D triangle mesh model for the terrain of interest. This mesh may be non-uniform and non-regular. Thus, the algorithm leverages research from computer graphics and computer vision to identify ridge-valley features on the terrain. These features serve as "obstacles" for an artificial potential field algorithm. The valleys are obstacles for a surveillance path, or the ridges are obstacles for a covert path. We incorporate geodesic-rather than Euclidean-distances into the potential field formulation to extend path planning to 3D surfaces. We present the theory of our proposed algorithm and provide experimental results

Robotic three-dimensional imaging system for under-vehicle inspection

Abstract: We present our research efforts toward the deployment of 3-D sensing technology to an under-vehicle inspection robot. The 3-D sensing modality provides flexibility with ambient lighting and illumination in addition to the ease of visualization, mobility, and in- creased confidence toward inspection. We leverage laser-based range-imaging techniques to reconstruct the scene of interest and address various design challenges in the scene modeling pipeline. On these 3-D mesh models, we propose a curvature-based surface feature toward the interpretation of the reconstructed 3-D geometry. The curvature variation measure (CVM) that we define as the en- tropic measure of curvature quantifies surface complexity indicative of the information present in the surface. We are able to segment the digitized mesh models into smooth patches and represent the automotive scene as a graph network of patches. The CVM at the nodes of the graph describes the surface patch. We demonstrate the descriptiveness of the CVM on manufacturer CAD and laser-

High Magnification and Long Distance Face Recognition: Database Acquisition, Evaluation, and Enhancement

Abstract: In this paper, we describe a face video database obtained from Long Distances and with High Magnifications, IRIS- LDHM Both indoor and outdoor sequences are collected under uncontrolled surveillance conditions The significance of this database lies in the fact that it is the first database to provide face images from long distances (indoor: 10 m~20 m and outdoor: 50 m~300 m) The corresponding system magnification is elevated from less than 3times to 20times for indoor and up to 375times for outdoor The database has applications in experimentations with human identification and authentication in long range surveillance and wide area monitoring The database will be made public to the research community for perusal towards long range face related research Deteriorations unique to high magnification and long range face images are investigated in terms of face recognition rates Magnification blur is proved to be an additional major degradation source, which can be alleviated via blur assessment and deblurring algorithms Experimental results validate a relative improvement of up to 25% in recognition rates after assessment and enhancement of degradations

Tracking a moving object with real‐time obstacle avoidance

Abstract: Purpose – Aims to develop a robotic platform to autonomously track a moving objectDesign/methodology/approach – This robotic platform, based on a modular system known as SafeBot, uses two sensors: a visual CCD camera and a laser‐based range sensor. The rigidly mounted camera tracks an object in front of the platform and generates appropriate drive commands to keep the object in view, even if the object itself moves. The range sensor detects other objects as the platform moves to provide real‐time obstacle avoidance while continuously tracking the original object.Findings – The current approach successfully tracks an object, particularly a human subject, and avoids reasonably sized obstacles, but on‐board processing limitations restrict the speed of the object to approximately 5 km/h.Originality/value – The core technology – a moving object tracked by a mobile robot with real‐time obstacle avoidance – is an integrated system comprising object tracking on a mobile platform and real‐time obstacle avoidance w...

Radial Supershapes for Solid Modeling

Abstract: In the previous work, an efficient method has been proposed to represent solid objects as multiple combinations of globally deformed supershapes. In this paper, this framework is applied with a new supershape implicit function that is based on the notion of radial distance and results are presented on realistic models composed of hundreds of hierarchically globally deformed supershapes. An implicit equation with guaranteed differential properties is obtained by simple combinations of the primitives’ implicit representations using R-function theory. The surface corresponding to the zero-set of the implicit equation is efficiently and directly polygonized using the primitives’ parametric forms. Moreover, hierarchical global deformations are considered to increase the range of shapes that can be modeled. The potential of the approach is illustrated by representing complex models composed of several hundreds of primitives inspired from CAD models of mechanical parts.

Supershape Recovery from 3D Data Sets

Abstract: In this paper, we apply supershapes and R-functions to surface recovery from 3D data sets. Individual supershapes are separately recovered from a segmented mesh. R-functions are used to perform Boolean operations between the reconstructed parts to obtain a single implicit equation of the reconstructed object that is used to define a global error reconstruction function. We present surface recovery results ranging from single synthetic data to real complex objects involving the composition of several supershapes and holes.

A Generalized and Automatic Image Contrast Enhancement Using Gray Level Grouping

Abstract: Contrast enhancement has an important role in image processing applications. Conventional contrast enhancement techniques either fail to produce satisfactory results for a broad variety of low-contrast images, or cannot be automatically applied to different images, because their parameters must be specified manually to produce a satisfactory result for a given image. This paper describes a new automatic method for contrast enhancement. The basic procedure is to first group the histogram components of a low-contrast image into the proper number of bins according to a selected criterion, then redistribute these bins uniformly over the grayscale, and finally ungroup the previously grouped gray-levels. Accordingly, this new technique is named Gray-Level Grouping (GLG). GLG not only produces results superior to conventional contrast enhancement techniques, but is also fully automatic in most circumstances, and is applicable to a broad variety of images.

Mobile scanning system for the fast digitization of existing roadways and structures

Abstract: Purpose – To present a Mobile Scanning System for digitizing three‐dimensional (3D) models of real‐world terrain.Design/methodology/approach – A combination of sensors (video, laser range, positioning, orientation) is placed on a mobile platform, which moves past the scene to be digitized. Data fusion from the sensors is performed to construct an accurate 3D model of the target environment.Findings – The developed system can acquire accurate models of real‐world environments in real time, at resolutions suitable for a variety of tasks.Originality/value – Treating the individual subsystems of the mobile scanning system independently yields a robust system that can be easily reconfigured on the fly for a variety of scanning scenarios.

Geometry Refinement of 3D Surfaces Using Kriging

Abstract: 3D imaging is a popular method for acquiring accurate models for a variety of applications. However, the size of the geometric features that can be modeled in this manner is dependant on the scanning system?s resolution. This paper presents a method that attempts to accurately reconstruct regions whose features are at or below the system?s scanning resolution, combining automatic region selection with a form of kriging. A curvature-based segmentation is followed by an automated geometry refinement procedure in which the model of spatial correlation between the irregularly sampled 3D data is automatically determined. Geometry refinement is done by a regularized kriging approach that is designed to preserve the sharp features typical to many 3D laser range applications. This method is validated on synthetic data, showing that the accuracy of our method is higher than that of its standard competitors. Then, the performance on real data is demonstrated through several examples.

Improving Video-Based Robot Self Localization Through Outlier Removal

Abstract: The purpose of this paper is to present a method for rejecting false matches of points from successive views in a video sequence - e.g., one used to perform Pose from Motion for a mobile sensing platform. Invariably, the algorithms used to determine point correspondences between two images output false matches along with the true. These false matches negatively impact the calculations required to perform the pose estimation from video. This paper presents a new algorithm for identifying these false matches and removing them from consideration in order to improve system performance. Experimental results show that our algorithm works in cases where the percentage of false matches may be as high as 80%, providing a set of point correspondences whose true/false match ratio is much higher than the mutual best match method commonly used for outlier filtering, resulting in comparable or better outlier rejection - increasing the true/false match ratio by 2-3 times - in only a fraction of the time.

Thermal Modeling and Imaging of As-built Vehicle Components

Abstract: This paper addresses the issue of thermal modeling of vehicle components where the 3D models of the components are not traditional CAD models derived from engineering drawings but are models derived from 3Dimaging scans of existing real-world objects. A “reverse engineering” pipeline is presented that uses 3D scanners to capture the geometry of an existing object from different views and then integrates these multiple views into a single 3D surface mesh description of the object. This process requires no a priori CAD drawings of the object and thus enables modeling in situations where the original manufacturer no longer exists or soldiers have made undocumented field modifications. The paper further discusses the use of these generated 3D models to simulate thermal imaging properties of the object using the Multi Service Electro-Optic Signature (MuSES) software. Thus, given an object of interest, this paper explores, first generating a 3D model of the object and, second, analyzing the thermal signature through simulation. As a third step, this paper investigates the experimental achievability and limitations of thermal image simulation of vehicle components.

Multispectral Fusion for Indoor and Outdoor Face Authentication

Abstract: Face analysis via multispectral imaging is a relatively unexplored territory in face recognition research The multispectral, multimodal and multi-illuminant IRIS-M3 database was acquired, indoors and outdoors, to promote research in this direction In the database, each data record has images spanning all bands in the visible spectrum and one thermal image, acquired under different illumination conditions The spectral power distributions of the lighting sources and daylight conditions are also encoded in the database Multispectral fused images show improved face recognition performance compared to the visible monochromatic images Galleries and probes were selected from the indoor and outdoor sections of the database to study the effects of data and decision fusion in the presence of lighting changes Our experiments were validated by comparing cumulative match characteristics of monochromatic probes against multispectral probes obtained via multispectral fusion by averaging, principal component analysis, wavelet analysis, illumination adjustment and decision level fusion In this effort, we demonstrate that spectral bands, either individually or fused by different techniques, provide better face recognition results with up to 78% improvement on conventional visible images

3D Target Scale Estimation and Motion Segmentation for Size Preserving Tracking in PTZ Video

Abstract: In size preserving video tracking, the camera’s focal length (zoom) is adjusted automatically to compensate for the changes in the target’s image size caused by the relative motion between the camera and the target. The accurate estimation of these changes is paramount to the system performance. The existing method of choice for real-time target scale estimation applies structure from motion (SFM) based on the weak perspective projection model [1]. We design a target scale estimation algorithm with linear solution based on the more advanced paraperspective projection model. Another key problem in SFM based algorithms is the separation between foreground and background features (image corners), especially when composite camera and target motions are involved. This paper also addresses a fast foreground/background separation algorithm, the affine shape method. The resulting segmentation automatically adapts to the target’s 3D geometry and motion. Experimental results illustrate the effectiveness of the proposed scale estimation and segmentation algorithms in tracking translating and rotating objects with a PTZ camera while preserving their sizes.

Reconstructing 3D CAD Models for Simulation Using Imaging-Based Reverse Engineering

Abstract: The purpose of this research is to investigate imaging-based methods to reconstruct 3D CAD models of real-world objects. The methodology uses structured lighting technologies such as coded-pattern projection and laser-based triangulation to sample 3D points on the surfaces of objects and then to reconstruct these surfaces from the dense point samples. This reverse engineering (RE) research presents reconstruction results for a military tire that is important to tire-soil simulations. The limitations of this approach are the current level of accuracy that imaging-based systems offer relative to more traditional CMM modeling systems. The benefit however is the potential for denser point samples and increased scanning speeds of objects, and with time, the imaging technologies should continue to improve to compete with CMM accuracy. This approach to RE should lead to high fidelity models of manufactured and prototyped components for comparison to the original CAD models and for simulation analysis. We focus this paper on the data collection and view registration problems within the RE pipeline.

Auto-focusing in extreme zoom surveillance: a system approach with application to faces

Abstract: Auto-focusing is an indispensable function for imaging systems used in surveillance and object tracking. In this paper, we conduct a study of an image-based passive auto-focusing control for high magnification (>50×) systems using off-the-shelf telescopes and digital camcorders with applications to long range near-ground surveillance and face tracking. Considering both speed of convergence and robustness to image degradations induced by high system magnifications and long observation distances, we introduce an auto-focusing mechanism suitable for such applications, including hardware design and algorithm development. We focus on the derivation of the transition criteria following maximum likelihood (ML) estimation for the selection of adaptive step sizes and the use of sharpness measures for the proper evaluation of high magnification images. The efficiency of the proposed system is demonstrated in real-time auto-focusing and tracking of faces from distances of 50m~300m.