Proceedings 30th Applied Imagery Pattern Recognition Workshop (AIPR 2001). Analysis and Understanding of Time Varying Imagery

10-12 Oct. 2001

Filter Results

Displaying Results 1 - 25 of 33
  • Proceedings 30th Applied Imagery Pattern Recognition Workshop (AIPR 2001). Analysis and Understanding of Time Varying Imagery

    Publication Year: 2001
    Request permission for commercial reuse | PDF file iconPDF (430 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 2001, Page(s): 201
    Request permission for commercial reuse | PDF file iconPDF (49 KB)
    Freely Available from IEEE
  • Face detection and eye location using a modified ALISA texture module

    Publication Year: 2001, Page(s):187 - 193
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (893 KB) | HTML iconHTML

    This paper presents an automatic method for face detection and eye location using a modified version of the ALISA Texture Module. ALISA (Adaptive Learning Image and Signal Analysis) is an adaptive classification engine based on collective learning systems theory. Using supervised training, the ALISA engine builds a set of multi-dimensional feature histograms that estimate the joint PDF of the feat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scene and content analysis from multiple video streams

    Publication Year: 2001, Page(s):119 - 125
    Cited by:  Papers (5)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (724 KB) | HTML iconHTML

    In this paper, we describe a framework for video analysis and a method to detect and understand the class of events we refer to as "split and merge events" from single or multiple video streams. We start with automatic detection of scene changes, including camera operations such as zoom, pan, tilts and scene cuts. For each new scene, camera calibration is performed, the scene geometry is estimated... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Directional edge registration for temporal chest image subtraction

    Publication Year: 2001, Page(s):32 - 36
    Cited by:  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1045 KB) | HTML iconHTML

    We used a directional filtering technique to accurately register the ribs on temporal chest radiographs. Rib registration was the primary technical objective. In order to accurately extract the ribs, we developed a directional edge function that used rotating kernels through a dynamic search technique to extract rib edges of varying contrast. A directionally-weighted operator with a phase-contrast... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model-based face tracking for dense motion field estimation

    Publication Year: 2001, Page(s):149 - 153
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (712 KB) | HTML iconHTML

    When estimating the dense motion field of a video sequence, if little is known or assumed about the content, a limited constraint approach such as optical flow must be used. Since optical flow algorithms generally use a small spatial area in the determination of each motion vector the resulting motion field can be noisy, particularly if the input video sequence is noisy. If the moving subject is k... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A recursive Otsu-Iris filter technique for high-speed detection of lumen region from endoscopic images

    Publication Year: 2001, Page(s):182 - 186
    Cited by:  Papers (3)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (532 KB) | HTML iconHTML

    In this paper, a hardware efficient technique to segment the lumen region from endoscopic images is presented. It is based on applying the combined Otsu-Iris filter operations recursively. The proposed technique applies the Otsu's procedure recursively to obtain a coarse region of interest (ROI), which is then subjected to an Iris filter operation so that a smaller enhanced region can be identifie... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multiple perspective spectral approach to object detection

    Publication Year: 2001, Page(s):115 - 118
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (383 KB) | HTML iconHTML

    Many applications for detection of objects such as video analysis require that candidate objects be observed over a range of perspectives in 3 dimensional space. As a result we must have a robust model and detection process for these objects in order to accurately detect them through a range of geometric transformations. In order to keep our detection process computationally efficient, we use a co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mixture of principal axes registration for change analysis in computer-aided diagnosis

    Publication Year: 2001, Page(s):25 - 31
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (657 KB) | HTML iconHTML

    Non-rigid image registration is a prerequisite for many medical image analysis applications, such as image fusion of multi-modality images and quantitative change analysis of a temporal sequence in computer-aided diagnosis. By establishing the point correspondence of the extracted feature points, it is possible to recover the deformation using nonlinear interpolation methods such as the thin-plate... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using video for recovering texture

    Publication Year: 2001, Page(s):129 - 134
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1177 KB) | HTML iconHTML

    Existing approaches to characterizing image texture usually rely on computing a local response to a bank of correlation filters, such as derivatives of a Gaussian, in one image. Recently, significant progress has been made in characterizing a single texture under varying viewpoint and illumination conditions, leading to the bi-directional texture function that describes the smooth variation of fil... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Channel-optimized video coding for low-power wireless applications

    Publication Year: 2001, Page(s):163 - 168
    Cited by:  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (704 KB) | HTML iconHTML

    This paper presents an error-robust channel-optimized coding algorithm for the transmission of low-rate video over wireless channels. The proposed coder uses a robust channel-optimized trellis-coded quantization (COTCQ) stage that is designed to optimize the image coding based on the channel characteristics. The resilience to channel errors is obtained without the use of channel coding or error co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experiments in estimation of independent 3D motion using EM

    Publication Year: 2001, Page(s):143 - 148
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (588 KB) | HTML iconHTML

    In this paper we address the problem of multiple 3D rigid body motion estimation from the optical flow. We use the differential epipolar constraint to measure the consistency of the local flow estimates with 3D rigid body motion and employ a probabilistic interpretation of the overall flowfield in terms of mixture models. The estimation of 3D motion parameters as well as the refinement of the init... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A qualitative image reconstruction from an axial image sequence

    Publication Year: 2001, Page(s):175 - 181
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (601 KB) | HTML iconHTML

    This paper presents a method to process axial monocular image sequences for mobile robot obstacle detection. We do not aim to achieve a complete scene reconstruction, but only to evaluate the time to collision and surface orientation useful for robot obstacle avoidance. Using a planar facet representation we first calculate formally the velocity field generated by the camera motion. The apparent d... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distributed multiuser visualization of time varying anatomical data

    Publication Year: 2001, Page(s):109 - 114
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (870 KB) | HTML iconHTML

    We describe a networked environment for navigating and visualizing 3-dimensional anatomical data with extensions for time varying volumes. The Duke Center for In Vivo Microscopy (CIVM) has been capturing volumetric data of mice using magnetic resonance microscopy. Current data sets are 5123 with 16 bit precision per voxel at an isotropic resolution of 50 microns. A new instrument will p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards robust face recognition from video

    Publication Year: 2001, Page(s):94 - 100
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (675 KB) | HTML iconHTML

    A novel, template-based method for face recognition is presented. The goals of the proposed method are to integrate multiple observations for improved robustness and to provide auxiliary confidence data for subsequent use in an automated video surveillance system. The proposed framework consists of a parallel system of classifiers, referred to as observers, where each observer is trained on one fa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Suitability of synthetic imagery for ATR evaluation

    Publication Year: 2001, Page(s):51 - 56
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (707 KB) | HTML iconHTML

    There is a commonly held belief among many who participate in ATR development and evaluation that a lack of data (imagery from tactical sensors) is a significant obstacle in the production and thorough evaluation of high performance ATR systems. Recognizing that it may be too costly or even impossible to collect a sufficient quantity of real data to adequately represent all ATR mission scenarios o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image fusion or 4D cardiac CTA and MR images

    Publication Year: 2001, Page(s):21 - 24
    Cited by:  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (592 KB) | HTML iconHTML

    Various imaging techniques can be used to evaluate coronary artery disease and cardiac function. However, no single imaging modality provides extensive information on both. The goal of this research is to develop a method for combining the coronary vasculature obtained from computed tomographic angiography (CTA) data with the myocardial functional information obtained from dynamic magnetic resonan... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The surgical CAD/CAM paradigm and an implementation for robotically-assisted percutaneous local therapy

    Publication Year: 2001, Page(s):3 - 8
    Cited by:  Patents (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1045 KB) | HTML iconHTML

    Computer-integrated surgery represents a growing segment of our national healthcare system. These systems transform preoperative images and other information into models of individual patients, assist clinicians in developing an optimized interventional plan, register this preoperative data to the actual patient in the operating room, and then use a variety of means, such as robots and image overl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A conversational paradigm for multimodal human interaction

    Publication Year: 2001, Page(s):80 - 86
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (769 KB) | HTML iconHTML

    We present an alternative to the manipulative and semaphoric gesture recognition paradigms. Human multimodal communicative behaviors form a tightly integrated whole. We present a paradigm multimodal analysis in natural discourse based on a feature decompositive psycholinguistically derived model that permits us to access the underlying structure and intent of multimodal communicative discourse. We... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multiresolution approach for video texture registration

    Publication Year: 2001, Page(s):126 - 128
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (355 KB) | HTML iconHTML

    Electro-optical imagery can have uniform characteristics that prevent it from being registered by conventional edge-based methods. Such uniform characteristics, if they have periodicity, can be exploited using multi-resolution texture extraction techniques. We first use a multi-resolution Markov model to represent electro-optical textures and apply an autoregressive statistical approach to find co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluating the benefits of assisted target recognition

    Publication Year: 2001, Page(s):39 - 45
    Cited by:  Papers (3)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (804 KB) | HTML iconHTML

    Image exploitation systems that employ automatic target recognition (ATR) technology generally require that a human-in-the-loop validates the ATR results, i.e. assisted target recognition. To evaluate the benefits of assisted target recognition, one must first understand the human's interaction with the ATR algorithms plus the many factors that influence the performance of both the imagery analyst... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using histograms to detect and track objects in color video

    Publication Year: 2001, Page(s):154 - 159
    Cited by:  Papers (51)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1019 KB) | HTML iconHTML

    Two methods of detecting and tracking objects in color video are presented. Color and edge histograms are explored as ways to model the background and foreground of a scene. The two types of methods are evaluated to determine their speed, accuracy and robustness. Histogram comparison techniques are used to compute similarity values that aid in identifying regions of interest. Foreground objects ar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A realtime object tracking system using a color camera

    Publication Year: 2001, Page(s):137 - 142
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (679 KB) | HTML iconHTML

    We describe a real-time object tracking system based on a color camera and a personal computer. The system is capable of tracking colored objects in the camera view in real-time. The algorithm uses the color, shape and motion of the object to achieve robust tracking even in the presence of partial occlusion and shape change. A key component of the system is a computationally efficient manner to tr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High storage capacity architecture for pattern recognition using an array of Hopfield neural networks

    Publication Year: 2001, Page(s):169 - 174
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB) | HTML iconHTML

    A new approach for the recognition of images using a two dimensional array of Hopfield neural networks is presented in this paper. In the proposed method, the N×N image is divided into sub-blocks of size M×M. Two-dimensional Hopfield neural networks of size M×M are used to learn and recognize the sub-images. All the N2/M2 Hopfield modules are functioning ind... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-modal fusion for video understanding

    Publication Year: 2001, Page(s):103 - 108
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (750 KB) | HTML iconHTML

    The exploitation of semantic information in computer vision problems can be difficult because of the large difference in representations and levels of knowledge. Image analysis is formulated in terms of low-level features describing image structure and intensity, while high-level knowledge such as purpose and common sense are encoded in abstract, non-geometric representations. In this work we atte... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.