Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on

Date 15-15 June 2000

Go

Filter Results

Displaying Results 1 - 25 of 116
  • Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)

    Publication Year: 2000
    Save to Project icon | Request Permissions | PDF file iconPDF (660 KB)  
    Freely Available from IEEE
  • Real-time 3D motion and structure of point features: a front-end system for vision-based control and interaction

    Publication Year: 2000 , Page(s): 778 - 779 vol.2
    Cited by:  Papers (10)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (230 KB)  

    We present a system that consists of one camera connected to a personal computer that can (a) select and track a number of high-contrast point features on a sequence of images, (b) estimate their three-dimensional motion and position relative to an inertial reference frame, assuming rigidity, (c) handle occlusions that cause point-features to disappear as well as new features to appear. The system can also (d) perform partial self-calibration and (e) check for consistency of the rigidity assumption, although these features are not implemented in the current release. All of this is done automatically and in real-time (30 Hz) for 40-50 point features using commercial off-the-shelf hardware. The system is based on an algorithm presented by Chiuso et al. (2000), the properties of which have been analyzed by Chiuso and Soatto (2000). In particular, the algorithm is provably observable, provably minimal and provably stable- under suitable conditions. The core of the system, consisting of C++ code ready to interface with a frame grabber as well as Matlab code for development, is available at http://ee.wustl.edu/-soatto/research.html. We demonstrate the system by showing its use as (1) an ego-motion estimator, (2) an object tracker, and (3) an interactive input device, all without any modification of the system settings. View full abstract»

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

    Publication Year: 2000 , Page(s): 799 - 804
    Save to Project icon | Request Permissions | PDF file iconPDF (294 KB)  
    Freely Available from IEEE
  • Scene modeling for wide area surveillance and image synthesis

    Publication Year: 2000 , Page(s): 160 - 167 vol.2
    Cited by:  Papers (19)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (508 KB)  

    We present a method for modeling a scene that is observed by a moving camera, where only a portion of the scene is visible at any time. This method uses mixture models to represent pixels in a panoramic view, and to construct a “background image” that contains only static (non-moving) parts of the scene. The method can be used to reliably detect moving objects in a video sequence, detect patterns of activity over a wide field of view, and remove moving objects from a video or panoramic mosaic. The method also yields improved results in detecting moving objects and in constructing mosaics in the presence of moving objects, when compared with techniques that are not based on scene modeling. We present examples illustrating the results View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust stereo ego-motion for long distance navigation

    Publication Year: 2000 , Page(s): 453 - 458 vol.2
    Cited by:  Papers (35)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (872 KB)  

    Several methods for computing observer motion from monocular and stereo image sequences have been proposed. However, accurate positioning over long distances requires a higher level of robustness than previously achieved. This paper describes several mechanisms for improving robustness in the context of a maximum-likelihood stereo ego-motion method. We demonstrate that even a robust system will accumulate super-linear error in the distance traveled due to increasing orientation errors. However, when an absolute orientation sensor is incorporated, the growth is reduced to linear in the distance traveled, grows much more slowly in practice. Our experiments, including a trial with 210 stereo pairs, indicate that these techniques can achieve errors below 1% of the distance traveled. This method has been implemented to run on-board a prototype Mars rover View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An energy-based framework for dense 3D registration of volumetric brain images

    Publication Year: 2000 , Page(s): 270 - 275 vol.2
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (432 KB)  

    In this paper we describe a new method for medical image registration. The registration is formulated as a minimization problem involving robust estimators. We propose an efficient hierarchical optimization framework which is both multiresolution and multigrid. An anatomical segmentation of the cortex is introduced in the adaptive partitioning of the volume on which the multigrid minimization is based. This allows to limit the estimation to the areas of interest, to accelerate the algorithm, and to refine the estimation in specified areas. Furthermore we introduce a methodology to constrain the registration with landmarks such as anatomical structures. The performances of this method are objectively evaluated on simulated data and its benefits are demonstrated on a large database of real acquisitions View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic recovery of relative camera rotations for urban scenes

    Publication Year: 2000 , Page(s): 282 - 289 vol.2
    Cited by:  Papers (26)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (416 KB)  

    In this paper we describe a formulation of extrinsic camera calibration that decouples rotation from translation by exploiting properties inherent in urban scenes. We then present an algorithm which uses edge features to robustly and accurately estimate relative rotations among multiple cameras given intrinsic calibration and approximate initial pose. The algorithm is linear both in the number of images and the number of features. We estimate the number and directions of vanishing points (VPs) with respect to each camera using a hybrid approach that combines the robustness of the Hough transform with the accuracy of expectation maximization. Matching and labeling methods identify unique VPs and correspond them across all cameras. Finally, a technique akin to bundle adjustment produces globally optimal estimates of relative camera rotations by bringing all VPs into optimal alignment. Uncertainty is modeled and used at every stage to improve accuracy. We assess the algorithm's performance on both synthetic and real data, and compare our results to those of semi-automated photogrammetric methods for a large set of real hemispherical images, using several consistency and error metrics View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning in Gibbsian fields: how accurate and how fast can it be?

    Publication Year: 2000 , Page(s): 2 - 9 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (728 KB)  

    In this article, we present a unified framework for learning Gibbs models from training images. We identify two key factors that determine the accuracy and speed of learning Gibbs models: (1). Fisher information, and (2). The accuracy of Monte Carlo estimate for partition functions. We propose three new learning algorithms under the unified framework. (I). The maximum partial likelihood estimator. (II). The maximum patch likelihood estimator, and (III). The maximum satellite likelihood estimator. The first two algorithms can speed up the minimax entropy algorithm by about 2D times without losing much accuracy. The third one makes use of a set of known Gibbs models as references-dubbed “satellites” and can approximately estimate the minimax entropy model in the speed of 10 seconds View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tracking segmented objects using tensor voting

    Publication Year: 2000 , Page(s): 118 - 125 vol.2
    Cited by:  Papers (6)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (428 KB)  

    The paper presents a new approach to track objects in motion when observed by a fixed camera, with severe occlusions, merging/splitting objects and defects in the detection. We first detect regions corresponding to moving objects in each frame, then try to establish their trajectory. We propose to implement the temporal continuity constraint efficiently, and apply it to tracking problems in realistic scenarios. The method is based on a spatiotemporal (2D+t) representation of the moving regions, and uses the tensor voting methodology to enforce smoothness in space and table of the tracked objects. Although other characteristics may be considered, only the connected components of the moving regions are used, without further assumptions about the object being tracked. We demonstrate the performance of the system on several real sequences View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A linear algorithm for camera self-calibration, motion and structure recovery for multi-planar scenes from two perspective images

    Publication Year: 2000 , Page(s): 474 - 479 vol.2
    Cited by:  Papers (5)  |  Patents (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (248 KB)  

    In this paper we show that given two homography matrices for two planes in space, there is a linear algorithm for the rotation and translation between the two cameras, the focal lengths of the two cameras and the plane equations in the space. Using the estimates as an initial guess, we can further optimize the solution by minimizing the difference between observations and reprojections. Experimental results are shown. We also provide a discussion about the relationship between this approach and the Kruppa equation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Surface growing from stereo images

    Publication Year: 2000 , Page(s): 571 - 576 vol.2
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (908 KB)  

    We present a new theoretical result for the problem of surface reconstruction from stereo images. For a given initial seed point, i.e. for a pair of corresponding points in the left and right image, the proposed algorithm grows the surface without directly computing the point correspondences. The method assumes the Lambertian surface reflectance model. Our approach is based on a surface normal calculation from the left and right image gradients. Knowing the surface normal, the algorithm grows the surface in the directions defined by the tangent plane. The algorithm is independent of the camera model, and requires placement of an initial seed point for each surface to be reconstructed. Technical problems associated with errors in the image gradient estimates and camera calibration are discussed and a solution is suggested. In addition to this algorithm, we present a theoretical result that permits one to track surfaces deforming in time, which is often encountered in medical applications (e.g. brain surface deforms during the surgery). These methods of surface reconstruction and deformable surface tracking are applied to the particular problem of brain shift, commonly recognized as one of the main source of errors in surgical navigation systems used in neurosurgery. We also suggest a way to overcome problems associated with brain surface specularities caused by fluids on the brain surface and lights in the operating room. We conclude with experimental results on real brain images and show that the surface reconstruction algorithm is robust to the position of the initial seed point View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A semi-automatic method for resolving occlusion in augmented reality

    Publication Year: 2000 , Page(s): 225 - 230 vol.2
    Cited by:  Papers (7)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1340 KB)  

    Realistic merging of virtual and real objects requires that the augmented patterns be correctly occluded by foreground objects. In this paper we propose a semi-automatic method for resolving occlusion in augmented reality which makes use of key-views. Once the user has outlined the occluding objects in the key-views, our system detects automatically these occluding objects in the intermediate views. A region of interest that contains the occluding objects is first computed from the outlined silhouettes. One of the main contribution of this paper is that this region takes into account the uncertainty on the computed interframe motion. Then a deformable region-based approach is used to recover the actual occluding boundary within the region of interest from this prediction View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting dynamic behavior in compressed fingerprint videos: distortion

    Publication Year: 2000 , Page(s): 320 - 326 vol.2
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (852 KB)  

    Distortions in fingerprint images arising from the elasticity of finger skin and the pressure and movement of fingers during image capture lead to great difficulties in establishing a match between multiple images acquired from a single finger. In a single fingerprint image depicting a finger at some given instant of time, it is difficult to get any distortion information. Further, static two-dimensional or three-dimensional (electronic) copies of fingerprints can be fabricated and used to spoof remote biometric security systems since the input required by the systems is not a function of time. This paper addresses these issues, by proposing the novel use of fingerprint video sequences to investigate and exploit dynamic behaviors manifested by fingers over time during image acquisition. In particular, we present a novel approach to detect and estimate distortion occurring in fingerprint video streams. Our approach directly works on MPEG-{1, 2} encoded fingerprint video bitstreams to estimate interfield flow without decompression, and uses flow characteristics to investigate temporal behaviour of the fingerprints. The joint temporal and motion analysis leads to a novel technique to detect and characterize distortion reliably. The proposed method has been tested on the NIST 24 database and the results are very promising View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature based visualization of geophysical data

    Publication Year: 2000 , Page(s): 276 - 281 vol.2
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (652 KB)  

    Our goal is to develop a feature based framework for data mining and forecasting from geophysical data fields. These data may be generated from either numerical simulation models or space based platforms. This paper focuses on pertinent features from sea surface temperature (SST) fields that are observed with the AVHRR satellite. Our contribution consist of three components: (1) A method for tracking feature velocities from from fluid motion with incompressibility constraint, (2) a method for localizing singular events such as vortices and saddle points from underlying feature velocities, and (3) application of our protocol to 12 years of high resolution real data to reveal novel seasonal and inter-annual trends based on computed events View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CueVideo: a system for cross-modal search and browse of video databases

    Publication Year: 2000 , Page(s): 786 - 787 vol.2
    Cited by:  Papers (2)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (152 KB)  

    The detection and recognition of events is a challenging problem in video databases. It involves cross-linking and combining information available in multiple modalities such as audio, video and associated text metadata. CueVideo is a system designed for the discovery and recognition of specific events called topics of discussion through advanced video summarization and cross-modal indexing. It supports search for relevant video content through several modes of video summarization including storyboards, moving storyboards and time-scale modified audio summarization. It also enables the recognition and indexing of topical events through cross-model search of audio and video content based on text and image queries respectively View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Surface landmark selection and matching in natural terrain

    Publication Year: 2000 , Page(s): 413 - 420 vol.2
    Cited by:  Papers (12)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1324 KB)  

    In this paper we present an algorithm for robust absolute position estimation in natural terrain based on landmarks extracted from dense 3-D surfaces. Our landmarks are constructed by concatenating pose dependent oriented surface points with pose invariant surface signatures into a single feature vector; this definition of landmarks allows a priori pose information to be used to constrain the search for landmark matches. The first step in our algorithm is to extract landmarks from stable and salient surface patches. These landmarks are then stored in a closest point search structure with which landmarks are matched efficiently using available pose constraints and invariant values. Finally, an iterative pose estimation algorithm, based on least median squares, is wrapped around landmark matching to eliminate outliers and estimate absolute position. To validate our algorithm, we show hundreds of absolute position estimation results from three different natural scenes. These results show that our algorithm can incorporate constraints on position and attitude for efficient landmark matching and match small and dense scene surface patches to large and coarse model surfaces View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A geometric approach to blind deconvolution with application to shape from defocus

    Publication Year: 2000 , Page(s): 10 - 17 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1032 KB)  

    We propose a solution to the generic “bilinear calibration-estimation problem” when using a quadratic cost function and restricting to (locally) translation-invariant imaging models. We apply the solution to the problem of reconstructing the three-dimensional shape and radiance of a scene from a number of defocused images. Since the imaging process maps the continuum of three-dimensional space onto the discrete pixel grid, rather than discretizing the continuum we exploit the structure of maps between (finite-and infinite-dimensional) Hilbert spaces and arrive at a principled algorithm that does not involve any choice of basis or discretization. Rather, these are uniquely determined by the data, and exploited in a functional singular value decomposition in order to obtain a regularized solution View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sensor networked mobile robotics

    Publication Year: 2000 , Page(s): 782 - 783 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (288 KB)  

    The dominant architecture for mobile robot perception uses sensors on-board the robot, providing a first-person perspective on the environment. We demonstrate a novel mobile robot architecture that uses an environment-based sensor network, which provides third-person perception. The idea is that a mobile robot working in the area tunes in to broadcasts from the video camera network (or in this case from an environment-based computer processing the video frames) to receive sensor data. This distributed sensing configuration offers several advantages over on-board sensing View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiscale combination of physically-based registration and deformation modeling

    Publication Year: 2000 , Page(s): 422 - 429 vol.2
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (680 KB)  

    In this paper we present a novel multiscale approach to recovery of nonrigid motion from sequences of registered intensity and range images. The main idea of our approach is that a finite element (FEM) model can naturally handle both registration and deformation modeling using a single model-driving strategy. The method includes a multiscale iterative algorithm based on analysis of the undirected Hausdorff distance to recover correspondences. The method is evaluated with respect to speed, accuracy, and noise sensitivity. Advantages of the proposed approach are demonstrated using man-made elastic materials and human skin motion. Experiments with regular grid features are used for performance comparison with a conventional approach (separate snakes and FEM models). It is shown that the new method does not require a grid and can adapt the model to available object features View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intel's Computer Vision Library: applications in calibration, stereo segmentation, tracking, gesture, face and object recognition

    Publication Year: 2000 , Page(s): 796 - 797 vol.2
    Cited by:  Papers (19)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (348 KB)  

    Intel's Microcomputer Research Lab has been developing a highly optimized Computer Vision Library (CVLib) that automatically detects processor type and loads the appropriate MMXTM technology assembly tuned module for that processor. MMX optimized functions are from 2 to 8 times faster than optimized C functions. We will be demonstrating various algorithms supported by CVLib and handing out CDs containing the library View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Iterative projective reconstruction from multiple views

    Publication Year: 2000 , Page(s): 430 - 437 vol.2
    Cited by:  Papers (22)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (300 KB)  

    We propose an iterative method for the recovery of the projective structure and motion from multiple images. It has been recently noted that by scaling the measurement matrix by the true projective depths, recovery of the structure and motion is possible by factorization. The reliable determination of the projective depths is crucial to the success of this approach. The previous approach recovers these projective depths using pairwise constraints among images. We first discuss a few important drawbacks with this approach. We then propose an iterative method where we simultaneously recover both the projective depths as well as the structure and motion that avoids some of these drawbacks by utilizing all of the available data uniformly. The new approach makes use of a subspace constraint on the projections of a 3D point onto an arbitrary number of images. The projective depths are readily determined by solving a generalized eigenvalue problem derived from the subspace constraint. We also formulate a dual subspace constraint on all the points in a given image, which can be used for verifying the projective geometry of a scene or object that was modeled. We prove the monotonic convergence of the iterative scheme to a local maximum. We show the robustness of the approach on both synthetic and real data despite large perspective distortions and varying initializations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Inconsistencies in edge detector evaluation

    Publication Year: 2000 , Page(s): 398 - 404 vol.2
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (192 KB)  

    In recent years, increasing effort has gone into evaluating computer vision algorithms in general, and edge detection algorithms in particular. Most of the evaluation techniques use only a few test images, leaving open the question of how broadly their results can be interpreted. Our research tests the consistency of the receiver operating characteristic (ROC) curve, and demonstrates why consistent edge detector evaluation is difficult to achieve. We show how easily the framework can be manipulated to rank any of three modern edge detectors in any order by making minor changes to the test imagery. We also note that at least some of the inconsistency is the result of the erratic nature of the algorithms themselves, suggesting that it is still possible to create better edge detectors View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel projections for stereo reconstruction

    Publication Year: 2000 , Page(s): 493 - 500 vol.2
    Cited by:  Papers (9)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    This paper proposes a novel technique to computing geometric information from images captured under parallel projections. Parallel images are desirable for stereo reconstruction because parallel projection significantly reduces foreshortening. As a result, correlation based matching becomes more effective. Since parallel projection cameras are not commonly available, we construct parallel images by rebinning a large sequence of perspective images. Epipolar geometry, depth recovery and projective invariant for both 1D and 2D parallel stereos are studied. From the uncertainty analysis of depth reconstruction, it is shown that parallel stereo is superior to both conventional perspective stereo and the recently developed multiperspective stereo for vision reconstruction, in that uniform reconstruction error is obtained in parallel stereo. Traditional stereo reconstruction techniques, e.g. multi-baseline stereo, can still be applicable to parallel stereo without any modifications because epipolar lines in a parallel stereo are perfectly straight. Experimental results further confirm the performance of our approach View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fluid structure and motion analysis from multi-spectrum 2D cloud image sequences

    Publication Year: 2000 , Page(s): 744 - 751 vol.2
    Cited by:  Papers (9)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (712 KB)  

    We present a novel approach to estimate and analyze 3D fluid structure and motion of clouds from multi-spectrum 2D cloud image sequences. Accurate cloud-top structure and motion are very important for a host of meteorological and climate applications. However, due to the extremely complex nature of cloud fluid motion, classical nonrigid motion analysis methods are insufficient for solving this particular problem. In this paper, two spectra of satellite cloud images are utilized. The high-resolution visible channel is first used to perform cloud tracking by using a recursive algorithm which integrates local motion analysis with a set of global fluid constraints, defined according to the physical fluid dynamics. Then, the infrared channel (thermodynamic information) is incorporated to post-process the cloud tracking results in order to capture the cloud density variations and small details of cloud fluidity. Experimental results on GOES (Geostationary Operational Environmental Satellite) cloud image sequences are presented in order to validate and evaluate both the effectiveness and robustness of our algorithm View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting and tracking human face and eye using an space-varying sensor and an active vision head

    Publication Year: 2000 , Page(s): 168 - 173 vol.2
    Cited by:  Papers (3)  |  Patents (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1000 KB)  

    We have developed a system for detecting and tracking human face and eye in an unstructured environment. We adopt a biologically plausible retinally connected neural network architecture and integrate it with an active vision system. While the active vision system tracks the object moving in real time, the neural network detects the face and eye location from the video stream at a slower rate. The paper provides a systematic way of creating and selecting examples for training the network by exploring the link between theory and practice. Experimental results on a real sequence of images from a space-varying sensor depicts the performance of the system View full abstract»

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