Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170)

Volume 1 • 20-20 Aug. 1998

Go

Filter Results

Displaying Results 1 - 25 of 246
  • Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170)

    Publication Year: 1998
    Request permission for reuse | PDF file iconPDF (2254 KB)
    Freely Available from IEEE
  • A non-linear filtering approach to image matching

    Publication Year: 1998, Page(s):1 - 3 vol.1
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (180 KB)

    In this paper we present a novel approach to high precision stereo image matching which employs an iterated extended Kalman filter (IEKF). The matching problem is formulated as a nonlinear filtering problem. We present a state-space representation of the matching problem, and show how nonlinear filtering techniques may be applied to determine optimal transformation parameters. To demonstrate the e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiresolution stereo image matching using complex wavelets

    Publication Year: 1998, Page(s):4 - 7 vol.1
    Cited by:  Papers (10)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (345 KB)

    This paper describes a multiresolution image-matching strategy, based on the complex discrete wavelet transform (CDWT), to derive a dense disparity field with hierarchical (coarse-to-fine) refinement. The CDWT feature space efficiently provides fractionally accurate matching results which are robust to typical image formation perturbations such as offsets, global scaling, and additive noise. At ea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal camera placement to obtain accurate 3D point positions

    Publication Year: 1998, Page(s):8 - 10 vol.1
    Cited by:  Papers (14)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (177 KB)

    Concerns the automation of the camera network design process in order to obtain accurate 3D measurements. We restrict ourselves to the problem where the camera positions are limited only by the incidence angle constraint and it is simplified to the case where the cameras remain at a fixed distance to the set of target points to be measured. The main question addressed is where to place the cameras... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Acquisition and visualization of colored 3D objects

    Publication Year: 1998, Page(s):11 - 15 vol.1
    Cited by:  Papers (21)  |  Patents (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (254 KB)

    This paper presents a complete system for scanning the geometry and surface color of a 3D object and for displaying realistic images of the object from arbitrary viewpoints. A stereo system with active light produces several views of dense range and color data. The data is registered and a surface that approximates the data is constructed. The surface estimate can be fairly coarse, as the appearan... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Search-based contour closure in range images

    Publication Year: 1998, Page(s):16 - 18 vol.1
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (74 KB)

    In this paper we describe a contour closure algorithm to derive a complete region segmentation of range images from an edge detection. The effectiveness of our approach is demonstrated by good results on real range images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Surface recovery by using regularization theory and its application to multiresolution analysis

    Publication Year: 1998, Page(s):19 - 23 vol.1
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (348 KB)

    In this paper, a surface recovery method using multiresolution wavelet transform is proposed. For representing 3D surface shapes, 4th order B-spline functions with uniform knots are introduced as scaling functions of spline wavelets. In order to estimate the surface function, a regularization problem is solved by an iterative algorithm. The estimated surface function can, be decomposed into an app... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • In defense of the Hough transform

    Publication Year: 1998, Page(s):24 - 26 vol.1
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (32 KB)

    The Hough transform has been a widely used technique for geometric primitive extraction. However, recently, a new family of techniques based on optimization, such as the genetic algorithm, the tabu search algorithm, the algorithm based on random samples of minimum subset, claimed their superiority over the Hough transform. In this paper, based on a reasonable criterion, namely the expected number ... View full abstract»

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

    Publication Year: 1998, Page(s):27 - 29 vol.1
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (96 KB)

    Binarization is reduced to function approximation in terms of quantization which is overlaid either with a recursion scheme or with discrete scale-space filtering. Approximations are solved to optimality not requiring any parametric input except that there be two segment classes of the image. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic quadratic calibration for correction of pixel classification boundaries to an accuracy of 2.5 millimeters: an application in cardiac imaging

    Publication Year: 1998, Page(s):30 - 33 vol.1
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (207 KB)

    Left ventricle (LV) boundaries estimated using automated pixel-based classifiers fall short in the apical zone and are not close the ground truth boundaries as delineated by the cardiologists. These errors are not random. They have a systematic positional and orientational bias, the boundary being under-estimated in the apex zone. They have a mean apex error of about 10.5 mm. The main reasons for ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new thresholding algorithm based on all-pole model

    Publication Year: 1998, Page(s):34 - 36 vol.1
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (111 KB)

    A new thresholding algorithm based on all-pole model histogram is presented. The parameters of the all-pole model are estimated from the second derivative of log model histogram. The main merits are that the model can produce the desired number of peaks in model histogram and the algorithm is efficient in computation. The proposed algorithm can be used for binarisation and multilevel thresholding ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using geometric properties for correspondence-less image alignment

    Publication Year: 1998, Page(s):37 - 41 vol.1
    Cited by:  Papers (9)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (559 KB)

    We describe a framework for image alignment that does not use explicit feature correspondences. We show how certain geometric properties of image contours are related to the parameters of the geometric transformation between the images. For a transformation model, we show how to recover the transformation parameters using simple statistical distributions of geometric properties. The use of these s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Representing 2D digital images through a normalized measure of redundancy

    Publication Year: 1998, Page(s):42 - 46 vol.1
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (120 KB)

    This paper presents a representational model in which spatial information is analyzed by multiple filters, each of which is sensitive to patterns that contain spatial frequencies in a restricted range. The model bases its responses on only those filters sensitive to significant structures in the image. Spatial structures are described at their best scales as given by a novel normalized redundancy ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reconstruction from affine cameras using closure constraints

    Publication Year: 1998, Page(s):47 - 50 vol.1
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (252 KB)

    This paper outlines a new method that makes reconstruction from an image sequence taken by affine cameras. The method is based on the so called closure constraints that link the camera matrices to the different affine quasi-tensors. This method can easily handle missing data and not only points, but also lines and conics are used to constrain the reconstruction. The method works in three steps: 1)... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sketching natural terrain from uncalibrated imagery

    Publication Year: 1998, Page(s):51 - 55 vol.1
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (422 KB)

    We propose a methodology to sketch the 3D geometry of an outdoor scene consisting of natural terrain. The method requires only a pair of uncalibrated images, but it produces a sketch where the order with respect to the dimensions of height above the ground plane and depth are correct. A dense representation is generated as a set of profile lines which overlays the original images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust self-calibration and Euclidean reconstruction via affine approximation

    Publication Year: 1998, Page(s):56 - 58 vol.1
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (180 KB)

    A new approach to self-calibration and Euclidean reconstruction from image sequences is presented. The key idea is to start with the affine camera model as a first approximation to obtain the affine 3D structure. It is then upgraded to an Euclidean structure and finally, refined by applying the full perspective camera model and bundle adjustment. The proposed scheme makes no assumption about the s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new camera projection model and its application in reprojection

    Publication Year: 1998, Page(s):59 - 63 vol.1
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (439 KB)

    We present a new camera projection model, which is intermediate between the affine camera model and the pin hole projection model. It is modeled as a perspective projection of 3D points into an arbitrary plane, followed by an affine transform of these projected points. We observe that the reprojection of a point into a novel image can be achieved uniquely provided that we have located a set of fiv... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Egomotion estimation on a topological space

    Publication Year: 1998, Page(s):64 - 66 vol.1
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (139 KB)

    We present an egomotion estimation method for a monocular observer moving with arbitrary motion. The method is uniquely based on the normal flow field and the estimation problem is defined in a particular topological space-the /spl Lscr/-space-to allow the use of global data for the final estimates. Additionally, robust statistics methods are used for motion model selection, and provide improved r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An intrinsic parameters self-calibration technique for active vision system

    Publication Year: 1998, Page(s):67 - 69 vol.1
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (67 KB)

    This paper presents a new camera intrinsic parameters self-calibration technique for an ordinary active vision system. By controlling a pan-tilt-translation camera platform to do a sequence of specially designed motions, called a camera motion configuration, we rigorously proved that the camera intrinsic parameters can be determined linearly under such two configurations: 1) regulating the camera'... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A model driven 3D image interpretation system applied to person detection in video images

    Publication Year: 1998, Page(s):70 - 73 vol.1
    Cited by:  Papers (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    Detecting persons in images is up to now an unsolved problem in general. We propose an approach which strictly follows the assumption that only objects and parts of these objects can be detected, if their appearance is known in advance. We consider the detection step as a first step towards the recognition process. The latter contains the reasoning about the movements of a person. The appearance o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting persons on changing background

    Publication Year: 1998, Page(s):74 - 76 vol.1
    Cited by:  Papers (10)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (300 KB)

    We need a reliable visual surveillance system that can work under various disturbances, such as changes of lighting and movements of background objects. We propose a method exploiting information over space and time. First, optical flow is computed, and then regions with uniform flow are extracted. The regions are hypothesized as parts of detection targets. Assuming that the targets move in consta... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ghost: a human body part labeling system using silhouettes

    Publication Year: 1998, Page(s):77 - 82 vol.1
    Cited by:  Papers (72)  |  Patents (47)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (774 KB)

    Ghost is a real time system for estimating human body posture and detecting body parts in monochromatic imagery. It constructs a silhouette based body model to determine the location of the body parts while people are in generic postures. It combines hierarchical body pose estimation, a convex hull analysis of the silhouette, and a partial mapping from the body parts to the silhouette segments usi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spotting recognition of head gestures from color image series

    Publication Year: 1998, Page(s):83 - 85 vol.1
    Cited by:  Papers (8)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (206 KB)

    Presents an approach for spotting recognition of human head gestures from color image series. First, we use an algorithm based on a perceptually uniform color system to detect skin color region and hair color region of the face from input images. Then, the 3D pose of the head relative to the camera is estimated by calculating the primary moment and secondary moment of the skin color region and the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast and accurate 3D gesture recognition interface

    Publication Year: 1998, Page(s):86 - 91 vol.1
    Cited by:  Papers (13)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (472 KB)

    A video-based gesture recognition system can serve as a natural and accurate 3D user input device. We describe a two-camera system, that recognizes three gesture classes: two static and one dynamic. For one of these gestures (pointing), the system estimates five parameters of 3D pose: position and pointing direction. The recognition is robust, independent of the user and fast (60 Hz), and the esti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A flexible feature matching for automatic face and facial feature points detection

    Publication Year: 1998, Page(s):92 - 95 vol.1
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (227 KB)

    An automatic face and facial feature points (FFPs) detection system is proposed. A face is represented as a graph where the nodes are placed at facial feature points (FFPs) labeled by their Gabor features and the edges describe their spatial relations. An innovative flexible feature matching is proposed to perform features correspondence between models and the input image. This matching model work... View full abstract»

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