Results 1  10
of
28
Threedimensional object recognition from single twodimensional images
 Artificial Intelligence
, 1987
"... A computer vision system has been implemented that can recognize threedimensional objects from unknown viewpoints in single grayscale images. Unlike most other approaches, the recognition is accomplished without any attempt to reconstruct depth information bottomup from the visual input. Instead, ..."
Abstract

Cited by 457 (7 self)
 Add to MetaCart
(Show Context)
A computer vision system has been implemented that can recognize threedimensional objects from unknown viewpoints in single grayscale images. Unlike most other approaches, the recognition is accomplished without any attempt to reconstruct depth information bottomup from the visual input. Instead, three other mechanisms are used that can bridge the gap between the twodimensional image and knowledge of threedimensional objects. First, a process of perceptual organization is used to form groupings and structures in the image that are likely to be invariant over a wide range of viewpoints. Second, a probabilistic ranking method is used to reduce the size of the search space during model based matching. Finally, a process of spatial correspondence brings the projections of threedimensional models into direct correspondence with the image by solving for unknown viewpoint and model parameters. A high level of robustness in the presence of occlusion and missing data can be achieved through full application of a viewpoint consistency constraint. It is argued that similar mechanisms and constraints form the basis for recognition in human vision. This paper has been published in Artificial Intelligence, 31, 3 (March 1987), pp. 355–395. 1 1
Fitting Parameterized ThreeDimensional Models to Images
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 1991
"... Modelbased recognition and motion tracking depends upon the ability to solve for projection and model parameters that will best fit a 3D model to matching 2D image features. This paper extends current methods of parameter solving to handle objects with arbitrary curved surfaces and with any nu ..."
Abstract

Cited by 343 (8 self)
 Add to MetaCart
Modelbased recognition and motion tracking depends upon the ability to solve for projection and model parameters that will best fit a 3D model to matching 2D image features. This paper extends current methods of parameter solving to handle objects with arbitrary curved surfaces and with any number of internal parameters representing articulations, variable dimensions, or surface deformations. Numerical
ThroughtheLens Camera Control
, 1992
"... In this paper we introduce throughthelens camera control, a body of techniques that permit a user to manipulate a virtual camera by controlling and constraining features in the image seen through its lens. Rather than solving for camera parameters directly, constrained optimization is used to com ..."
Abstract

Cited by 143 (7 self)
 Add to MetaCart
(Show Context)
In this paper we introduce throughthelens camera control, a body of techniques that permit a user to manipulate a virtual camera by controlling and constraining features in the image seen through its lens. Rather than solving for camera parameters directly, constrained optimization is used to compute their time derivatives based on desired changes in userdefined controls. This effectively permits new controls to be defined independent of the underlying parameterization. The controls can also serve as constraints, maintaining their values as others are changed. We describe the techniques in general and work through a detailed example of a specific camera model. Our implementation demonstrates a gallery of useful controls and constraints and provides some examples of how these may be used in composing images and animations.
Threedimensional shape knowledge for joint image segmentation and pose estimation
 Pattern Recognition, volume 3663 of LNCS
, 2005
"... In this article we present the integration of 3D shape knowledge into a variational model for level set based image segmentation and tracking. Given a 3D surface model of an object that is visible in the image of one or multiple cameras calibrated to the same world coordinate system, the object co ..."
Abstract

Cited by 57 (31 self)
 Add to MetaCart
(Show Context)
In this article we present the integration of 3D shape knowledge into a variational model for level set based image segmentation and tracking. Given a 3D surface model of an object that is visible in the image of one or multiple cameras calibrated to the same world coordinate system, the object contour extracted by the segmentation method is applied to estimate the 3D pose parameters of the object. Viceversa, the surface model projected to the image plane helps in a topdown manner to improve the extraction of the contour. While common alternative segmentation approaches, which integrate 2D shape knowledge, face the problem that an object can look very differently from various viewpoints, a 3D free form model ensures that for each view the model can fit the data in the image very well. Moreover, one additionally solves the higher level problem of determining the object pose in 3D space. Due to the variational formulation, the approach clearly states all model assumptions in a single energy functional that is locally minimized by our method. Its performance is demonstrated by experiments with a monocular and a stereo camera system. 1 1
Optimal Geometric Model Matching Under Full 3D Perspective
, 1994
"... Modelbased object recognition systems have rarely dealt directly with 3D perspective while matching models to images. The algorithms presented here use 3D pose recovery during matching to explicitly and quantitatively account for changes in model appearance associated with 3D perspective. These alg ..."
Abstract

Cited by 34 (15 self)
 Add to MetaCart
Modelbased object recognition systems have rarely dealt directly with 3D perspective while matching models to images. The algorithms presented here use 3D pose recovery during matching to explicitly and quantitatively account for changes in model appearance associated with 3D perspective. These algorithms use randomstart local search to find, with high probability, the globally optimal correspondence between model and image features in spaces containing over 2 100 possible matches. Three specific algorithms are compared on robot landmark recognition problems. A fullperspective algorithm uses the 3D pose algorithm in all stages of search while two hybrid algorithms use a computationally less demanding weakperspective procedure to rank alternative matches and updates 3D pose only when moving to a new match. These hybrids successfully solve problems involving perspective, and in less time than required by the fullperspective algorithm.
Combined Region and Motionbased 3D Tracking of Rigid and Articulated Objects
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
"... In this paper, we propose the combined use of complementary concepts for 3D tracking: region fitting on one side, and dense optical flow as well as tracked SIFT features on the other. Both concepts are chosen such that they can compensate for the shortcomings of each other. While tracking by the ob ..."
Abstract

Cited by 21 (4 self)
 Add to MetaCart
(Show Context)
In this paper, we propose the combined use of complementary concepts for 3D tracking: region fitting on one side, and dense optical flow as well as tracked SIFT features on the other. Both concepts are chosen such that they can compensate for the shortcomings of each other. While tracking by the object region can prevent the accumulation of errors, optical flow and SIFT can handle larger transformations. Whereas segmentation works best in case of homogeneous objects, optical flow computation and SIFT tracking rely on sufficiently structured objects. We show that a sensible combination yields a general tracking system that can be applied in a large variety of scenarios without the need to manually adjust weighting parameters.
Pose estimation in conformal geometric algebra. Part II: Realtime pose estimation using extended feature concepts
 Journal of Mathematical Imaging and Vision
, 2005
"... Abstract. 2D3D pose estimation means to estimate the relative position and orientation of a 3D object with respect to a reference camera system. This work has its main focus on the theoretical foundations of the 2D3D pose estimation problem: We discuss the involved mathematical spaces and their in ..."
Abstract

Cited by 21 (15 self)
 Add to MetaCart
(Show Context)
Abstract. 2D3D pose estimation means to estimate the relative position and orientation of a 3D object with respect to a reference camera system. This work has its main focus on the theoretical foundations of the 2D3D pose estimation problem: We discuss the involved mathematical spaces and their interaction within higher order entities. To cope with the pose problem (how to compare 2D projective image features with 3D Euclidean object features), the principle we propose is to reconstruct image features (e.g. points or lines) to one dimensional higher entities
3d vision techniques for autonomous vehicles
, 1988
"... those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the funding agencies. 4 Contents ..."
Abstract

Cited by 16 (0 self)
 Add to MetaCart
(Show Context)
those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the funding agencies. 4 Contents
A Fully Projective Formulation for Lowe's Tracking Algorithm
, 1996
"... David Lowe's influential and classic algorithm for tracking objects with known geometry is formulated with certain simplifying assumptions. A version implemented by Ishii et al. makes different simplifying assumptions. We formulate a full projective solution and apply the same algorithm (Newto ..."
Abstract

Cited by 15 (4 self)
 Add to MetaCart
David Lowe's influential and classic algorithm for tracking objects with known geometry is formulated with certain simplifying assumptions. A version implemented by Ishii et al. makes different simplifying assumptions. We formulate a full projective solution and apply the same algorithm (Newton's method). We report results of extensive testing of these three algorithms. We compute two imagespace and six posespace error metrics to quantify the effects of object pose, errors in initial solutions, and image noise levels. We consider several scenaria, from relatively unconstrained conditions to those that mirror realworld and real time constraints. The conclusion is that the full projective formulation makes the algorithm orders of magnitude more accurate and gives it superexponential convergence properties with arguably better computationtime properties. This material is based on work supported by the LusoAmerican Foundation, Calouste Gulbenkian Foundation, JNICT, CAPES pro...
Numerical Methods for ModelBased Pose Recovery
 Techn. Rept. 659, Comp. Sci. Dept., The Univ. of
, 1997
"... In this paper we review and compare several techniques for modelbased pose recovery (extrinsic camera calibration) from monocular images. We classify the solutions reported in the literature as analytical perspective, affine and numerical perspective. We also present reformulations for two of the ..."
Abstract

Cited by 13 (1 self)
 Add to MetaCart
(Show Context)
In this paper we review and compare several techniques for modelbased pose recovery (extrinsic camera calibration) from monocular images. We classify the solutions reported in the literature as analytical perspective, affine and numerical perspective. We also present reformulations for two of the most important numerical perspective solutions: Lowe's algorithm and PhongHoraud's algorithm. Our improvement to Lowe's algorithm consists of eliminating some simplifying assumptions on its projective equations. A careful experimental evaluation reveals that the resulting fully projective algorithm has superexponential convergence properties for a wide range of initial solutions and, under realistic usage conditions, it is up to an order of magnitude more accurate than the original formulation, with arguably better computationtime properties. Our extension to PhongHoraud's algorithm is, to the best of our knowledge, the first method for independent orientation recovery that actually ex...