TY - CONF
T1 - Efficiently Determining Silhouette Consistency
T2 - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on
Y1 - 2007
A1 - Li Yi
A1 - Jacobs, David W.
KW - camera;scaled
KW - consistency;image
KW - miscalibrated
KW - orthographic
KW - problem;silhouette
KW - projection;shape-from-silhouette
KW - reconstruction;
AB - Volume intersection is a frequently used technique to solve the Shape-From-Silhouette problem, which constructs a 3D object estimate from a set of silhouettes taken with calibrated cameras. It is natural to develop an efficient algorithm to determine the consistency of a set of silhouettes before performing time-consuming reconstruction, so that inaccurate silhouettes can be omitted. In this paper we first present a fast algorithm to determine the consistency of three silhouettes from known (but arbitrary) viewing directions, assuming the projection is scaled orthographic. The temporal complexity of the algorithm is linear in the number of points of the silhouette boundaries. We further prove that a set of more than three convex silhouettes are consistent if and only if any three of them are consistent. Another possible application of our approach is to determine the miscalibrated cameras in a large camera system. A consistent subset of cameras can be determined on the fly and miscalibrated cameras can also be recalibrated at a coarse scale. Real and synthesized data are used to demonstrate our results.
JA - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on
M3 - 10.1109/CVPR.2007.383161
ER -
TY - CONF
T1 - An algebraic approach to surface reconstruction from gradient fields
T2 - Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on
Y1 - 2005
A1 - Agrawal,A.
A1 - Chellapa, Rama
A1 - Raskar, R.
KW - algebra;
KW - algebraic
KW - approach;
KW - Computer
KW - confinement;
KW - discrete
KW - domain
KW - error
KW - field;
KW - from
KW - gradient
KW - graph
KW - image
KW - integrability;
KW - linear
KW - local
KW - methods;
KW - photometric
KW - reconstruction;
KW - shading;
KW - SHAPE
KW - stereo;
KW - surface
KW - system;
KW - theory;
KW - vision;
AB - Several important problems in computer vision such as shape from shading (SFS) and photometric stereo (PS) require reconstructing a surface from an estimated gradient field, which is usually non-integrable, i.e. have non-zero curl. We propose a purely algebraic approach to enforce integrability in discrete domain. We first show that enforcing integrability can be formulated as solving a single linear system Ax =b over the image. In general, this system is under-determined. We show conditions under which the system can be solved and a method to get to those conditions based on graph theory. The proposed approach is non-iterative, has the important property of local error confinement and can be applied to several problems. Results on SFS and PS demonstrate the applicability of our method.
JA - Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on
VL - 1
M3 - 10.1109/ICCV.2005.31
ER -
TY - CONF
T1 - Moving Object Segmentation and Dynamic Scene Reconstruction Using Two Frames
T2 - Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Y1 - 2005
A1 - Agrawala, Ashok K.
A1 - Chellapa, Rama
KW - 3D
KW - analysis;
KW - constraints;
KW - dynamic
KW - ego-motion
KW - estimation;
KW - flow
KW - image
KW - images;
KW - independent
KW - INTENSITY
KW - least
KW - mean
KW - median
KW - method;
KW - methods;
KW - model;
KW - MOTION
KW - motion;
KW - moving
KW - object
KW - of
KW - parallax
KW - parallax;
KW - parametric
KW - processing;
KW - reconstruction;
KW - scene
KW - segmentation;
KW - signal
KW - squares
KW - squares;
KW - static
KW - structure;
KW - subspace
KW - surface
KW - translational
KW - two-frame
KW - unconstrained
KW - video
JA - Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
VL - 2
M3 - 10.1109/ICASSP.2005.1415502
ER -
TY - CONF
T1 - 3D model refinement using surface-parallax
T2 - Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
Y1 - 2004
A1 - Agrawala, Ashok K.
A1 - Chellapa, Rama
KW - 3D
KW - adaptive
KW - arbitrary
KW - camera
KW - coarse
KW - compensation;
KW - Computer
KW - DEM;
KW - depth
KW - digital
KW - ELEVATION
KW - environments;
KW - epipolar
KW - estimation;
KW - field;
KW - image
KW - incomplete
KW - INTENSITY
KW - map;
KW - model
KW - MOTION
KW - parallax;
KW - plane-parallax
KW - reconstruction;
KW - recovery;
KW - refinement;
KW - sequence;
KW - sequences;
KW - surface
KW - surfaces;
KW - urban
KW - vision;
KW - windowing;
AB - We present an approach to update and refine coarse 3D models of urban environments from a sequence of intensity images using surface parallax. This generalizes the plane-parallax recovery methods to surface-parallax using arbitrary surfaces. A coarse and potentially incomplete depth map of the scene obtained from a digital elevation map (DEM) is used as a reference surface which is refined and updated using this approach. The reference depth map is used to estimate the camera motion and the motion of the 3D points on the reference surface is compensated. The resulting parallax, which is an epipolar field, is estimated using an adaptive windowing technique and used to obtain the refined depth map.
JA - Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
VL - 3
M3 - 10.1109/ICASSP.2004.1326537
ER -
TY - CONF
T1 - A 2D profile reconstruction in a multilayered waveguide structure
T2 - Antennas and Propagation Society International Symposium, 2003. IEEE
Y1 - 2003
A1 - Seydou,F.
A1 - Duraiswami, Ramani
A1 - Seppanen,T.
KW - (mathematics);
KW - 2D
KW - dual
KW - duality
KW - electromagnetic
KW - equations;
KW - inhomogeneous
KW - Maxwell
KW - media;
KW - method;
KW - multilayered
KW - multilayers;
KW - profile
KW - reconstruction;
KW - scattering;
KW - space
KW - structure;
KW - theory;
KW - wave
KW - waveguide
KW - waveguides;
AB - We discuss the problem of finding a profile or its location for a 2D scattering of electromagnetic waves with fixed frequencies in a waveguide multilayered domain. We use the dual space method (DSM) of Colton and Monk. Our goal is to extend our previous work of TE and TM cases to the more complicated case of a waveguide. We emphasize on the frequency range in the reconstruction.
JA - Antennas and Propagation Society International Symposium, 2003. IEEE
VL - 1
M3 - 10.1109/APS.2003.1217513
ER -
TY - CONF
T1 - View synthesis of articulating humans using visual hull
T2 - Multimedia and Expo, 2003. ICME '03. Proceedings. 2003 International Conference on
Y1 - 2003
A1 - Yue,Zhanfeng
A1 - Liang Zhao
A1 - Chellapa, Rama
KW - analysis;
KW - body
KW - convex
KW - gesture
KW - hull;
KW - human
KW - image
KW - image-based
KW - image;
KW - mapping;
KW - MOTION
KW - part
KW - parts;
KW - postures;
KW - recognition;
KW - reconstruction;
KW - segmentation;
KW - silhouette
KW - synthesis;
KW - TEXTURE
KW - texture;
KW - view
KW - virtual
KW - visual
AB - In this paper, we present a method, which combines image-based visual hull and human body part segmentation for overcoming the inability of the visual hull method to reconstruct concave regions. The virtual silhouette image corresponding to the given viewing direction is first produced with image-based visual hull. Human body part localization technique is used to segment the input images and the rendered virtual silhouette image into convex body parts. The body parts in the virtual view are generated separately from the corresponding body parts in the input views and then assembled together. The previously rendered silhouette image is used to locate the corresponding body parts in input views and avoid the unconnected or squeezed regions in the assembled final view. Experiments show that this method can improve the reconstruction of concave regions for human postures and texture mapping.
JA - Multimedia and Expo, 2003. ICME '03. Proceedings. 2003 International Conference on
VL - 1
M3 - 10.1109/ICME.2003.1220961
ER -
TY - CONF
T1 - 3D face reconstruction from video using a generic model
T2 - Multimedia and Expo, 2002. ICME '02. Proceedings. 2002 IEEE International Conference on
Y1 - 2002
A1 - Chowdhury, A.R.
A1 - Chellapa, Rama
A1 - Krishnamurthy, S.
A1 - Vo, T.
KW - 3D
KW - algorithm;
KW - algorithms;
KW - analysis;
KW - Carlo
KW - chain
KW - Computer
KW - Face
KW - from
KW - function;
KW - generic
KW - human
KW - image
KW - Markov
KW - MCMC
KW - methods;
KW - model;
KW - Monte
KW - MOTION
KW - optimisation;
KW - OPTIMIZATION
KW - processes;
KW - processing;
KW - recognition;
KW - reconstruction
KW - reconstruction;
KW - sampling;
KW - sequence;
KW - sequences;
KW - SfM
KW - signal
KW - structure
KW - surveillance;
KW - video
KW - vision;
AB - Reconstructing a 3D model of a human face from a video sequence is an important problem in computer vision, with applications to recognition, surveillance, multimedia etc. However, the quality of 3D reconstructions using structure from motion (SfM) algorithms is often not satisfactory. One common method of overcoming this problem is to use a generic model of a face. Existing work using this approach initializes the reconstruction algorithm with this generic model. The problem with this approach is that the algorithm can converge to a solution very close to this initial value, resulting in a reconstruction which resembles the generic model rather than the particular face in the video which needs to be modeled. We propose a method of 3D reconstruction of a human face from video in which the 3D reconstruction algorithm and the generic model are handled separately. A 3D estimate is obtained purely from the video sequence using SfM algorithms without use of the generic model. The final 3D model is obtained after combining the SfM estimate and the generic model using an energy function that corrects for the errors in the estimate by comparing local regions in the two models. The optimization is done using a Markov chain Monte Carlo (MCMC) sampling strategy. The main advantage of our algorithm over others is that it is able to retain the specific features of the face in the video sequence even when these features are different from those of the generic model. The evolution of the 3D model through the various stages of the algorithm is presented.
JA - Multimedia and Expo, 2002. ICME '02. Proceedings. 2002 IEEE International Conference on
VL - 1
M3 - 10.1109/ICME.2002.1035815
ER -
TY - CONF
T1 - Bayesian structure from motion using inertial information
T2 - Image Processing. 2002. Proceedings. 2002 International Conference on
Y1 - 2002
A1 - Qian,Gang
A1 - Chellapa, Rama
A1 - Qinfen Zheng
KW - 3D
KW - analysis;
KW - Bayes
KW - Bayesian
KW - camera
KW - estimation;
KW - image
KW - images;
KW - importance
KW - inertial
KW - information;
KW - methods;
KW - MOTION
KW - motion;
KW - parameter
KW - processing;
KW - real
KW - reconstruction;
KW - sampling;
KW - scene
KW - sensors;
KW - sequence;
KW - sequences;
KW - sequential
KW - signal
KW - structure-from-motion;
KW - synthetic
KW - systems;
KW - video
AB - A novel approach to Bayesian structure from motion (SfM) using inertial information and sequential importance sampling (SIS) is presented. The inertial information is obtained from camera-mounted inertial sensors and is used in the Bayesian SfM approach as prior knowledge of the camera motion in the sampling algorithm. Experimental results using both synthetic and real images show that, when inertial information is used, more accurate results can be obtained or the same estimation accuracy can be obtained at a lower cost.
JA - Image Processing. 2002. Proceedings. 2002 International Conference on
VL - 3
M3 - 10.1109/ICIP.2002.1038996
ER -
TY - CONF
T1 - The processing of form documents
T2 - Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on
Y1 - 1993
A1 - David Doermann
A1 - Rosenfeld, A.
KW - AUTOMATIC
KW - business
KW - detectors;
KW - document
KW - documents;
KW - extraction;
KW - feature
KW - form
KW - forms;
KW - generation;
KW - generic
KW - handling;
KW - known
KW - markings;
KW - model
KW - modeling;
KW - non-form
KW - optimal
KW - properties;
KW - reconstruction;
KW - set;
KW - specialized
KW - stroke
KW - width
AB - An overview of an approach to the generic modeling and processing of known forms is presented. The system provides a methodology by which models are generated from regions in the document based on their usage. Automatic extraction of an optimal set of features to be used for registration is proposed, and it is shown how specialized detectors can be designed for each feature based on their position, orientation and width properties. Registration of the form with the model is accomplished using probing to establish correspondence. Form components which are corrupted by markings are detected and isolated, the intersections are interpreted and the properties of the non-form markings are used to reconstruct the strokes through the intersections. The feasibility of these ideas is demonstrated through an implementation of key components of the system
JA - Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on
M3 - 10.1109/ICDAR.1993.395687
ER -