Prof. Janusz Konrad Profile

Prof. Janusz Konrad

Professor at Boston Univ

SPIE Involvement:

Author

Publications (27)

Proceedings Article | 22 February 2012 Paper

Automatic 2D-to-3D image conversion using 3D examples from the internet

J. Konrad, G. Brown, M. Wang, P. Ishwar, C. Wu, D. Mukherjee

Proceedings Volume 8288, 82880F (2012) https://doi.org/10.1117/12.910601

KEYWORDS: 3D image processing, Databases, Image filtering, Image fusion, 3D modeling, Video, Associative arrays, Image restoration, 3D video streaming, Cameras

Read Abstract +

The availability of 3D hardware has so far outpaced the production of 3D content. Although to date many methods have been proposed to convert 2D images to 3D stereopairs, the most successful ones involve human operators and, therefore, are time-consuming and costly, while the fully-automatic ones have not yet achieved the same level of quality. This subpar performance is due to the fact that automatic methods usually rely on assumptions about the captured 3D scene that are often violated in practice. In this paper, we explore a radically different approach inspired by our work on saliency detection in images. Instead of relying on a deterministic scene model for the input 2D image, we propose to "learn" the model from a large dictionary of stereopairs, such as YouTube 3D. Our new approach is built upon a key observation and an assumption. The key observation is that among millions of stereopairs available on-line, there likely exist many stereopairs whose 3D content matches that of the 2D input (query). We assume that two stereopairs whose left images are photometrically similar are likely to have similar disparity fields. Our approach first finds a number of on-line stereopairs whose left image is a close photometric match to the 2D query and then extracts depth information from these stereopairs. Since disparities for the selected stereopairs differ due to differences in underlying image content, level of noise, distortions, etc., we combine them by using the median. We apply the resulting median disparity field to the 2D query to obtain the corresponding right image, while handling occlusions and newly-exposed areas in the usual way. We have applied our method in two scenarios. First, we used YouTube 3D videos in search of the most similar frames. Then, we repeated the experiments on a small, but carefully-selected, dictionary of stereopairs closely matching the query. This, to a degree, emulates the results one would expect from the use of an extremely large 3D repository. While far from perfect, the presented results demonstrate that on-line repositories of 3D content can be used for effective 2D-to-3D image conversion. With the continuously increasing amount of 3D data on-line and with the rapidly growing computing power in the cloud, the proposed framework seems a promising alternative to operator-assisted 2D-to-3D conversion.

Proceedings Article | 28 January 2008 Paper

Behavior subtraction

Pierre-Marc Jodoin, Venkatesh Saligrama, Janusz Konrad

Proceedings Volume 6822, 68220B (2008) https://doi.org/10.1117/12.770757

KEYWORDS: Video, Video surveillance, Cameras, Motion detection, Motion models, Detection and tracking algorithms, Surveillance, Visualization, Error analysis, Algorithm development

Read Abstract +

Proceedings Article | 5 March 2007 Paper

Crosstalk in automultiscopic 3-D displays: Blessing in disguise?

Ashish Jain, Janusz Konrad

Proceedings Volume 6490, 649012 (2007) https://doi.org/10.1117/12.707982

KEYWORDS: 3D displays, Multiplexing, Optical filters, Image filtering, Fourier transforms, 3D modeling, Mathematical modeling, 3D image processing, Cameras, LCDs

Read Abstract +

Proceedings Article | 5 March 2007 Paper

Compression of still multiview images for 3-D automultiscopic spatially-multiplexed displays

Ryan Lau, Serdar Ince, Janusz Konrad

Proceedings Volume 6490, 64900O (2007) https://doi.org/10.1117/12.695529

KEYWORDS: Image compression, Multiplexing, 3D displays, Video compression, Receivers, Glasses, Video, Image processing, 3D image processing, Visualization

Read Abstract +

Proceedings Article | 5 March 2007 Paper

Spline-based intermediate view reconstruction

Serdar Ince, Janusz Konrad, Carlos Vázquez

Proceedings Volume 6490, 64900F (2007) https://doi.org/10.1117/12.699372

KEYWORDS: Reconstruction algorithms, Lawrencium, Cameras, Error analysis, Optical flow, 3D modeling, Video, Image restoration, Image quality, Anisotropic diffusion

Read Abstract +

Proceedings Article | 22 March 2005 Paper

Recovery of a missing color component in stereo images (or helping NASA find little green Martians)

Serdar Ince, Janusz Konrad

Proceedings Volume 5664, (2005) https://doi.org/10.1117/12.580752

KEYWORDS: Cameras, Mars, Optical filters, Reconstruction algorithms, Motion estimation, 3D image processing, RGB color model, 3D vision, Algorithm development, Camera shutters

Read Abstract +

Proceedings Article | 14 March 2005 Paper

Importance of motion in motion-compensated temporal discrete wavelet transforms

Janusz Konrad, Nikola Bozinovic

Proceedings Volume 5685, (2005) https://doi.org/10.1117/12.589882

KEYWORDS: Motion estimation, Discrete wavelet transforms, Motion models, Video, Motion measurement, Video coding, Transform theory, Motion analysis, Video compression, Wavelets

Read Abstract +

Proceedings Article | 2 November 2004 Paper

Design of a high-definition imaging (HDI) analysis technique adapted to challenging environments

Sophie Laurent, William Karl, Janusz Konrad, Jody Wilson, Jeffrey Baumgardner, Michael Mendillo

Proceedings Volume 5558, (2004) https://doi.org/10.1117/12.581739

KEYWORDS: Information operations, Mercury, Image quality, Image registration, Space telescopes, Telescopes, Point spread functions, Signal to noise ratio, Atmospheric optics, Adaptive optics

Read Abstract +

Proceedings Article | 21 May 2004 Paper

Non-orthogonal subsampling and anti-alias filtering for multiscopic 3D displays

Janusz Konrad, Philippe Agniel

Proceedings Volume 5291, (2004) https://doi.org/10.1117/12.524079

KEYWORDS: Image filtering, RGB color model, 3D displays, Multiplexing, Digital signal processing, Filtering (signal processing), LCDs, Optimal filtering, 3D image processing, Visualization

Read Abstract +

Proceedings Article | 18 January 2004 Paper

Joint space-time motion-based video segmentation and occlusion detection using multiphase level sets

Mirko Ristivojevic, Janusz Konrad

Proceedings Volume 5308, (2004) https://doi.org/10.1117/12.523975

KEYWORDS: Image segmentation, Motion models, Motion estimation, Video, Motion measurement, 3D modeling, Motion detection, 3D image processing, Image processing, Video compression

Read Abstract +

Proceedings Article | 18 January 2004 Paper

Transversal versus lifting approach to motion-compensated temporal discrete wavelet transform of image sequences: equivalence and tradeoffs

Janusz Konrad

Proceedings Volume 5308, (2004) https://doi.org/10.1117/12.530472

KEYWORDS: Discrete wavelet transforms, Transform theory, Motion models, Image compression, Motion analysis, Affine motion model, Performance modeling, Video compression, Analytical research, Digital filtering

Read Abstract +

Proceedings Article | 18 January 2004 Paper

Multiple motion and occlusion segmentation with a multiphase level set method

Yonggang Shi, Janusz Konrad, William Karl

Proceedings Volume 5308, (2004) https://doi.org/10.1117/12.525144

KEYWORDS: Image segmentation, Video, Motion models, Algorithm development, Image processing algorithms and systems, Binary data, Motion estimation, Motion analysis, Video compression, Image analysis

Read Abstract +

Proceedings Article | 23 June 2003 Paper

Scan order and quantization for 3D-DCT coding

Nikola Bozinovic, Janusz Konrad

Proceedings Volume 5150, (2003) https://doi.org/10.1117/12.503324

KEYWORDS: Quantization, Convolution, Motion estimation, 3D image processing, 3D scanning, Video, 3D modeling, Motion models, Video coding, 3D video compression

Read Abstract +

Proceedings Article | 30 May 2003 Paper

Artifact reduction in lenticular multiscopic 3D displays by means of anti-alias filtering

Janusz Konrad, Philippe Agniel

Proceedings Volume 5006, (2003) https://doi.org/10.1117/12.474153

KEYWORDS: 3D displays, RGB color model, Optical filters, Image filtering, Multiplexing, LCDs, Filtering (signal processing), Visualization, Fourier transforms, Distortion

Read Abstract +

Proceedings Article | 7 May 2003 Paper

Probabilistic video stabilization using Kalman filtering and mosaicing

Andrey Litvin, Janusz Konrad, William Karl

Proceedings Volume 5022, (2003) https://doi.org/10.1117/12.476436

KEYWORDS: Video, Cameras, Motion models, Motion estimation, Affine motion model, Filtering (signal processing), Electronic filtering, Optical filters, Video processing, Digital filtering

Read Abstract +

Proceedings Article | 7 May 2003 Paper

Video segmentation and occlusion detection over multiple frames

Janusz Konrad, Mirko Ristivojevic

Proceedings Volume 5022, (2003) https://doi.org/10.1117/12.476652

KEYWORDS: Image segmentation, Video, Cameras, 3D image processing, Image processing, Motion estimation, Motion models, Surveillance, Video surveillance, 3D modeling

Read Abstract +

Proceedings Article | 7 May 2003 Paper

Recovering large-amplitude disparity fields using adaptive interpolation

Moustapha Kardouchi, Janusz Konrad

Proceedings Volume 5022, (2003) https://doi.org/10.1117/12.476625

KEYWORDS: Feature extraction, Sensors, Video, Optical flow, Affine motion model, Image processing, 3D displays, Glasses, Machine vision, Computer vision technology

Read Abstract +

Proceedings Article | 29 December 2000 Paper

Estimation of large-amplitude motion and disparity fields: application to intermediate view reconstruction

Moustapha Kardouchi, Janusz Konrad, C. Vazquez

Proceedings Volume 4310, (2000) https://doi.org/10.1117/12.411811

KEYWORDS: Cameras, Motion estimation, Sensors, Optical flow, Image processing, Video, 3D modeling, Image quality, Feature extraction, Corner detection

Read Abstract +

This paper describes a method for establishing dense correspondence between two images in a video sequence (motion) or in a stereo pair (disparity) in case of large displacements. In order to deal with large-amplitude motion or disparity fields, multi-resolution techniques such as blocks matching and optical flow have been used in the past. Although quite successful, these techniques cannot easily cope with motion/disparity discontinuities as they do not explicitly exploit image structure. Additionally, their computational complexity is high; block matching requires examination of numerous vector candidates while optical flow-based techniques are iterative. In this paper, we propose a new approach that addresses both issues. The approach combines feature matching with Delaunay triangulation, and thus reliable long-range correspondences result while the computational complexity is not high (sparse representation). In the proposed approach, feature points are found first using a simple intensity corner detector. Then, correspondence pairs between two images are found by maximizing cross-correlation over a small window. Finally, the Delaunay triangulation is applied to the resulting points, and a dense vector field is computed by planar interpolation over Delaunay triangles. The resulting vector field is continuous everywhere, and thus does not reflect motion or depth discontinuities at object boundaries. In order to improve the rendition of such discontinuities, we propose to further divide Delaunay triangles whenever the displacement vectors within a triangle do not allow good intensity match. The approach has been extensively tested on stereoscopic images in the context of intermediate view reconstruction where the quality of estimated disparity fields is critical for final image rendering. The first results are very encouraging as the reconstructed images are of high quality, especially at object boundaries, and the computational complexity is lower than that of multi- resolution block matching.

Proceedings Article | 3 May 2000 Paper

Dense-disparity estimation from feature correspondences

Janusz Konrad, Zhong-Dan Lan

Proceedings Volume 3957, (2000) https://doi.org/10.1117/12.384433

KEYWORDS: Cameras, Optical filters, Image fusion, Image processing, Image compression, 3D image processing, Image filtering, Feature extraction, Image restoration, Visualization

Read Abstract +

Proceedings Article | 19 April 2000 Paper

Multiple motion segmentation with level sets

Abdol-Reza Mansouri, Bounlith Sirivong, Janusz Konrad

Proceedings Volume 3974, (2000) https://doi.org/10.1117/12.382993

KEYWORDS: Image segmentation, Motion estimation, Partial differential equations, Image compression, Video processing, Image processing algorithms and systems, Motion models, Terbium, Feature extraction, Machine vision

Read Abstract +

Proceedings Article | 19 April 2000 Paper

Minimum description length region tracking with level sets

Abdol-Reza Mansouri, Janusz Konrad

Proceedings Volume 3974, (2000) https://doi.org/10.1117/12.382985

KEYWORDS: Detection and tracking algorithms, Partial differential equations, Motion estimation, Video surveillance, Motion models, Cameras, Video, Image segmentation, Affine motion model, Databases

Read Abstract +

Proceedings Article | 24 May 1999 Paper

Enhancement of viewer comfort in stereoscopic viewing: parallax adjustment

Janusz Konrad

Proceedings Volume 3639, (1999) https://doi.org/10.1117/12.349379

KEYWORDS: Cameras, 3D image processing, 3D modeling, Reconstruction algorithms, Algorithm development, Image fusion, Visualization, Eye, Lithium, Signal processing

Read Abstract +

Proceedings Article | 30 April 1998 Paper

Robust quadtree-based disparity estimation for the reconstruction of intermediate stereoscopic images

Anthony Mancini, Janusz Konrad

Proceedings Volume 3295, (1998) https://doi.org/10.1117/12.307193

KEYWORDS: Reconstruction algorithms, Cameras, 3D image processing, Video, Image restoration, 3D modeling, Error analysis, Ions, 3D image reconstruction, Image quality

Read Abstract +

Proceedings Article | 9 January 1998 Paper

Motion-based video segmentation using continuation method and robust cost functions

Cheng-Hong Yang, Janusz Konrad

Proceedings Volume 3309, (1998) https://doi.org/10.1117/12.298389

KEYWORDS: Image segmentation, Motion estimation, Motion models, Video, Ions, Quantization, Data modeling, Tin, Video coding, Image processing

Read Abstract +

Proceedings Article | 9 January 1998 Paper

Block-based winner-takes-all reconstruction of intermediate stereoscopic images

Abdol-Reza Mansouri, Janusz Konrad

Proceedings Volume 3309, (1998) https://doi.org/10.1117/12.298405

KEYWORDS: Cameras, Expectation maximization algorithms, Reconstruction algorithms, Binary data, 3D image processing, 3D modeling, Image processing, Infrared imaging, Nonlinear filtering, Linear filtering

Read Abstract +

Proceedings Article | 21 April 1995 Paper

Motion modeling and estimation for very low bit rate video coding

Janusz Konrad, Abdol-Reza Mansouri, Eric Dubois, Viet-Nam Dang, Jean-Bernard Chartier

Proceedings Volume 2501, (1995) https://doi.org/10.1117/12.206730

KEYWORDS: Motion estimation, Image segmentation, Motion models, Video coding, Image compression, Algorithm development, Low bit rate video, Image fusion, Video, Image processing algorithms and systems

Read Abstract +

Proceedings Article | 17 April 1995 Paper

Motion-compensated interpolation using trajectories with acceleration

Michel Chahine, Janusz Konrad

Proceedings Volume 2419, (1995) https://doi.org/10.1117/12.206354

KEYWORDS: Motion models, Motion estimation, Video coding, Video, Mouth, Image processing, Eye models, Receivers, Error analysis, Low bit rate video

Read Abstract +

Showing 5 of 27 publications

Conference Committee Involvement (25)

Three-Dimensional Imaging, Visualization, and Display 2019

15 April 2019 | Baltimore, MD, United States

Three-Dimensional Imaging, Visualization, and Display 2018

16 April 2018 | Orlando, FL, United States

Three-Dimensional Imaging, Visualization, and Display 2017

10 April 2017 | Anaheim, CA, United States

Three-Dimensional Imaging, Visualization, and Display 2016

18 April 2016 | Baltimore, MD, United States

Three-Dimensional Imaging, Visualization, and Display 2015

20 April 2015 | Baltimore, MD, United States

Visual Information Processing and Communication VI

10 February 2015 | San Francisco, California, United States

Visual Information Processing and Communication V

5 February 2014 | San Francisco, California, United States

Visual Information Processing and Communication IV

6 February 2013 | Burlingame, California, United States

Visual Information Processing and Communication III

24 January 2012 | Burlingame, California, United States

Visual Information Processing and Communication II

25 January 2011 | San Francisco Airport, California, United States

Stereoscopic Displays and Applications XXII

24 January 2011 | San Francisco Airport, California, United States

Visual Information Processing and Communication

19 January 2010 | San Jose, California, United States

Stereoscopic Displays and Applications XXI

18 January 2010 | San Jose, California, United States

Visual Communications and Image Processing 2009

20 January 2009 | San Jose, California, United States

Stereoscopic Displays and Applications XX

19 January 2009 | San Jose, California, United States

Visual Communications and Image Processing 2008

29 January 2008 | San Jose, California, United States

Stereoscopic Displays and Applications XIX

28 January 2008 | San Jose, California, United States

Visual Communications and Image Processing 2007

30 January 2007 | San Jose, CA, United States

Stereoscopic Displays and Applications XVIII

29 January 2007 | San Jose, CA, United States

Visual Communications and Image Processing 2006

17 January 2006 | San Jose, California, United States

Stereoscopic Displays and Applications XVII

16 January 2006 | San Jose, California, United States

Image and Video Communications and Processing 2005

18 January 2005 | San Jose, California, United States

Stereoscopic Displays and Applications XVI

17 January 2005 | San Jose, California, United States

Stereoscopic Displays and Applications XV

19 January 2004 | San Jose, California, United States

Stereoscopic Displays and Applications XIV

21 January 2003 | Santa Clara, CA, United States

Showing 5 of 25 Conference Committees

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years