Janusz Konrad | Boston University (original) (raw)

Papers by Janusz Konrad

Research paper thumbnail of Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions

arXiv (Cornell University), Oct 12, 2016

Bookmarks Related papers MentionsView impact

Research paper thumbnail of CNN-Based Indoor Occupant Localization via Active Scene Illumination

Bookmarks Related papers MentionsView impact

Research paper thumbnail of VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition

arXiv (Cornell University), Mar 19, 2018

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Privacy-preserving, indoor occupant localization using a network of single-pixel sensors

We propose an approach to indoor occupant localization using a network of single-pixel, visible-l... more We propose an approach to indoor occupant localization using a network of single-pixel, visible-light sensors. In addition to preserving privacy, our approach vastly reduces data transmission rate and is agnostic to eavesdropping. We develop two purely data-driven localization algorithms and study their performance using a network of 6 such sensors. In one algorithm, we divide the monitored floor area (2.37m×2.72m) into a 3×3 grid of cells and classify location of a single person as belonging to one of the 9 cells using a support vector machine classifier. In the second algorithm, we estimate person's coordinates using support vector regression. In cross-validation tests in public (e.g., conference room) and private (e.g., home) scenarios, we obtain 67-72% correct classification rate for cells and 0.31-0.35m mean absolute distance error within the monitored space. Given the simplicity of sensors and processing, these are encouraging results and can lead to useful applications today.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtraction

IEEE Access, 2021

Bookmarks Related papers MentionsView impact

Research paper thumbnail of A fully-convolutional neural network for background subtraction of unseen videos

arXiv (Cornell University), Jul 26, 2019

Bookmarks Related papers MentionsView impact

Research paper thumbnail of On the Importance of Motion Invertibility in MCTF/DWT Video Coding

Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Arithmetic coding of a lossless contour based representation of label images

Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Estimation of nonlinear transfer curves for conversion of color images to a known color space

Proceedings of International Conference on Image Processing

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Modeling Motion for Spatial Scalability

2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings

Abstract The dramatic proliferation of visual displays, from cell phones, through video iPods, PD... more Abstract The dramatic proliferation of visual displays, from cell phones, through video iPods, PDAs, and notebooks, to high-quality HDTV screens, has raised the demand for a video compression scheme capable of decoding a" once-encoded" video at a range of supported video resolutions and with high quality. A promising solution to this problem has been recently proposed in the form of wavelet video coding based on motion-compensated temporal filtering (MCTF); scalability is naturally supported while efficiency is comparable ...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Crosstalk in automultiscopic 3-D displays: blessing in disguise?

Stereoscopic Displays and Virtual Reality Systems XIV, 2007

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Region-adaptive transform based on a stochastic model

This paper is concerned with linear transforms for arbitrarily-shaped image segments. In contrast... more This paper is concerned with linear transforms for arbitrarily-shaped image segments. In contrast to othertechniques described in the literature, the proposedtransform is based upon a stochastic model of image covariancewithin the considered region. Emerging froma separable stationary Markov model proposed for rectangularregions [7], we derive a non-stationary Markovmodel with natural boundary conditions. We computeits eigentransform, which is the optimum linear transformunder a broad...

Bookmarks Related papers MentionsView impact

[Research paper thumbnail of Video Analytics for Surveillance: Theory and Practice [From the Guest Editors](https://attachments.academia-assets.com/117425718/thumbnails/1.jpg)

IEEE Signal Processing Magazine, 2010

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Subsampling models and anti-alias filters for 3-D automultiscopic displays

IEEE Transactions on Image Processing, 2006

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Special Section on Distributed Camera Networks: Sensing, Processing, Communication, and Implementation

IEEE Transactions on Image Processing, 2010

Bookmarks Related papers MentionsView impact

Research paper thumbnail of POCS reconstruction of stereoscopic views

Proc. Int. Conf. on Augmented, Virtual Environments and 3-Dimensional Imaging, ICAV3D, May 1, 2001

This paper presents an application of POCS (projection onto convex sets) methodology to the recon... more This paper presents an application of POCS (projection onto convex sets) methodology to the reconstruction of intermediate stereoscopic views. The basic problem in such a reconstruction, resulting from disparity compensation, is that of the recovery of a regularly-sampled image from its irregularly-spaced samples. This problem also arises in other image processing and coding applications. The results reported here improve our previous POCS-based reconstruction method by locally adapting the algorithm to the ...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Spatio-Visual Fusion-Based Person Re-Identification for Overhead Fisheye Images

IEEE Access, 2023

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Privacy-Preserving Indoor Localization via Active Scene Illumination

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Supervised People Counting Using An Overhead Fisheye Camera

We propose two supervised methods for people counting using an overhead fisheye camera. As oppose... more We propose two supervised methods for people counting using an overhead fisheye camera. As opposed to standard cameras, fisheye cameras offer a large field of view and, when mounted overhead, reduce occlusions. However, methods developed for standard cameras perform poorly on fisheye images since they do not account for the radial image geometry. Furthermore, no large-scale fisheye-image datasets with radially-aligned bounding box annotations are available for training. We adapt YOLOv3 trained on standard images for people counting in fisheye images. In one method, YOLOv3 is applied to 24 rotated, overlapping windows and the results are post-processed to produce a people count. In another method, YOLOv3 is applied to windows of interest extracted by background subtraction. For evaluation, we collected and annotated an indoor fisheye-image dataset that we make public. Experiments on this dataset show that our methods reduce the people counting MAE of two natural benchmarks by over 60%.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Spatio-Visual Fusion-Based Person Re-Identification for Overhead Fisheye Images

arXiv (Cornell University), Dec 21, 2022

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions

arXiv (Cornell University), Oct 12, 2016

Bookmarks Related papers MentionsView impact

Research paper thumbnail of CNN-Based Indoor Occupant Localization via Active Scene Illumination

Bookmarks Related papers MentionsView impact

Research paper thumbnail of VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition

arXiv (Cornell University), Mar 19, 2018

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Privacy-preserving, indoor occupant localization using a network of single-pixel sensors

We propose an approach to indoor occupant localization using a network of single-pixel, visible-l... more We propose an approach to indoor occupant localization using a network of single-pixel, visible-light sensors. In addition to preserving privacy, our approach vastly reduces data transmission rate and is agnostic to eavesdropping. We develop two purely data-driven localization algorithms and study their performance using a network of 6 such sensors. In one algorithm, we divide the monitored floor area (2.37m×2.72m) into a 3×3 grid of cells and classify location of a single person as belonging to one of the 9 cells using a support vector machine classifier. In the second algorithm, we estimate person's coordinates using support vector regression. In cross-validation tests in public (e.g., conference room) and private (e.g., home) scenarios, we obtain 67-72% correct classification rate for cells and 0.31-0.35m mean absolute distance error within the monitored space. Given the simplicity of sensors and processing, these are encouraging results and can lead to useful applications today.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtraction

IEEE Access, 2021

Bookmarks Related papers MentionsView impact

Research paper thumbnail of A fully-convolutional neural network for background subtraction of unseen videos

arXiv (Cornell University), Jul 26, 2019

Bookmarks Related papers MentionsView impact

Research paper thumbnail of On the Importance of Motion Invertibility in MCTF/DWT Video Coding

Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Arithmetic coding of a lossless contour based representation of label images

Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Estimation of nonlinear transfer curves for conversion of color images to a known color space

Proceedings of International Conference on Image Processing

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Modeling Motion for Spatial Scalability

2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings

Abstract The dramatic proliferation of visual displays, from cell phones, through video iPods, PD... more Abstract The dramatic proliferation of visual displays, from cell phones, through video iPods, PDAs, and notebooks, to high-quality HDTV screens, has raised the demand for a video compression scheme capable of decoding a" once-encoded" video at a range of supported video resolutions and with high quality. A promising solution to this problem has been recently proposed in the form of wavelet video coding based on motion-compensated temporal filtering (MCTF); scalability is naturally supported while efficiency is comparable ...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Crosstalk in automultiscopic 3-D displays: blessing in disguise?

Stereoscopic Displays and Virtual Reality Systems XIV, 2007

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Region-adaptive transform based on a stochastic model

This paper is concerned with linear transforms for arbitrarily-shaped image segments. In contrast... more This paper is concerned with linear transforms for arbitrarily-shaped image segments. In contrast to othertechniques described in the literature, the proposedtransform is based upon a stochastic model of image covariancewithin the considered region. Emerging froma separable stationary Markov model proposed for rectangularregions [7], we derive a non-stationary Markovmodel with natural boundary conditions. We computeits eigentransform, which is the optimum linear transformunder a broad...

Bookmarks Related papers MentionsView impact

[Research paper thumbnail of Video Analytics for Surveillance: Theory and Practice [From the Guest Editors](https://attachments.academia-assets.com/117425718/thumbnails/1.jpg)

IEEE Signal Processing Magazine, 2010

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Subsampling models and anti-alias filters for 3-D automultiscopic displays

IEEE Transactions on Image Processing, 2006

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Special Section on Distributed Camera Networks: Sensing, Processing, Communication, and Implementation

IEEE Transactions on Image Processing, 2010

Bookmarks Related papers MentionsView impact

Research paper thumbnail of POCS reconstruction of stereoscopic views

Proc. Int. Conf. on Augmented, Virtual Environments and 3-Dimensional Imaging, ICAV3D, May 1, 2001

This paper presents an application of POCS (projection onto convex sets) methodology to the recon... more This paper presents an application of POCS (projection onto convex sets) methodology to the reconstruction of intermediate stereoscopic views. The basic problem in such a reconstruction, resulting from disparity compensation, is that of the recovery of a regularly-sampled image from its irregularly-spaced samples. This problem also arises in other image processing and coding applications. The results reported here improve our previous POCS-based reconstruction method by locally adapting the algorithm to the ...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Spatio-Visual Fusion-Based Person Re-Identification for Overhead Fisheye Images

IEEE Access, 2023

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Privacy-Preserving Indoor Localization via Active Scene Illumination

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Supervised People Counting Using An Overhead Fisheye Camera

We propose two supervised methods for people counting using an overhead fisheye camera. As oppose... more We propose two supervised methods for people counting using an overhead fisheye camera. As opposed to standard cameras, fisheye cameras offer a large field of view and, when mounted overhead, reduce occlusions. However, methods developed for standard cameras perform poorly on fisheye images since they do not account for the radial image geometry. Furthermore, no large-scale fisheye-image datasets with radially-aligned bounding box annotations are available for training. We adapt YOLOv3 trained on standard images for people counting in fisheye images. In one method, YOLOv3 is applied to 24 rotated, overlapping windows and the results are post-processed to produce a people count. In another method, YOLOv3 is applied to windows of interest extracted by background subtraction. For evaluation, we collected and annotated an indoor fisheye-image dataset that we make public. Experiments on this dataset show that our methods reduce the people counting MAE of two natural benchmarks by over 60%.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Spatio-Visual Fusion-Based Person Re-Identification for Overhead Fisheye Images

arXiv (Cornell University), Dec 21, 2022

Bookmarks Related papers MentionsView impact