Sorry, you need to enable JavaScript to visit this website.

Image Formation

Domain Agnostic Video Prediction from Motion Selective Kernels


Existing conditional video prediction approaches train a network from large databases and generalise to previously unseen data. We take the opposite stance, and introduce a model that learns from the first frames of a given video and extends its content and motion, to, \eg double its length. To this end, we propose a dual network that can use in a flexible way both dynamic and static convolutional motion kernels, to predict future frames. We demonstrate experimentally the robustness of our approach on challenging videos in-the-wild and show that it is competitive related baselines.

Paper Details

Authors:
Submitted On:
19 September 2019 - 11:54pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

prinet-icip2019-presentation-onlineversion.pdf

(6)

Keywords

Subscribe

[1] , "Domain Agnostic Video Prediction from Motion Selective Kernels", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4756. Accessed: Oct. 17, 2019.
@article{4756-19,
url = {http://sigport.org/4756},
author = { },
publisher = {IEEE SigPort},
title = {Domain Agnostic Video Prediction from Motion Selective Kernels},
year = {2019} }
TY - EJOUR
T1 - Domain Agnostic Video Prediction from Motion Selective Kernels
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4756
ER -
. (2019). Domain Agnostic Video Prediction from Motion Selective Kernels. IEEE SigPort. http://sigport.org/4756
, 2019. Domain Agnostic Video Prediction from Motion Selective Kernels. Available at: http://sigport.org/4756.
. (2019). "Domain Agnostic Video Prediction from Motion Selective Kernels." Web.
1. . Domain Agnostic Video Prediction from Motion Selective Kernels [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4756

Machine-Assisted Annotation of Forensic Imagery


Image collections, if critical aspects of image content are exposed, can spur research and practical applications in many domains. Supervised machine learning may be the only feasible way to annotate very large collections. However, leading approaches rely on large samples of completely and accurately annotated images. In the case of a large forensic collection that we are aiming to annotate, neither the complete annotation nor the large training samples can be feasibly produced. We, therefore, investigate ways to assist manual annotation efforts done by forensic experts.

Paper Details

Authors:
Sara Mousavi, Ramin Nabati, Megan Kleeschulte, Dawnie Steadman, Audris Mockus
Submitted On:
16 September 2019 - 10:28am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

SaraMousaviICIP19Poster.pdf

(11)

Keywords

Additional Categories

Subscribe

[1] Sara Mousavi, Ramin Nabati, Megan Kleeschulte, Dawnie Steadman, Audris Mockus, "Machine-Assisted Annotation of Forensic Imagery", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4641. Accessed: Oct. 17, 2019.
@article{4641-19,
url = {http://sigport.org/4641},
author = {Sara Mousavi; Ramin Nabati; Megan Kleeschulte; Dawnie Steadman; Audris Mockus },
publisher = {IEEE SigPort},
title = {Machine-Assisted Annotation of Forensic Imagery},
year = {2019} }
TY - EJOUR
T1 - Machine-Assisted Annotation of Forensic Imagery
AU - Sara Mousavi; Ramin Nabati; Megan Kleeschulte; Dawnie Steadman; Audris Mockus
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4641
ER -
Sara Mousavi, Ramin Nabati, Megan Kleeschulte, Dawnie Steadman, Audris Mockus. (2019). Machine-Assisted Annotation of Forensic Imagery. IEEE SigPort. http://sigport.org/4641
Sara Mousavi, Ramin Nabati, Megan Kleeschulte, Dawnie Steadman, Audris Mockus, 2019. Machine-Assisted Annotation of Forensic Imagery. Available at: http://sigport.org/4641.
Sara Mousavi, Ramin Nabati, Megan Kleeschulte, Dawnie Steadman, Audris Mockus. (2019). "Machine-Assisted Annotation of Forensic Imagery." Web.
1. Sara Mousavi, Ramin Nabati, Megan Kleeschulte, Dawnie Steadman, Audris Mockus. Machine-Assisted Annotation of Forensic Imagery [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4641

ADAPTIVE BRIGHTNESS LEARNING FOR ACTIVE OBJECT RECOGNITION

Paper Details

Authors:
Chunlei Huo, Chunhong Pan
Submitted On:
7 May 2019 - 9:43pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_final.pdf

(36)

Keywords

Subscribe

[1] Chunlei Huo, Chunhong Pan, "ADAPTIVE BRIGHTNESS LEARNING FOR ACTIVE OBJECT RECOGNITION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3983. Accessed: Oct. 17, 2019.
@article{3983-19,
url = {http://sigport.org/3983},
author = {Chunlei Huo; Chunhong Pan },
publisher = {IEEE SigPort},
title = {ADAPTIVE BRIGHTNESS LEARNING FOR ACTIVE OBJECT RECOGNITION},
year = {2019} }
TY - EJOUR
T1 - ADAPTIVE BRIGHTNESS LEARNING FOR ACTIVE OBJECT RECOGNITION
AU - Chunlei Huo; Chunhong Pan
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3983
ER -
Chunlei Huo, Chunhong Pan. (2019). ADAPTIVE BRIGHTNESS LEARNING FOR ACTIVE OBJECT RECOGNITION. IEEE SigPort. http://sigport.org/3983
Chunlei Huo, Chunhong Pan, 2019. ADAPTIVE BRIGHTNESS LEARNING FOR ACTIVE OBJECT RECOGNITION. Available at: http://sigport.org/3983.
Chunlei Huo, Chunhong Pan. (2019). "ADAPTIVE BRIGHTNESS LEARNING FOR ACTIVE OBJECT RECOGNITION." Web.
1. Chunlei Huo, Chunhong Pan. ADAPTIVE BRIGHTNESS LEARNING FOR ACTIVE OBJECT RECOGNITION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3983

GlobalSIP 2018 Presentation Slide

Paper Details

Authors:
Submitted On:
23 November 2018 - 1:40pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

GlobalSIP2018_DongHyeYe.pptx

(66)

Keywords

Subscribe

[1] , "GlobalSIP 2018 Presentation Slide", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3754. Accessed: Oct. 17, 2019.
@article{3754-18,
url = {http://sigport.org/3754},
author = { },
publisher = {IEEE SigPort},
title = {GlobalSIP 2018 Presentation Slide},
year = {2018} }
TY - EJOUR
T1 - GlobalSIP 2018 Presentation Slide
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3754
ER -
. (2018). GlobalSIP 2018 Presentation Slide. IEEE SigPort. http://sigport.org/3754
, 2018. GlobalSIP 2018 Presentation Slide. Available at: http://sigport.org/3754.
. (2018). "GlobalSIP 2018 Presentation Slide." Web.
1. . GlobalSIP 2018 Presentation Slide [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3754

IMPROVING LIDAR DEPTH RESOLUTION WITH DITHER


Using detector arrays can speed up lidar systems by parallelizing acquisition.
However, current SPAD arrays have time bins longer than
typical laser pulse durations, resulting in measurement errors dominated
by quantization. We propose an optical time-of-flight system
that uses subtractive dither to improve image depth resolution.
Modeling the measurement noise with a generalized Gaussian distribution
further improves estimation error in simulations, although
model mismatch prevents the same advantage for our experimental

Paper Details

Authors:
Joshua Rapp, Robin M. A. Dawson, Vivek K Goyal
Submitted On:
7 October 2018 - 11:39am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster PDF

(89)

Keywords

Subscribe

[1] Joshua Rapp, Robin M. A. Dawson, Vivek K Goyal, "IMPROVING LIDAR DEPTH RESOLUTION WITH DITHER", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3593. Accessed: Oct. 17, 2019.
@article{3593-18,
url = {http://sigport.org/3593},
author = {Joshua Rapp; Robin M. A. Dawson; Vivek K Goyal },
publisher = {IEEE SigPort},
title = {IMPROVING LIDAR DEPTH RESOLUTION WITH DITHER},
year = {2018} }
TY - EJOUR
T1 - IMPROVING LIDAR DEPTH RESOLUTION WITH DITHER
AU - Joshua Rapp; Robin M. A. Dawson; Vivek K Goyal
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3593
ER -
Joshua Rapp, Robin M. A. Dawson, Vivek K Goyal. (2018). IMPROVING LIDAR DEPTH RESOLUTION WITH DITHER. IEEE SigPort. http://sigport.org/3593
Joshua Rapp, Robin M. A. Dawson, Vivek K Goyal, 2018. IMPROVING LIDAR DEPTH RESOLUTION WITH DITHER. Available at: http://sigport.org/3593.
Joshua Rapp, Robin M. A. Dawson, Vivek K Goyal. (2018). "IMPROVING LIDAR DEPTH RESOLUTION WITH DITHER." Web.
1. Joshua Rapp, Robin M. A. Dawson, Vivek K Goyal. IMPROVING LIDAR DEPTH RESOLUTION WITH DITHER [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3593

A MATRIX-FREE RECONSTRUCTION METHOD FOR COMPRESSIVE FOCAL PLANE ARRAY IMAGING


In this study, we propose a novel algorithm for compressive imaging using digital micromirror device (DMD) modulated focal plane array (FPA) data. In this setting, DMD modulates the scene in the image domain by blocking some of the pixels at a higher resolution level. For reconstruction, a regularized optimization problem is solved, whereas reconstruction time is crucial for a practical compressive sensing application.

Paper Details

Authors:
Alper Güngör, Oğuzhan Fatih Kar, Emre Güven
Submitted On:
5 October 2018 - 7:09am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip_poster_v2.pdf

(71)

Keywords

Additional Categories

Subscribe

[1] Alper Güngör, Oğuzhan Fatih Kar, Emre Güven, "A MATRIX-FREE RECONSTRUCTION METHOD FOR COMPRESSIVE FOCAL PLANE ARRAY IMAGING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3533. Accessed: Oct. 17, 2019.
@article{3533-18,
url = {http://sigport.org/3533},
author = {Alper Güngör; Oğuzhan Fatih Kar; Emre Güven },
publisher = {IEEE SigPort},
title = {A MATRIX-FREE RECONSTRUCTION METHOD FOR COMPRESSIVE FOCAL PLANE ARRAY IMAGING},
year = {2018} }
TY - EJOUR
T1 - A MATRIX-FREE RECONSTRUCTION METHOD FOR COMPRESSIVE FOCAL PLANE ARRAY IMAGING
AU - Alper Güngör; Oğuzhan Fatih Kar; Emre Güven
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3533
ER -
Alper Güngör, Oğuzhan Fatih Kar, Emre Güven. (2018). A MATRIX-FREE RECONSTRUCTION METHOD FOR COMPRESSIVE FOCAL PLANE ARRAY IMAGING. IEEE SigPort. http://sigport.org/3533
Alper Güngör, Oğuzhan Fatih Kar, Emre Güven, 2018. A MATRIX-FREE RECONSTRUCTION METHOD FOR COMPRESSIVE FOCAL PLANE ARRAY IMAGING. Available at: http://sigport.org/3533.
Alper Güngör, Oğuzhan Fatih Kar, Emre Güven. (2018). "A MATRIX-FREE RECONSTRUCTION METHOD FOR COMPRESSIVE FOCAL PLANE ARRAY IMAGING." Web.
1. Alper Güngör, Oğuzhan Fatih Kar, Emre Güven. A MATRIX-FREE RECONSTRUCTION METHOD FOR COMPRESSIVE FOCAL PLANE ARRAY IMAGING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3533

MULTI-EXPOSURE FUSION WITH CNN FEATURES

Paper Details

Authors:
Hui Li
Submitted On:
5 October 2018 - 3:06am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster of paper 2448

(85)

Keywords

Subscribe

[1] Hui Li, "MULTI-EXPOSURE FUSION WITH CNN FEATURES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3508. Accessed: Oct. 17, 2019.
@article{3508-18,
url = {http://sigport.org/3508},
author = {Hui Li },
publisher = {IEEE SigPort},
title = {MULTI-EXPOSURE FUSION WITH CNN FEATURES},
year = {2018} }
TY - EJOUR
T1 - MULTI-EXPOSURE FUSION WITH CNN FEATURES
AU - Hui Li
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3508
ER -
Hui Li. (2018). MULTI-EXPOSURE FUSION WITH CNN FEATURES. IEEE SigPort. http://sigport.org/3508
Hui Li, 2018. MULTI-EXPOSURE FUSION WITH CNN FEATURES. Available at: http://sigport.org/3508.
Hui Li. (2018). "MULTI-EXPOSURE FUSION WITH CNN FEATURES." Web.
1. Hui Li. MULTI-EXPOSURE FUSION WITH CNN FEATURES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3508

ROBUST AND EFFECTIVE HYPERSPECTRAL PANSHARPENING USING SPATIO-SPECTRAL TOTAL VARIATION


Acquiring high-resolution hyperspectral (HS) images is a very challenging task. To this end, hyperspectral pansharpening techniques have been widely studied, which estimate an HS image of high spatial and spectral resolution (high HS image) from a pair of an HS image of high spectral resolution but low spatial resolution (low HS image) and a high spatial resolution panchromatic (PAN) image.

Paper Details

Authors:
Shunsuke Ono, Itsuo Kumazawa
Submitted On:
24 April 2018 - 3:30am
Short Link:
Type:
Event:

Document Files

ICASSP2018_poster.pdf

(116)

Keywords

Subscribe

[1] Shunsuke Ono, Itsuo Kumazawa, "ROBUST AND EFFECTIVE HYPERSPECTRAL PANSHARPENING USING SPATIO-SPECTRAL TOTAL VARIATION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3159. Accessed: Oct. 17, 2019.
@article{3159-18,
url = {http://sigport.org/3159},
author = {Shunsuke Ono; Itsuo Kumazawa },
publisher = {IEEE SigPort},
title = {ROBUST AND EFFECTIVE HYPERSPECTRAL PANSHARPENING USING SPATIO-SPECTRAL TOTAL VARIATION},
year = {2018} }
TY - EJOUR
T1 - ROBUST AND EFFECTIVE HYPERSPECTRAL PANSHARPENING USING SPATIO-SPECTRAL TOTAL VARIATION
AU - Shunsuke Ono; Itsuo Kumazawa
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3159
ER -
Shunsuke Ono, Itsuo Kumazawa. (2018). ROBUST AND EFFECTIVE HYPERSPECTRAL PANSHARPENING USING SPATIO-SPECTRAL TOTAL VARIATION. IEEE SigPort. http://sigport.org/3159
Shunsuke Ono, Itsuo Kumazawa, 2018. ROBUST AND EFFECTIVE HYPERSPECTRAL PANSHARPENING USING SPATIO-SPECTRAL TOTAL VARIATION. Available at: http://sigport.org/3159.
Shunsuke Ono, Itsuo Kumazawa. (2018). "ROBUST AND EFFECTIVE HYPERSPECTRAL PANSHARPENING USING SPATIO-SPECTRAL TOTAL VARIATION." Web.
1. Shunsuke Ono, Itsuo Kumazawa. ROBUST AND EFFECTIVE HYPERSPECTRAL PANSHARPENING USING SPATIO-SPECTRAL TOTAL VARIATION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3159

Optimal Stopping Times for Estimating Bernoulli Parameters with Applications to Active Imaging


We address the problem of estimating the parameter of a Bernoulli process. This arises in many applications, including photon-efficient active imaging where each illumination period is regarded as a single Bernoulli trial. We introduce a framework within which to minimize the mean-squared error (MSE) subject to an upper bound on the mean number of trials. This optimization has several simple and intuitive properties when the Bernoulli parameter has a beta prior.

Paper Details

Authors:
John Murray-Bruce, Vivek K Goyal
Submitted On:
18 July 2018 - 1:20pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP 2018 Poster

(156)

Keywords

Subscribe

[1] John Murray-Bruce, Vivek K Goyal, "Optimal Stopping Times for Estimating Bernoulli Parameters with Applications to Active Imaging", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3084. Accessed: Oct. 17, 2019.
@article{3084-18,
url = {http://sigport.org/3084},
author = {John Murray-Bruce; Vivek K Goyal },
publisher = {IEEE SigPort},
title = {Optimal Stopping Times for Estimating Bernoulli Parameters with Applications to Active Imaging},
year = {2018} }
TY - EJOUR
T1 - Optimal Stopping Times for Estimating Bernoulli Parameters with Applications to Active Imaging
AU - John Murray-Bruce; Vivek K Goyal
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3084
ER -
John Murray-Bruce, Vivek K Goyal. (2018). Optimal Stopping Times for Estimating Bernoulli Parameters with Applications to Active Imaging. IEEE SigPort. http://sigport.org/3084
John Murray-Bruce, Vivek K Goyal, 2018. Optimal Stopping Times for Estimating Bernoulli Parameters with Applications to Active Imaging. Available at: http://sigport.org/3084.
John Murray-Bruce, Vivek K Goyal. (2018). "Optimal Stopping Times for Estimating Bernoulli Parameters with Applications to Active Imaging." Web.
1. John Murray-Bruce, Vivek K Goyal. Optimal Stopping Times for Estimating Bernoulli Parameters with Applications to Active Imaging [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3084

Optimal Spectrum Estimation and System Trade-Off in Long-Distance Frequency-Modulated Continuous-Wave LIDAR


Frequency-modulated continuous-wave (FMCW) LIDAR is a promising technology for next-generation integrated 3D imaging systems. However, it has been considered difficult to apply FMCW LIDAR for long-distance (>100m) targets, such as those in automotive and airborne applications. Maintaining coherence between the reflected beam from the target and locally forwarded beam becomes a significant challenge for tunable laser design.

Paper Details

Authors:
Pavan Bhargava, Vladimir Stojanovic
Submitted On:
14 April 2018 - 11:27pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp2018_fmcw_poster.pdf

(220)

Keywords

Subscribe

[1] Pavan Bhargava, Vladimir Stojanovic, "Optimal Spectrum Estimation and System Trade-Off in Long-Distance Frequency-Modulated Continuous-Wave LIDAR", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2872. Accessed: Oct. 17, 2019.
@article{2872-18,
url = {http://sigport.org/2872},
author = {Pavan Bhargava; Vladimir Stojanovic },
publisher = {IEEE SigPort},
title = {Optimal Spectrum Estimation and System Trade-Off in Long-Distance Frequency-Modulated Continuous-Wave LIDAR},
year = {2018} }
TY - EJOUR
T1 - Optimal Spectrum Estimation and System Trade-Off in Long-Distance Frequency-Modulated Continuous-Wave LIDAR
AU - Pavan Bhargava; Vladimir Stojanovic
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2872
ER -
Pavan Bhargava, Vladimir Stojanovic. (2018). Optimal Spectrum Estimation and System Trade-Off in Long-Distance Frequency-Modulated Continuous-Wave LIDAR. IEEE SigPort. http://sigport.org/2872
Pavan Bhargava, Vladimir Stojanovic, 2018. Optimal Spectrum Estimation and System Trade-Off in Long-Distance Frequency-Modulated Continuous-Wave LIDAR. Available at: http://sigport.org/2872.
Pavan Bhargava, Vladimir Stojanovic. (2018). "Optimal Spectrum Estimation and System Trade-Off in Long-Distance Frequency-Modulated Continuous-Wave LIDAR." Web.
1. Pavan Bhargava, Vladimir Stojanovic. Optimal Spectrum Estimation and System Trade-Off in Long-Distance Frequency-Modulated Continuous-Wave LIDAR [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2872

Pages