prof.irfanessa.com

Presentation at Google I/0 2013 by Matthias Grundmann, John Gregg, and Vivek Kwatra on our Video Stabilizer on YouTube

Video stabilization is a key component of YouTubes video enhancement tools and youtube.com/editor. All YouTube uploads are automatically detected for shakiness and suggested stabilization if needed. This talk will describe the technical details behind our fully automatic one-click stabilization technology, including aspects such as camera path optimization, rolling shutter detection and removal, distributed computing for real-time previews, and camera shake detection. More info: http://googleresearch.blogspot.com/2012/05/video-stabilization-on-youtube.html

via Secrets of Video Stabilization on YouTube — Google I/O 2013.

The Computation + Journalism Symposium 2013, held Jan 31 – Feb 1, 2013, at Georgia Institute of Technology, Atlanta, GA, USA was a huge success. Please see the videos here of all the sessions. See me discuss computational journalism with Phil Meyer, and my slides and take-away points from the closing session.

Irfan Essa
Georgia Tech
School of Interactive Computing
GVU and RIM @ GT Centers

October 19, 2012, 3:30 PM, NSH 1305

Abstract

In this talk, I will discuss a variety of approaches my group is working on for video analysis and enhancement. In particular, I will describe our approach for a video stabilizer, currently implemented and running on YouTube, and its extensions.

This method generates stabilized videos by employing L1-optimal camera paths to remove undesirable motions [1]. We compute camera paths that are optimally partitioned into constant, linear and parabolic segments mimicking the camera motions employed by professional cinematographers. We propose a linear programming framework to minimize the first, second, and third derivatives of the resulting camera path. Our method allows for video stabilization beyond the conventional filtering that only suppresses high frequency jitter. An additional challenge in videos shot from mobile phones are rolling shutter distortions. Modern CMOS cameras capture the frame one scan-line at a time, which results in non-rigid image distortions such as shear and wobble. I will demonstrate a solution based on a novel mixture model of homographies parametrized by scan-line blocks to correct these rolling shutter distortions [2]. Our method does not rely on a-priori knowledge of the readout time nor requires prior camera calibration. A thorough evaluation based on a user study and direct comparisons to other approaches, demonstrates a general preference for our algorithm.

I will conclude the talk by showcasing a live demo of the stabilizer. This work is in collaboration with Matthias Grundmann and Vivek Kwatra at Google, and appears in following two papers.

Time permitting, I will discuss some other projects we are working on, including video segmentation and retargetting.

[1] Matthias Grundmann, Vivek Kwatra, Irfan Essa, CVPR 2011, www.cc.gatech.edu/cpl/projects/videostabilization

[2] Matthias Grundmann, Vivek Kwatra, Daniel Castro Irfan Essa, ICCP 2012, Best paper, www.cc.gatech.edu/cpl/projects/rollingshutter

Host: Takeo Kanade

via Robotics Institute: Talks and Seminars.

Video Enhancement and Analysis: From Content Analysis to Video Stabilization for YouTube

Irfan Essa
Georgia Institute of Technology

October 14, 2012 15:00 – 16:00, Huxely Room. South Kensington Campus, Imperial College, London

Abstract

The talk will describe a variety of efforts undertaken on analysis of  video to enhancement and synthesis of video. An overview of the past work on representing and analyzing videos as a stochastic process and use of this in a form of Video Textures will be provided.  Majority of the talk will then focus on the recent effort which resulted in a widely-used video stabilizer currently implemented on YouTube and its extensions. This method generates stabilized videos by employing L1-optimal camera paths to remove undesirable motions. We compute camera paths that are optimally partitioned into constant, linear and parabolic segments mimicking the camera motions employed by professional cinematographers. To this end, we propose a linear programming framework to minimize the first, second, and third derivatives of the resulting camera path. Our method allows for video stabilization beyond the conventional filtering that only suppresses high frequency jitter. An additional challenge in videos shot from mobile phones are rolling shutter distortions.  We demonstrate a solution based on a novel mixture model of homographies parametrized by scanline blocks to correct these rolling shutter distortions. Our method does not rely on a-priori knowledge of the readout time nor requires prior camera calibration.  This work is in collaboration with Matthias Grundmann and Vivek Kwatra at Google.

Via Distinguished Seminar Series in Computer Science Irfan Essa – GA Tech.

Wednesday September 19, 2012, 7:00pm in the Hill Auditorium, High Museum, Altanta.

In this sixth installment of Lumière’s Fall Lecture Series, Shannon Perich, curator of the photographic history collection at the National Museum of American History, Smithsonian Institution, and Irfan Essa of the Georgia Institute of Technology will each speak to the future of art in a rapidly expanding digital culture. Their commentary will be followed by a panel discussion with audience participation. The panel will address the threats and opportunities created by a growing range of capabilities to create, distribute, and interact with art. Additional information is available at www.lumieregallery.net.This lecture is a collaborative event with the Atlanta Celebrates Photography 2012 Festival.

via Lumière’s Fall Lecture and Panel Discussion.

SLIDES now available here

At ACM sponsored, 14th International Conference on Ubiquitous Computing (Ubicomp 2012), Pittsburgh, PA, September 5 – 7, 2012.

Here are the highlights of my group’s participation in Ubicomp 2012.

• E. Thomaz, V. Bettadapura, G. Reyes, M. Sandesh, G. Schindler, T. Ploetz, G. D. Abowd, and I. Essa (2012), “Recognizing Water-Based Activities in the Home Through Infrastructure-Mediated Sensing,” in Proceedings of ACM International Conference on Ubiquitous Computing (UBICOMP), 2012. [PDF] [WEBSITE] (Oral Presentation at 2pm on Wednesday September 5, 2012).
• J. Wang, G. Schindler, and I. Essa (2012), “Orientation Aware Scene Understanding for Mobile Camera,” in Proceedings of ACM International Conference on Ubiquitous Computing (UBICOMP), 2012. [PDF[WEBSITE] (Oral Presentation at 2pm on Thursday September 6, 2012).

In addition, my colleague, Gregory Abowd has a position paper on “What next, Ubicomp? Celebrating an intellectual disappearing act” on Wednesday 11:15am session and my other colleague/collaborator Thomas Ploetz has a paper on “Automatic Assessment of Problem Behavior in Individuals with Developmental Disabilities” with his co-authors Nils Hammerla, Agata Rozga, Andrea Reavis, Nathan Call, Gregory Abowd on Friday September 6, in the 9:15am session.

Video Stabilization and Rolling Shutter Removal on YouTube

Abstract

In this talk, I will over a variety of approaches my group is working on for video analysis and enhancement. In particular, I will describe our approach for a video stabilizer (currently implemented on YouTube) and its extensions. This work is in collaboration with Matthias Grundmann and Vivek Kwatra at Google. This method generates stabilized videos by employing L1-optimal camera paths to remove undesirable motions [1]. We compute camera paths that are optimally partitioned into constant, linear and parabolic segments mimicking the camera motions employed by professional cinematographers. To this end, we propose a linear programming framework to minimize the first, second, and third derivatives of the resulting camera path. Our method allows for video stabilization beyond the conventional filtering that only suppresses high frequency jitter. An additional challenge in videos shot from mobile phones are rolling shutter distortions. Modern CMOS cameras capture the frame one scanline at a time, which results in non-rigid image distortions such as shear and wobble. I will demonstrate a solution based on a novel mixture model of homographies parametrized by scanline blocks to correct these rolling shutter distortions [2]. Our method does not rely on a-priori knowledge of the readout time nor requires prior camera calibration. A thorough evaluation based on a user study demonstrates a general preference for our algorithm.

I will conclude the talk by showcasing a live demo of the stabilizer and time permitting, I will discuss some other projects we are working on.

[1] Matthias Grundmann, Vivek Kwatra, Irfan Essa, CVPR 2011, www.cc.gatech.edu/cpl/projects/videostabilization

[2] Matthias Grundmann, Vivek Kwatra, Daniel Castro Irfan Essa, ICCP 2012, Best paper, www.cc.gatech.edu/cpl/projects/rollingshutter

At IEEE CVPR 2012 is in Providence RI, from Jun 16 – 21, 2012.

Busy week ahead meeting good friends and colleagues. Here are some highlights of what my group is involved with.

Paper in Main Conference

• K. Kim, D. Lee, and I. Essa (2012), “Detecting Regions of Interest in Dynamic Scenes with Camera Motions,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012. [PDF] [WEBSITE] [VIDEO] [Poster on Tuesday 6/19/2012]

Demo in Main Conference

• M. Grundmann, V. Kwatra, D. Castro, and I. Essa (2012), “Calibration-Free Rolling Shutter Removal,” in [WEBSITE] [VIDEO] (Paper in ICCP 2012) [Demo on Monday and Tuesday (6/18-19) at the Google Booth]

Invited Talk in Workshop

• Irfan Essa, Invited Talk in CVPR Workshop 2012: Large-Scale Video Search and Mining on Thursday 6/21/2012

Videos Understanding: Extracting Content and Context from Video.

(Presentation at the International Workshop on Computer Vision 2012, Ortigia, Siracusa, Sicily, May 22-24, 2012.)

Irfan Essa
GEORGIA Tech

Abstract

In this talk, I will describe various efforts aimed at extracting context and content from video. I will highlight some of our recent work in extracting spatio-temporal features and the related saliency information from the video, which can be used to detect and localize regions of interest in video. Then I will describe approaches that use structured and unstructured representations to recognize the complex and extended-time actions.  I will also discuss the need for unsupervised activity discovery, and detection of anomalous activities from videos. I will show a variety of examples, which will include online videos, mobile videos, surveillance and home monitoring video, and sports videos. Finally, I will pose a series of questions and make observations about how we need to extend our current paradigms of video understanding to go beyond local spatio-temporal features, and standard time-series and bag of words models.