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.

I am here in Barcelona for my 4th summer, participating in the Georgia Tech, College of Computing’s International Study Abroad Programs in Barcelona, ESP. Teaching two classes and spending time with 64 student participants, 4 teaching assistants, and 6 faculty from GA Tech.  Spending time with Faculty at Facultat d’Informàtica de Barcelona – UPC, our hosts here in Barcelona.

• CS 4464: Computational Journalism: This class is aimed at understanding the computational and technological advancements in the area of journalism. Primary focus is on the study of technologies for developing new tools for (a) sense-making from diverse news information sources, (b) the impact of more and cheaper networked sensors (c) collaborative human models for information aggregation and sense-making, (d) mashups and the use of programming in journalism, (e) the impact of mobile computing and data gathering, (f) computational approaches to information quality, (g) data mining for personalization and aggregation, and (h) citizen journalism. 
• CS 4475: Computational Photography: This class explores perceptual and technical aspects of pictures, and more precisely the capture and depiction of reality on a 2D medium. The scientific, perceptual, and artistic principles behind image-making will be emphasized. Topics include the relationship between pictorial techniques and the human visual system; intrinsic limitations of 2D representations and their possible compensations; and technical issues involving depiction. Technical aspects of image capture and rendering, and exploration of how such a medium can be used to its maximum potential, will be examined. Material from recent coursera offering of Computational Photography will be leveraged this class.

The Computational Photography MOOC offering in Coursera came to a close with the following final announcement (abridged here) on May 7, 2013.

Computational photographers:

Thanks for joining us for an engaging 5 weeks of collaboratively learning the wonderful aspects of computational photography. We bid you all farewell now and hope to see some of you in a future reincarnation of this class, building on the feedback provided by many of you. Keep a lookout for the repeat of the same class, and for another class continuing to more advanced topics.

Final graded scores, and the the certificate of completion will be made available this week. All assignment solutions are available, as requested. We will also keep the class site open for a while.

Do remember that we still welcome your feedback, so use the forums. If you haven’t done so already, please do spend a few minutes to fill out the survey for the last week of class, which is part of a survey we are conducting to understand and evaluate online classes offerings like this one.

Again, thanks for participating, and good luck with your future endeavors. And remember to take good pictures, and to have fun computing with photographs.

via Announcements | Computational Photography.

We are live!

Welcome to the course website!

As you take a look around, there are a few things we want to bring to your attention:

1. Do note that while this is an introductory class, we do require that you have working knowledge of college level mathematics, which includes concepts like Linear Algebra and Calculus. In addition, the programming assignments will require access to a computer with Python and OpenCV. Instructions for installing this software are available here, which is also linked in the navigation bar of the site. The responsibility to get your computer system working with this software is entirely yours. The diverse nature of computer platforms and softwares do offer challenges in setting up such systems and we encourage folks to use the forums to help each other with challenges faced.Please get started with the software installation as soon as possible!

2. These online courses are still rather mysterious, we want to learn as much as we can about them What works? What doesnt?. Accordingly, we invite you to participate in occasional surveys that are part of the research study. The surveys will tell us about you, and how the course is working for you. The information you provide will help us make the course better and improve our ability to provide more intellectually engaging content. Participation in the surveys is completely optional and will not affect your grade in the course in any way. For your reference, here is a link to a PDF document Consent Form that describes the surveys and study in more detail.If you would like to participate, begin by filling out the background survey here. Also, keep an eye on the syllabus page and the weekly announcements for end-of-week surveys.

3. The syllabus page will be updated every week to reflect all of the course content as it becomes available. Please consult that page if you are unsure about what to do next. The page also contains useful information about class logistics, policies, and frequently asked questions.

4. Note that the lecture videos page contains links to the subtitles, slides, and video file downloads for each of the lecture videos.Thank you for your attention, and I hope you will have fun in the following few weeks!

-Denis

via Announcements | Computational Photography.

Title: Computational Video: Post-processing Methods for Stabilization, Retargeting and Segmentation

Matthias Grundmann
School of Interactive Computing
College of Computing
Georgia Institute of Technology

Date: February 04, 2013 (Monday)
Time: 3:00p – 6:00p EST
Location: Nano building, 116-118

Abstract:

In this thesis, we address a variety of challenges for analysis and enhancement of Computational Video. We present novel post-processing methods to bridge the difference between professional and casually shot videos mostly seen on online sites. Our research presents solutions to three well-defined problems: (1) Video stabilization and rolling shutter removal in casually-shot, uncalibrated videos; (2) Content-aware video retargeting; and (3) spatio-temporal video segmentation to enable efficient video annotation. We showcase several real-world applications building on these techniques.

We start by proposing a novel algorithm for video stabilization that 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 achieve this, 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 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. We propose 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. Our novel video stabilization and calibration free rolling shutter removal have been deployed on YouTube where they have successfully stabilized millions of videos. We also discuss several extensions to the stabilization algorithm and present technical details behind the widely used YouTube Video Stabilizer.

We address the challenge of changing the aspect ratio of videos, by proposing algorithms that retarget videos to fit the form factor of a given device without stretching or letter-boxing. Our approaches use all of the screen’s pixels, while striving to deliver as much video-content of the original as possible. First, we introduce a new algorithm that uses discontinuous seam-carving in both space and time for resizing videos. Our algorithm relies on a novel appearance-based temporal coherence formulation that allows for frame-by-frame processing and results in temporally discontinuous seams, as opposed to geometrically smooth and continuous seams. Second, we present a technique, that builds on the above mentioned video stabilization approach. We effectively automate classical pan and scan techniques by smoothly guiding a virtual crop window via saliency constraints.

Finally, we introduce an efficient and scalable technique for spatio-temporal segmentation of long video sequences using a hierarchical graph-based algorithm. We begin by over-segmenting a volumetric video graph into space-time regions grouped by appearance. We then construct a “region graph” over the obtained  segmentation and iteratively repeat this process over multiple levels to create a tree of spatio-temporal segmentations. This hierarchical approach generates high quality segmentations, and allows subsequent applications to choose from varying levels of granularity. We demonstrate the use of spatio-temporal segmentation as users interact with the video, enabling efficient annotation of objects within the video.

Committee:

• Dr. Irfan Essa (Advisor, School of Interactive Computing, Georgia Tech)
• Dr. Jim Rehg (School of Interactive Computing, Georgia Tech)
• Dr. Frank Dellaert (School of Interactive Computing, Georgia Tech)
• Dr. Michael Black (Perceiving Systems Department, Max Planck Institute for Intelligent Systems)
• Dr. Sing Bing Kang (Adjunct Faculty, Georgia Tech; Microsoft Research, Microsoft Corp.)
• Dr. Vivek Kwatra (Google Research, Google Inc.)

Join us for the 2nd Computation + Journalism Symposium 2013 in Atlanta, GA on Jan 31 – Feb 1, 2013

What role does computation have in the practice of journalism today and in the near future? As computer-driven forces like automation and aggregation increasingly alter the role of journalists and journalism in society, how can computation become a force of deliberate, positive social impact in journalism and civic life? Five years after the first Computation and Journalism symposium at Georgia Tech, this event brings together leaders in both journalism and computation to discuss and debate current trends and future opportunities.

Join us for the second Symposium on Computation + Journalism to be held at the Georgia Institute of Technology in Atlanta on Jan 31, – Feb 1, 2012. Visit this site for additional details.

Georgia Tech Alumna Named Rhodes Scholar | College of Computing.

Georgia Tech alumna Joy Buolamwini has been named a Rhodes scholar. She will attend the University of Oxford, where she plans to pursue degrees in African studies and global governance and diplomacy.

A 2012 computer science graduate from Memphis, Tenn., Buolamwini plans to use her skills to lower barriers in communication with the goal of increasing commerce, keeping governments accountable and improving the quality of life for millions of people.

“My mission is to show compassion through computation,” Buolamwini said. “The heart of computing is humanity, and as a Rhodes scholar, I will have an unprecedented opportunity to gain a deeper understanding of developing nations and global governance while connecting with world leaders who are committed to fighting the world’s fight – making sure each individual can reach her human potential.”

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.

Weakly Supervised Learning of Object Segmentations from Web-Scale Videos

• G. Hartmann, M. Grundmann, J. Hoffman, D. Tsai, V. Kwatra, O. Madani, S. Vijayanarasimhan, I. Essa, J. Rehg, and R. Sukthankar (2012), “Weakly Supervised Learning of Object Segmentations from Web-Scale Videos,” in Proceedings of ECCV 2012 Workshop on Web-scale Vision and Social Media, 2012. [PDF] [BIBTEX]

  @inproceedings{2012-Hartmann-WSLOSFWV,
    Author = {Glenn Hartmann and Matthias Grundmann and Judy Hoffman and David Tsai and Vivek Kwatra and Omid Madani and Sudheendra Vijayanarasimhan and Irfan Essa and James Rehg and Rahul Sukthankar},
    Booktitle = {Proceedings of ECCV 2012 Workshop on Web-scale Vision and Social Media},
    Date-Added = {2012-10-23 15:03:18 +0000},
    Date-Modified = {2012-10-23 15:07:04 +0000},
    Pdf = {http://www.cs.cmu.edu/~rahuls/pub/eccv2012wk-cp-rahuls.pdf},
    Title = {Weakly Supervised Learning of Object Segmentations from Web-Scale Videos},
    Year = {2012}}

Abstract

We propose to learn pixel-level segmentations of objects from weakly labeled (tagged) internet videos. Specically, given a large collection of raw YouTube content, along with potentially noisy tags, our goal is to automatically generate spatiotemporal masks for each object, such as dog”, without employing any pre-trained object detectors. We formulate this problem as learning weakly supervised classiers for a set of independent spatio-temporal segments. The object seeds obtained using segment-level classiers are further rened using graphcuts to generate high-precision object masks. Our results, obtained by training on a dataset of 20,000 YouTube videos weakly tagged into 15 classes, demonstrate automatic extraction of pixel-level object masks. Evaluated against a ground-truthed subset of 50,000 frames with pixel-level annotations, we conrm that our proposed methods can learn good object masks just by watching YouTube.

Presented at: ECCV 2012 Workshop on Web-scale Vision and Social Media, 2012, October 7-12, 2012, in Florence, ITALY.

Awarded the BEST PAPER AWARD!

Linguistic Transfer of Human Assembly Tasks to Robots

• N. Dantam, I. Essa, and M. Stilman (2012), “Linguistic Transfer of Human Assembly Tasks to Robots,” in Proceedings of Intelligent Robots and Systems (IROS), 2012. [PDF] [BIBTEX]

  @inproceedings{2012-Dantam-LTHATR,
    Author = {N. Dantam and I. Essa and M. Stilman},
    Booktitle = {Proceedings of Intelligent Robots and Systems (IROS)},
    Date-Added = {2012-10-23 15:07:46 +0000},
    Date-Modified = {2012-10-23 15:08:57 +0000},
    Pdf = {http://www.cc.gatech.edu/~ndantam3/papers/dantam2012assembly.pdf},
    Title = {Linguistic Transfer of Human Assembly Tasks to Robots},
    Year = {2012}}

Abstract

We demonstrate the automatic transfer of an assembly task from human to robot. This work extends efforts showing the utility of linguistic models in verifiable robot control policies by now performing real visual analysis of human demonstrations to automatically extract a policy for the task. This method tokenizes each human demonstration into a sequence of object connection symbols, then transforms the set of sequences from all demonstrations into an automaton, which represents the task-language for assembling a desired object. Finally, we combine this assembly automaton with a kinematic model of a robot arm to reproduce the demonstrated task.

Presented at: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2012), October 7-12, 2012 Vilamoura, Algarve, Portugal.