prof.irfanessa.com

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!

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.

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

Here is an excerpt from a Google Research Blog on our Video Stabilization on YouTube.  Now even more improved.

One thing we have been working on within Research at Google is developing methods for making casual videos look more professional, thereby providing users with a better viewing experience. Professional videos have several characteristics that differentiate them from casually shot videos. For example, in order to tell a story, cinematographers carefully control lighting and exposure and use specialized equipment to plan camera movement.

We have developed a technique that mimics professional camera moves and applies them to videos recorded by handheld devices. Cinematographers use specialized equipment such as tripods and dollies to plan their camera paths and hold them steady. In contrast, think of a video you shot using a mobile phone camera. How steady was your hand and were you able to anticipate an interesting moment and smoothly pan the camera to capture that moment? To bridge these differences, we propose an algorithm that automatically determines the best camera path and recasts the video as if it were filmed using stabilization equipment.

Via Video Stabilization on YouTube.

Calibration-Free Rolling Shutter Removal

• M. Grundmann, V. Kwatra, D. Castro, and I. Essa (2012), “Calibration-Free Rolling Shutter Removal,” in Proceedings of IEEE Conference on Computational Photography (ICCP), 2012. [PDF] [WEBSITE] [VIDEO] [DOI] [BLOG] [BIBTEX]

  @inproceedings{2012-Grundmann-CRSR,
    Author = {Matthias Grundmann and Vivek Kwatra and Daniel Castro and Irfan Essa},
    Blog = {http://prof.irfanessa.com/2012/04/28/paper-iccp12/},
    Booktitle = {Proceedings of IEEE Conference on Computational Photography (ICCP)},
    Date-Added = {2012-04-09 22:40:38 +0000},
    Date-Modified = {2013-01-26 14:24:42 +0000},
    Doi = {http://dx.doi.org/10.1109/ICCPhot.2012.6215213},
    Pdf = {http://www.cc.gatech.edu/~irfan/p/2012-Grundmann-CRSR.pdf},
    Publisher = {IEEE Computer Society},
    Title = {Calibration-Free Rolling Shutter Removal},
    Url = {http://www.cc.gatech.edu/cpl/projects/rollingshutter/},
    Video = {http://www.youtube.com/watch?v=_Pr_fpbAok8},
    Year = {2012},
    Bdsk-Url-1 = {http://www.cc.gatech.edu/cpl/projects/rollingshutter/}}

Abstract

We present a novel algorithm for efficient removal of rolling shutter distortions in uncalibrated streaming videos. Our proposed method is calibration free as it does not need any knowledge of the camera used, nor does it require calibration using specially recorded calibration sequences. Our algorithm can perform rolling shutter removal under varying focal lengths, as in videos from CMOS cameras equipped with an optical zoom. We evaluate our approach across a broad range of cameras and video sequences demonstrating robustness, scalability, and repeatability. We also conducted a user study, which demonstrates a preference for the output of our algorithm over other state-of-the art methods. Our algorithm is computationally efficient, easy to parallelize, and robust to challenging artifacts introduced by various cameras with differing technologies.

Presented at IEEE International Conference on Computational Photography, Seattle, WA, April 27-29, 2012.

Winner of BEST PAPER AWARD.

Our following paper was just awarded the Excellent Paper for 2011 in Computer Vision by Google Research.

• M. Grundmann, V. Kwatra, and I. Essa (2011), “Auto-Directed Video Stabilization with Robust L1 Optimal Camera Paths,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011. [PDF] [WEBSITE] [VIDEO] [DEMO] [DOI] [BLOG] [BIBTEX]

  @inproceedings{2011-Grundmann-AVSWROCP,
    Author = {M. Grundmann and V. Kwatra and I. Essa},
    Blog = {http://prof.irfanessa.com/2011/06/19/videostabilization/},
    Booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    Date-Modified = {2013-01-26 14:23:00 +0000},
    Demo = {http://www.youtube.com/watch?v=0MiY-PNy-GU},
    Doi = {http://dx.doi.org/10.1109/CVPR.2011.5995525},
    Month = {June},
    Pdf = {http://www.cc.gatech.edu/~irfan/p/2011-Grundmann-AVSWROCP.pdf},
    Publisher = {IEEE Computer Society},
    Title = {Auto-Directed Video Stabilization with Robust L1 Optimal Camera Paths},
    Url = {http://www.cc.gatech.edu/cpl/projects/videostabilization/},
    Video = {http://www.youtube.com/watch?v=i5keG1Y810U},
    Year = {2011},
    Bdsk-Url-1 = {http://www.cc.gatech.edu/cpl/projects/videostabilization/}}

Casually shot videos captured by handheld or mobile cameras suffer from significant amount of shake. Existing in-camera stabilization methods dampen high-frequency jitter but do not suppress low-frequency movements and bounces, such as those observed in videos captured by a walking person. On the other hand, most professionally shot videos usually consist of carefully designed camera configurations, using specialized equipment such as tripods or camera dollies, and employ ease-in and ease-out for transitions. Our stabilization technique automatically converts casual shaky footage into more pleasant and professional looking videos by mimicking these cinematographic principles. The original, shaky camera path is divided into a set of segments, each approximated by either constant, linear or parabolic motion, using an algorithm based on robust L1 optimization. The stabilizer has been part of the YouTube Editor youtube.com/editor since March 2011.

via Research Blog.

Our work, as described in the following paper, now showcased in youtube.

• M. Grundmann, V. Kwatra, and I. Essa (2011), “Auto-Directed Video Stabilization with Robust L1 Optimal Camera Paths,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011. [PDF] [WEBSITE] [VIDEO] [DEMO] [DOI] [BLOG] [BIBTEX]

  @inproceedings{2011-Grundmann-AVSWROCP,
    Author = {M. Grundmann and V. Kwatra and I. Essa},
    Blog = {http://prof.irfanessa.com/2011/06/19/videostabilization/},
    Booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    Date-Modified = {2013-01-26 14:23:00 +0000},
    Demo = {http://www.youtube.com/watch?v=0MiY-PNy-GU},
    Doi = {http://dx.doi.org/10.1109/CVPR.2011.5995525},
    Month = {June},
    Pdf = {http://www.cc.gatech.edu/~irfan/p/2011-Grundmann-AVSWROCP.pdf},
    Publisher = {IEEE Computer Society},
    Title = {Auto-Directed Video Stabilization with Robust L1 Optimal Camera Paths},
    Url = {http://www.cc.gatech.edu/cpl/projects/videostabilization/},
    Video = {http://www.youtube.com/watch?v=i5keG1Y810U},
    Year = {2011},
    Bdsk-Url-1 = {http://www.cc.gatech.edu/cpl/projects/videostabilization/}}

YouTube effects: Shake it like an Instagram picture

via YouTube effects: Shake it like an Instagram picture — Online Video News.

YouTube users can now apply a number of Instagram-like effects to their videos, giving them a cartoonish or Lomo-like look with the click of a button. The effects are part of a new editing feature that also includes cropping and advanced image stabilization.

Taking the shaking out of video uploads should go a long way towards making some of the amateur footage captured on mobile phones more watchable, but it can also be resource-intensive — which is why Google’s engineers invented an entirely new approach toward image stabilization.

The new editing functionality will be part of YouTube’s video page, where a new “Edit video” button will offer access to filters and other editing functionality. This type of post-processing is separate from YouTube’s video editor, which allows to produce new videos based on existing clips.

via Auto-Directed Video Stabilization with Robust L1 Optimal Camera Paths – Google Research Blog.

Auto-Directed Video Stabilization with Robust L1 Optimal Camera Paths
Posted by Matthias Grundmann, Vivek Kwatra, and Irfan Essa,

Earlier this year, we announced the launch of new features on the YouTube Video Editor, including stabilization for shaky videos, with the ability to preview them in real-time. The core technology behind this feature is detailed in this paper, which will be presented at the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2011).

Casually shot videos captured by handheld or mobile cameras suffer from significant amount of shake. Existing in-camera stabilization methods dampen high-frequency jitter but do not suppress low-frequency movements and bounces, such as those observed in videos captured by a walking person. On the other hand, most professionally shot videos usually consist of carefully designed camera configurations, using specialized equipment such as tripods or camera dollies, and employ ease-in and ease-out for transitions. Our goal was to devise a completely automatic method for converting casual shaky footage into more pleasant and professional looking videos.

Our technique mimics the cinematographic principles outlined above by automatically determining the best camera path using a robust optimization technique. The original, shaky camera path is divided into a set of segments, each approximated by either a constant, linear or parabolic motion. Our optimization finds the best of all possible partitions using a computationally efficient and stable algorithm.

To achieve real-time performance on the web, we distribute the computation across multiple machines in the cloud. This enables us to provide users with a real-time preview and interactive control of the stabilized result. Above we provide a video demonstration of how to use this feature on the YouTube Editor. We will also demo this live at Google’s exhibition booth in CVPR 2011.

For more details see the Project Site. See the youtube video of the system on youtube. See the paper in PDF, and a technical video of the work.

Full paper is

• Matthias Grundmann, Vivek Kwatra, and Irfan Essa (2011), “Auto-Directed Video Stabilization with Robust L1 Optimal Camera Paths,” In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2011), Colorado Springs, CO, USA. [PDF][Video][Blog][Demo][Project Site]