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.

http://www.youtube.com/watch?v=0MiY-PNy-GU

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]

• Grundmann, Kwatra, and 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][Google Research Blog] [BIBTEX]

   @inproceedings{2011-Grundmann-AVSWROCP, Author = {M. Grundmann and V. Kwatra and I. Essa}, Booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, Month = {June}, Pdf = {http://www.cc.gatech.edu/~irfan/p/2011-Grundmann-AVSWROCP}, 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}}

Abstract

We present a novel algorithm for automatically applying constrainable, L1-optimal camera paths to generate stabilized videos by removing undesired motions. Our goal is to compute camera paths that are composed of constant, linear and parabolic segments mimicking the camera motions employed by professional cinematographers. To this end, our algorithm is based on 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 of camera paths that only suppresses high frequency jitter. We incorporate additional constraints on the path of the camera directly in our algorithm, allowing for stabilized and retargeted videos. Our approach accomplishes this without the need of user interaction or costly 3D reconstruction of the scene, and works as a post-process for videos from any camera or from an online source.

Abstract

Videos of multi-player team sports provide a challenging domain for dynamic scene analysis. Player actions and interactions are complex as they are driven by many factors, such as the short-term goals of the individual player, the overall team strategy, the rules of the sport, and the current context of the game. We show that constrained multi-agent events can be analyzed and even predicted from video. Such analysis requires estimating the global movements of all players in the scene at any time, and is needed for modeling and predicting how the multi-agent play evolves over time on the field. To this end, we propose a novel approach to detect the locations of where the play evolution will proceed, e.g. where interesting events will occur, by tracking player positions and movements over time. We start by extracting the ground level sparse movement of players in each time-step, and then generate a dense motion field. Using this field we detect locations where the motion converges, implying positions towards which the play is evolving. We evaluate our approach by analyzing videos of a variety of complex soccer plays.

• Matthias Grundmann, Vivek Kwatra, Mei Han, Irfan Essa (2010) “Discontinuous Seam-Carving for Video Retargeting” in Proceedings of IEEE Computer Vision and Pattern Recognition Conference (CVPR), San Francisco, CA, USA, June 2010 [PDF][Website][DOI][Video (Youtube)].

Abstract

We introduce a new algorithm for video retargeting 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. This formulation optimizes the difference in appearance of the resultant retargeted frame to the optimal temporally coherent one, and allows for carving around fast moving salient regions.

Additionally, we generalize the idea of appearance-based coherence to the spatial domain by introducing piece-wise spatial seams. Our spatial coherence measure minimizes the change in gradients during retargeting, which preserves spatial detail better than minimization of color difference alone. We also show that per-frame saliency (gradient- based or feature-based) does not always produce desirable retargeting results and propose a novel automatically computed measure of spatio-temporal saliency. As needed, a user may also augment the saliency by interactive region-brushing. Our retargeting algorithm processes the video sequentially, making it conducive for streaming applications.

Abstract

We present 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, which are temporally coherent with stable region boundaries, and allows subse- quent applications to choose from varying levels of granularity. We further improve segmentation quality by using dense optical flow to guide temporal connections in the initial graph.

We also propose two novel approaches to improve the scalability of our technique: (a) a parallel out- of-core algorithm that can process volumes much larger than an in-core algorithm, and (b) a clip-based process- ing algorithm that divides the video into overlapping clips in time, and segments them successively while enforcing consistency.

We demonstrate hierarchical segmentations on video shots as long as 40 seconds, and even support a streaming mode for arbitrarily long videos, albeit without the ability to process them hierarchically.

Abstract

We present a novel approach for robust localization of multiple people observed using multiple cameras. We usethis location information to generate sports visualizations,which include displaying a virtual offside line in soccer games, and showing players’ positions and motion patterns.Our main contribution is the modeling and analysis for the problem of fusing corresponding players’ positional informationas finding minimum weight K-length cycles in complete K-partite graphs. To this end, we use a dynamic programmingbased approach that varies over a continuum of being maximally to minimally greedy in terms of the numberof paths explored at each iteration. We present an end-to-end sports visualization framework that employs our proposed algorithm-class. We demonstrate the robustness of our framework by testing it on 60; 000 frames of soccerfootage captured over 5 different illumination conditions, play types, and team attire.

• Matthias Grundmann, Vivek Kwatra, Mei Han, and Irfan Essa (2010) “Discontinuous Seam-Carving for Video Retargeting” (a GA Tech, Google Collaboration)
• Matthias Grundmann, Vivek Kwatra, Mei Han, and Irfan Essa (2010) “Efficient Hierarchical Graph-Based Video Segmentation” (a GA Tech, Google Collaboration)
• Kihwan Kim, Matthias Grundmann, Ariel Shamir, Iain Matthews, Jessica Hodgins, and Irfan Essa (2010) “Motion Fields to Predict Play Evolution in Dynamic Sport Scenes” (a GA Tech, Disney Collaboration)
• Raffay Hamid, Ramkrishan Kumar, Matthias Grundmann, Kihwan Kim, Irfan Essa, and Jessica Hodgins (2010) “Player Localization Using Multiple Static Cameras for Sports Visualization” (a GA Tech, Disney Collaboration)

Abstract

This paper presents an algorithm for the automatic segmentation of monocular videos into foreground and background layers. Correct segmentations are produced even in the presence of large background motion with nearly stationary foreground. There are three key contributions. The first is the introduction of a novel motion representation, “motons”, inspired by research in object recognition. Second, we propose learning the segmentation likelihood from the spatial context of motion. The learning is efficiently performed by Random Forests. The third contribution is a general taxonomy of tree-based classifiers, which facilitates theoretical and experimental comparisons of several known classification algorithms, as well as spawning new ones. Diverse visual cues such as motion, motion context, colour, contrast and spatial priors are fused together by means of a Conditional Random Field (CRF) model. Segmentation is then achieved by binary min-cut. Our algorithm requires no initialization. Experiments on many video-chat type sequences demonstrate the effectiveness of our algorithm in a variety of scenes. The segmentation results are comparable to those obtained by stereo systems.

Abstract

Speech reading, also known as lip reading, is aimed at extracting visual cues of lip and facial movements to aid in recognition of speech. The main hurdle for speech reading is that visual measurements of lip and facial motion lack information-rich features like the Mel frequency cepstral coefficients (MFCC), widely used in acoustic speech recognition. These MFCC are used with hidden Markov models (HMM) in most speech recognition systems at present. Speech reading could greatly benefit from automatic selection and formation of informative features from measurements in the visual domain. These new features can then be used with HMM to capture the dynamics of lip movement and eventual recognition of lip shapes. Towards this end, we use AdaBoost methods for automatic visual feature formation. Specifically, we design an asymmetric variant of AdaBoost M2 algorithm to deal with the ill-posed multi-class sample distribution inherent in our problem. Our experiments show that the boosted HMM approach outperforms conventional AdaBoost and HMM classifiers. Our primary contributions are in the design of (a) boosted HMM and (b) asymmetric multi-class boosting.