Michal Irani

Actions as space-time shapes

Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as three-dimensional shapes induced by the silhouettes in the space-time volume. We adopt a recent approach by Gorelick et al. (2004) for analyzing 2D shapes and generalize it to deal with volumetric space-time action shapes. Our method utilizes properties of the solution to the Poisson equation to extract space-time features such as local space-time saliency, action dynamics, shape structure and orientation. We show that these features are useful for action recognition, detection and clustering. The method is fast, does not require video alignment and is applicable in (but not limited to) many scenarios where the background is known. Moreover, we demonstrate the robustness of our method to partial occlusions, non-rigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action and low quality video

Improving resolution by image registration

Abstract Image resolution can be improved when the relative displacements in image sequences are known accurately, and some knowledge of the imaging process is available. The proposed approach is similar to back-projection used in tomography. Examples of improved image resolution are given for gray-level and color images, when the unknown image displacements are computed from the image sequence.

Actions as Space-Time Shapes

Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as three-dimensional shapes induced by the silhouettes in the space-time volume. We adopt a recent approach [14] for analyzing 2D shapes and generalize it to deal with volumetric space-time action shapes. Our method utilizes properties of the solution to the Poisson equation to extract space-time features such as local space-time saliency, action dynamics, shape structure, and orientation. We show that these features are useful for action recognition, detection, and clustering. The method is fast, does not require video alignment, and is applicable in (but not limited to) many scenarios where the background is known. Moreover, we demonstrate the robustness of our method to partial occlusions, nonrigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action, and low-quality video.

Super-resolution from a single image

Methods for super-resolution can be broadly classified into two families of methods: (i) The classical multi-image super-resolution (combining images obtained at subpixel misalignments), and (ii) Example-Based super-resolution (learning correspondence between low and high resolution image patches from a database). In this paper we propose a unified framework for combining these two families of methods. We further show how this combined approach can be applied to obtain super resolution from as little as a single image (with no database or prior examples). Our approach is based on the observation that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Recurrence of patches within the same image scale (at subpixel misalignments) gives rise to the classical super-resolution, whereas recurrence of patches across different scales of the same image gives rise to example-based super-resolution. Our approach attempts to recover at each pixel its best possible resolution increase based on its patch redundancy within and across scales.

Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency

Abstract Accurate computation of image motion enables the enhancement of image sequences. In scenes having multiple moving objects the motion computation is performed together with object segmentation by using a unique temporal integration approach. After the motion for the different image regions is computed, these regions can be enhanced by fusing several successive frames covering the same region. Enhancements treated here include improvement of image resolution, filling-in occluded regions, and reconstruction of transparent objects.

Summarizing visual data using bidirectional similarity

We propose a principled approach to summarization of visual data (images or video) based on optimization of a well-defined similarity measure. The problem we consider is re-targeting (or summarization) of image/video data into smaller sizes. A good ldquovisual summaryrdquo should satisfy two properties: (1) it should contain as much as possible visual information from the input data; (2) it should introduce as few as possible new visual artifacts that were not in the input data (i.e., preserve visual coherence). We propose a bi-directional similarity measure which quantitatively captures these two requirements: Two signals S and T are considered visually similar if all patches of S (at multiple scales) are contained in T, and vice versa. The problem of summarization/re-targeting is posed as an optimization problem of this bi-directional similarity measure. We show summarization results for image and video data. We further show that the same approach can be used to address a variety of other problems, including automatic cropping, completion and synthesis of visual data, image collage, object removal, photo reshuffling and more.

Computing occluding and transparent motions

Computing the motions of several moving objects in image sequences involves simultaneous motion analysis and segmentation. This task can become complicated when image motion changes significantly between frames, as with camera vibrations. Such vibrations make tracking in longer sequences harder, as temporal motion constancy cannot be assumed. The problem becomes even more difficult in the case of transparent motions.A method is presented for detecting and tracking occluding and transparent moving objects, which uses temporal integration without assuming motion constancy. Each new frame in the sequence is compared to a dynamic internal representation image of the tracked object. The internal representation image is constructed by temporally integrating frames after registration based on the motion computation. The temporal integration maintains sharpness of the tracked object, while blurring objects that have other motions. Comparing new frames to the internal representation image causes the motion analysis algorithm to continue tracking the same object in subsequent frames, and to improve the segmentation.

Event-based analysis of video

Dynamic events can be regarded as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple statistical distance measure between video sequences (possibly of different lengths) based on their behavioral content. This measure is non-parametric and can thus handle a wide range of dynamic events. We use this measure for isolating and clustering events within long continuous video sequences. This is done without prior knowledge of the types of events, their models, or their temporal extent. An outcome of such a clustering process is a temporal segmentation of long video sequences into event-consistent sub-sequences, and their grouping into event-consistent clusters. Our event representation and associated distance measure can also be used for event-based indexing into long video sequences, even when only one short example-clip is available. However, when multiple example-clips of the same event are available (either as a result of the clustering process, or given manually), these can be used to refine the event representation, the associated distance measure, and accordingly the quality of the detection and clustering process.

Mosaic based representations of video sequences and their applications

Recently, there has been a growing interest in the use of mosaic images to represent the information contained in video sequences. The paper systematically investigates how to go beyond thinking of the mosaic simply as a visualization device, but rather as a basis for efficient representation of video sequences. We describe two different types of mosaics called the static and the dynamic mosaic that are suitable for different needs and scenarios. We discuss a series of extensions to these basic mosaics to provide representations at multiple spatial and temporal resolutions and to handle 3D scene information. We describe techniques for the basic elements of the mosaic construction process, namely alignment, integration, and residual analysis. We describe several applications of mosaic representations including video compression, enhancement, enhanced visualization, and other applications in video indexing, search, and manipulation.<<ETX>>

Video indexing based on mosaic representations

Video is a rich source of information. It provides visual information about scenes. This information is implicitly buried inside the raw video data, however, and is provided with the cost of very high temporal redundancy. While the standard sequential form of video storage is adequate for viewing in a movie mode, it fails to support rapid access to information of interest that is required in many of the emerging applications of video. This paper presents an approach for efficient access, use and manipulation of video data. The video data are first transformed from their sequential and redundant frame-based representation, in which the information about the scene is distributed over many frames, to an explicit and compact scene-based representation, to which each frame can be directly related. This compact reorganization of the video data supports nonlinear browsing and efficient indexing to provide rapid access directly to information of interest. This paper describes a new set of methods for indexing into the video sequence based on the scene-based representation. These indexing methods are based on geometric and dynamic information contained in the video. These methods complement the more traditional content-based indexing methods, which utilize image appearance information (namely, color and texture properties) but are considerably simpler to achieve and are highly computationally efficient.