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.

This paper presents a method for capturing and computing 3D parallax. 3D parallax, as used here, refers to vertical offset from the ground plane, height. The method is based on analyzing shadows of vertical poles (e.g., a tall building’s contour) that sweep the object. Unlike existing beam-scanning approaches, such as shadow or structured light, that recover the distance of a point from the camera, our approach measures the height from the ground plane directly. Previous methods compute the distance from the camera using triangulation between rays outgoing from the light-source and the camera. Such a triangulation is difficult when the objects are far from the camera, and requires accurate knowledge of the light source position. In contrast, our approach intersects two (unknown) planes generated separately by two casting objects. This omits the need to precompute the location of the light source. Furthermore, it allows a moving light source to be used. The proposed setup is particularly useful when the camera cannot directly face the scene or when the object is far away from the camera. A good example is an urban scene captured by a single webcam.

In the near future, the majority of personal computers are expected to have several processing units. This is referred to as core multiprocessing (CMP). Furthermore, each of the computation units will be capable of running multiple hardware threads. To benefit from the additional processing power, application developers should multithread their software. This paper studies the scalability (expected speedup factor) of multimedia applications and provides guidelines for proper utilization of these new multi-core platforms. In particular, we discuss the decomposition method, load balancing, synchronization primitives, interaction with the operating system and hardware issues such as cache hierarchy and memory bandwidth. Our results are based on analysis of several state-of-the-art applications, including H.264 video encoding, panoramic image stitching and dense optical-flow estimation. We demonstrate how to multithread them properly, and report scalability results on several next-generation multi-core platforms

We propose a method for constructing a video sequence of high space-time resolution by combining information from multiple low-resolution video sequences of the same dynamic scene. Super-resolution is performed simultaneously in time and in space. By "temporal super-resolution," we mean recovering rapid dynamic events that occur faster than regular frame-rate. Such dynamic events are not visible (or else are observed incorrectly) in any of the input sequences, even if these are played in "slow-motion." The spatial and temporal dimensions are very different in nature, yet are interrelated. This leads to interesting visual trade-offs in time and space and to new video applications. These include: 1) treatment of spatial artifacts (e.g., motion-blur) by increasing the temporal resolution and 2) combination of input sequences of different space-time resolutions (e.g., NTSC, PAL, and even high quality still images) to generate a high quality video sequence. We further analyze and compare characteristics of temporal super-resolution to those of spatial super-resolution. These include: How many video cameras are needed to obtain increased resolution? What is the upper bound on resolution improvement via super-resolution? What is the temporal analogue to the spatial "ringing" effect?

Illustrating motion in still imagery for the purpose of summary, abstraction and motion description is important for a diverse spectrum of fields, ranging from arts to sciences. In this paper, we introduce a method that produces an action synopsis for presenting motion in still images. The method carefully selects key poses based on an analysis of a skeletal animation sequence, to facilitate expressing complex motions in a single image or a small number of concise views. Our approach is to embed the high-dimensional motion curve in a low-dimensional Euclidean space, where the main characteristics of the skeletal action are kept. The lower complexity of the embedded motion curve allows a simple iterative method which analyzes the curve and locates significant points, associated with the key poses of the original motion. We present methods for illustrating the selected poses in an image as a means to convey the action. We applied our methods to a variety of motions of human actions given either as 3D animation sequences or as video clips, and generated images that depict their synopsis.

This paper describes an approach for locating annotations generated in one video and properly placing them in a second, modified version of the same video. We focus on modifications that standard Television (TV) broadcasts may experience, including content insertion and deletion (i.e., commercials), format conversions and different start/end recording times. To overcome these modifications, we propose content-based video timelines. We identify the position of a frame in a long video stream with an accuracy of one frame based on its content, without using embedded time codes. To make this approach feasible, we use a compact representation of a video frame, which we call a "fingerprint". Fingerprints capture small temporal variations within shots and therefore allow precise position recovery. Our fingerprints' efficient storage size, extraction time and comparison complexity suggest that our approach can be applied using off-the-shelf PCs and TV "set-top" boxes.

This paper studies the problem of sequence-to-sequence alignment, namely, establishing correspondences in time and in space between two different video sequences of the same dynamic scene. The sequences are recorded by uncalibrated video cameras which are either stationary or jointly moving, with fixed (but unknown) internal parameters and relative intercamera external parameters. Temporal variations between image frames (such as moving objects or changes in scene illumination) are powerful cues for alignment, which cannot be exploited by standard image-to-image alignment techniques. We show that, by folding spatial and temporal cues into a single alignment framework, situations which are inherently ambiguous for traditional image-to-image alignment methods, are often uniquely resolved by sequence-to-sequence alignment. Furthermore, the ability to align and integrate information across multiple video sequences both in time and in space gives rise to new video applications that are not possible when only image-to-image alignment is used.

This paper shows how two image sequences that have no spatial overlap between their fields of view can be aligned both in time and in space. Such alignment is possible when the two cameras are attached closely together and are moved jointly in space. The common motion induces "similar" changes over time within the two sequences. This correlated temporal behavior is used to recover the spatial and temporal transformations between the two sequences. The requirement of "coherent appearance" in standard image alignment techniques is therefore replaced by "coherent temporal behavior", which is often easier to satisfy. This approach to alignment can be used not only for aligning nan-overlapping sequences, but also for handling other cases that are inherently difficult for standard image alignment techniques. We demonstrate applications of this approach to three real-world problems: (i) alignment of non-overlapping sequences for generating wide-screen movies, (ii) alignment of images (sequences) obtained at significantly different zooms, for surveillance applications, and (iii) multi-sensor image alignment for multi-sensor fusion.

The paper presents an approach for establishing correspondences in time and in space between two different video sequences of the same dynamic scene, recorded by stationary uncalibrated video cameras. The method simultaneously estimates both spatial alignment as well as temporal synchronization (temporal alignment) between the two sequences, using all available spatio-temporal information. Temporal variations between image frames (such as moving objects or changes in scene illumination) are powerful cues for alignment, which cannot be exploited by standard image-to-image alignment techniques. We show that by folding spatial and temporal cues into a single alignment framework, situations which are inherently ambiguous for traditional image-to-image alignment methods, are often uniquely resolved by sequence-to-sequence alignment. We also present a "direct" method for sequence-to-sequence alignment. The algorithm simultaneously estimates spatial and temporal alignment parameters directly from measurable sequence quantities, without requiring prior estimation of point correspondences, frame correspondences, or moving object detection. Results are shown on real image sequences taken by multiple video cameras.