Showing papers by "Shai Avidan published in 2007"

Seam carving for content-aware image resizing

Abstract: Effective resizing of images should not only use geometric constraints, but consider the image content as well We present a simple image operator called seam carving that supports content-aware image resizing for both reduction and expansion A seam is an optimal 8-connected path of pixels on a single image from top to bottom, or left to right, where optimality is defined by an image energy function By repeatedly carving out or inserting seams in one direction we can change the aspect ratio of an image By applying these operators in both directions we can retarget the image to a new size The selection and order of seams protect the content of the image, as defined by the energy function Seam carving can also be used for image content enhancement and object removal We support various visual saliency measures for defining the energy of an image, and can also include user input to guide the process By storing the order of seams in an image we create multi-size images, that are able to continuously change in real time to fit a given size

Ensemble Tracking

Abstract: We consider tracking as a binary classification problem, where an ensemble of weak classifiers is trained online to distinguish between the object and the background. The ensemble of weak classifiers is combined into a strong classifier using AdaBoost. The strong classifier is then used to label pixels in the next frame as either belonging to the object or the background, giving a confidence map. The peak of the map and, hence, the new position of the object, is found using mean shift. Temporal coherence is maintained by updating the ensemble with new weak classifiers that are trained online during tracking. We show a realization of this method and demonstrate it on several video sequences

Synthetic Aperture Tracking: Tracking through Occlusions

Abstract: Occlusion is a significant challenge for many tracking algorithms. Most current methods can track through transient occlusion, but cannot handle significant extended occlusion when the object's trajectory may change significantly. We present a method to track a 3D object through significant occlusion using multiple nearby cameras (e.g., a camera array). When an occluder and object are at different depths, different parts of the object are visible or occluded in each view due to parallax. By aggregating across these views, the method can track even when any individual camera observes very little of the target object. Implementation- wise, the methods are straightforward and build upon established single-camera algorithms. They do not require explicit modeling or reconstruction of the scene and enable tracking in complex, dynamic scenes with moving cameras. Analysis of accuracy and robustness shows that these methods are successful when upwards of '70% of the object is occluded in every camera view. To the best of our knowledge, this system is the first capable of tracking in the presence of such significant occlusion.

Statistics of Infrared Images

Abstract: The proliferation of low-cost infrared cameras gives us a new angle for attacking many unsolved vision problems by leveraging a larger range of the electromagnetic spectrum. A first step to utilizing these images is to explore the statistics of infrared images and compare them to the corresponding statistics in the visible spectrum. In this paper, we analyze the power spectra as well as the marginal and joint wavelet coefficient distributions of datasets of indoor and outdoor images. We note that infrared images have noticeably less texture indoors where temperatures are more homogenous. The joint wavelet statistics also show strong correlation between object boundaries in IR and visible images, leading to high potential for vision applications using a combined statistical model.

Fast Pixel/Part Selection with Sparse Eigenvectors

Abstract: We extend the "Sparse LDA" algorithm of [7] with new sparsity bounds on 2-class separability and efficient partitioned matrix inverse techniques leading to 1000-fold speed-ups. This mitigates the 0(n4) scaling that has limited this algorithm's applicability to vision problems and also prioritizes the less-myopic backward elimination stage by making it faster than forward selection. Experiments include "sparse eigenfaces" and gender classification on FERET data as well as pixel/part selection for OCR on MNIST data using Bayesian (GP) classification. Sparse- LDA is an attractive alternative to the more demanding Automatic Relevance Determination. State-of-the-art recognition is obtained while discarding the majority of pixels in all experiments. Our sparse models also show a better fit to data in terms of the "evidence" or marginal likelihood.

Centralized and Distributed Multi-view Correspondence

Abstract: A probabilistic algorithm is presented for finding correspondences across multiple images in systems with large numbers of cameras and considerable overlap. The algorithm employs the theory of random graphs to provide an efficient probabilistic algorithm that performs Wide-baseline Stereo (WBS) comparisons on a small number of image pairs, and then propagates correspondence information among the cameras. A concrete mathematical analysis of its performance is given. The algorithm is extended to handle false-positive and false-negative failures of the WBS computations. We characterize the detectability of the existence of such failures, and propose an efficient method for this detection. Based on this, we propose a heuristic method for discarding false matches, and demonstrate its effectiveness in reducing errors. Since in many multi-camera applications cameras are attached to processors that handle local processing and communication, it is natural to consider distributed solutions that make use of the local processors and do not use a central computer. Our algorithm is especially suited to run in a distributed setting. If the local processors are sufficiently powerful, this allows an order of magnitude increase in computational efficiency. More importantly, a distributed implementation provides strong robustness guarantees, and eliminates the existence of a single point of failure that is inherent when the application is coordinated by a central computer. We show how to efficiently overcome processor crashes and communication failures with a minimal reduction in the quality of the algorithm's results.