Ahmed M. Elgammal

Learn More
Background subtraction is a method typically used to segment moving regions in image sequences taken from a static camera by comparing each new frame to a model of the scene background. We present a novel non-parametric background model and a background subtraction approach. The model can handle situations where the background of the scene is cluttered and(More)
We aim to infer 3D body pose directly from human silhouettes. Given a visual input (silhouette), the objective is to recover the intrinsic body configuration, recover the viewpoint, reconstruct the input and detect any spatial or temporal outliers. In order to recover intrinsic body configuration (pose) from the visual input (silhouette), we explicitly(More)
Bilinear and multi-linear models have been successful in decomposing static image ensembles into perceptually orthogonal sources of variations, e.g., separation of style and content. If we consider the appearance of human motion such as gait, facial expression and gesturing, most of such activities result in nonlinear manifolds in the image space. The(More)
Many vision algorithms depend on the estimation of a probability density function from observations. Kernel density estimation techniques are quite general and powerful methods for this problem, but have a significant disadvantage in that they are computationally intensive. In this paper, we explore the use of kernel density estimation with the fast Gauss(More)
In this paper we propose a framework for learning a regression function form a set of local features in an image. The regression is learned from an embedded representation that reflects the local features and their spatial arrangement as well as enforces supervised manifold constraints on the data. We applied the approach for viewpoint estimation on a(More)
This paper addresses the problem of capturing the dynamics for exemplar-based recognition systems. Traditional HMM provides a probabilistic tool to capture system dynamics and in exemplar paradigm, HMM states are typically coupled with the exemplars. Alternatively, we propose a non-parametric HMM approach that uses a discrete HMM with arbitrary states(More)
We present a framework for monocular 3D kinematic pose tracking and viewpoint estimation of periodic and quasi-periodic human motions from an uncalibrated camera. The approach we introduce here is based on learning both the visual observation manifold and the kinematic manifold of the motion using a joint representation. We show that the visual manifold of(More)
Recently several methods for background subtraction from moving camera were proposed. They use bottom up cues to segment video frames into foreground and background regions. Due to this lack of explicit models, they can easily fail to detect a foreground object when such cues are ambiguous in certain parts of the video. This becomes even more challenging(More)
In this paper we present a probabilistic framework for tracking regions based on their appearance. We exploit the feature-spatial distribution of a region representing an object as a probabilistic constraint to track that region over time. The tracking is achieved by maximizing a similaritybased objective function over transformation space given a(More)