Browsing A. James Clark School of Engineering by Author "Abdelkader, Mohamed F."
Now showing 1 - 2 of 2
Results Per Page
- ItemActivity Representation from Video Using Statistical Models on Shape Manifolds(2010) Abdelkader, Mohamed F.; Chellappa, Rama; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Activity recognition from video data is a key computer vision problem with applications in surveillance, elderly care, etc. This problem is associated with modeling a representative shape which contains significant information about the underlying activity. In this dissertation, we represent several approaches for view-invariant activity recognition via modeling shapes on various shape spaces and Riemannian manifolds. The first two parts of this dissertation deal with activity modeling and recognition using tracks of landmark feature points. The motion trajectories of points extracted from objects involved in the activity are used to build deformation shape models for each activity, and these models are used for classification and detection of unusual activities. In the first part of the dissertation, these models are represented by the recovered 3D deformation basis shapes corresponding to the activity using a non-rigid structure from motion formulation. We use a theory for estimating the amount of deformation for these models from the visual data. We study the special case of ground plane activities in detail because of its importance in video surveillance applications. In the second part of the dissertation, we propose to model the activity by learning an affine invariant deformation subspace representation that captures the space of possible body poses associated with the activity. These subspaces can be viewed as points on a Grassmann manifold. We propose several statistical classification models on Grassmann manifold that capture the statistical variations of the shape data while following the intrinsic Riemannian geometry of these manifolds. The last part of this dissertation addresses the problem of recognizing human gestures from silhouette images. We represent a human gesture as a temporal sequence of human poses, each characterized by a contour of the associated human silhouette. The shape of a contour is viewed as a point on the shape space of closed curves and, hence, each gesture is characterized and modeled as a trajectory on this shape space. We utilize the Riemannian geometry of this space to propose a template-based and a graphical-based approaches for modeling these trajectories. The two models are designed in such a way to account for the different invariance requirements in gesture recognition, and also capture the statistical variations associated with the contour data.
- ItemIntegration and Evaluation of a Video Surveillance System(2005-08-19) Abdelkader, Mohamed F.; Chellappa, Rama; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Visual surveillance systems are getting a lot of attention over the last few years, due to a growing need for surveillance applications. In this thesis, we present a visual surveillance system that integrates modules for motion detection, tracking, and trajectory characterization to achieve robust monitoring of moving objects in scenes under surveillance. The system operates on video sequences acquired by stationary color and infra-red surveillance cameras. Motion detection is implemented using an algorithm that combines thresholding of temporal variance and background modeling. The tracking algorithm combines motion and appearance information into an appearance model and uses a particle filter framework for object tracking. The trajectory analysis module builds a model for a given normal activity using a factorization approach, and uses this model for the detection of any abnormal motion pattern. The system was tested on a large ground-truthed data set containing hundreds of color and FLIR image sequences. Results of performance evaluation using these sequences are reported in this thesis.