UMD Theses and Dissertations

Permanent URI for this collectionhttp://hdl.handle.net/1903/3

New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a given thesis/dissertation in DRUM.

More information is available at Theses and Dissertations at University of Maryland Libraries.

Browse

Filters

2008 - 20102

Settings

Subject: search.filters.subject.object tracking

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Object Tracking and Mensuration in Surveillance Videos
    (2010) Shao, Jie; Chellappa, Rama; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This thesis focuses on tracking and mensuration in surveillance videos. The first part of the thesis discusses several object tracking approaches based on the different properties of tracking targets. For airborne videos, where the targets are usually small and with low resolutions, an approach of building motion models for foreground/background proposed in which the foreground target is simplified as a rigid object. For relatively high resolution targets, the non-rigid models are applied. An active contour-based algorithm has been introduced. The algorithm is based on decomposing the tracking into three parts: estimate the affine transform parameters between successive frames using particle filters; detect the contour deformation using a probabilistic deformation map, and regulate the deformation by projecting the updated model onto a trained shape subspace. The active appearance Markov chain (AAMC). It integrates a statistical model of shape, appearance and motion. In the AAMC model, a Markov chain represents the switching of motion phases (poses), and several pairwise active appearance model (P-AAM) components characterize the shape, appearance and motion information for different motion phases. The second part of the thesis covers video mensuration, in which we have proposed a heightmeasuring algorithm with less human supervision, more flexibility and improved robustness. From videos acquired by an uncalibrated stationary camera, we first recover the vanishing line and the vertical point of the scene. We then apply a single view mensuration algorithm to each of the frames to obtain height measurements. Finally, using the LMedS as the cost function and the Robbins-Monro stochastic approximation (RMSA) technique to obtain the optimal estimate.
  • Thumbnail Image
    Item
    ROBUST TECHNIQUES FOR VISUAL SURVEILLANCE
    (2008-07-29) Tran, Son Dinh; David, Larry S; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    The work described here aims at improving the performance of three building blocks of visual surveillance systems: foreground detection, object tracking and event detection. First, a new background subtraction algorithm is presented for foreground detection. The background model is built with a set of codewords for every pixel. The codeword contains the pixel's principle color and a tangent vector that represents the color variation at that pixel. As the scene illumination changes, a pixel's color is predicted using a linear model of the codeword and the codeword, in turn, is updated using the new observation. We carried out a number of experiments on sequences that have extensive lighting change and compare with previously developed algorithms. Second, we describe a multi-resolution tracking framework developed with efficiency and robustness in mind. Efficiency is achieved by processing low resolution data whenever possible. Robustness results from multiple level coarse-to-fine searching in the tracking state space. We combine sequential filtering both in time and resolution levels int a probabilistic framework. A color blob tracker is implemented and the tracking results are evaluated in a number of experiments. Third, we present a tracking algorithm based on motion analysis of regional affine invariant image features. The tracked object is represented with a probabilistic occupancy map. Using this map as support, regional features are detected and matched across frames. The motion of pixels is then established based on the feature motion. The object occupancy map is in turn updated according to the pixel motion consistency. We describe experiments to measure the sensitivity of our approach to inaccuracy in initialization, and compare it with other approaches. Fourth, we address the problem of visual event recognition in surveillance where noise and missing observations are serious problems. Common sense domain knowledge is exploited to overcome them. The knowledge is represented as first- order logic production rules with associated weights to indicate their confidence. These rules are used in combination with a relaxed deduction algorithm to construct a network of grounded atoms, the Markov Logic Network. The network is used to perform probabilistic inference for input queries about events of interest. The system's performance is demonstrated on a number of videos from a parking lot domain that contains complex interactions of people and vehicles.