Computer Vision, Object Association, Nonoverlapping


In this dissertation, we address the problem of object detection and object association across multiple cameras over large areas that are well modeled by planes. We present a unifying probabilistic framework that captures the underlying geometry of planar scenes, and present algorithms to estimate geometric relationships between different cameras, which are subsequently used for co-operative association of objects. We first present a local1 object detection scheme that has three fundamental innovations over existing approaches. First, the model of the intensities of image pixels as independent random variables is challenged and it is asserted that useful correlation exists in intensities of spatially proximal pixels. This correlation is exploited to sustain high levels of detection accuracy in the presence of dynamic scene behavior, nominal misalignments and motion due to parallax. By using a non-parametric density estimation method over a joint domain-range representation of image pixels, complex dependencies between the domain (location) and range (color) are directly modeled. We present a model of the background as a single probability density. Second, temporal persistence is introduced as a detection criterion. Unlike previous approaches to object detection that detect objects by building adaptive models of the background, the foreground is modeled to augment the detection of objects (without explicit tracking), since objects detected in the preceding frame contain substantial evidence for detection in the current frame. Finally, the background and foreground models are used competitively in a MAP-MRF decision framework, stressing spatial context as a condition of detecting interesting objects and the posterior function is maximized efficiently by finding the minimum cut of a capacitated graph. Experimental validation of the method is performed and presented on a diverse set of data. We then address the problem of associating objects across multiple cameras in planar scenes. Since cameras may be moving, there is a possibility of both spatial and temporal non-overlap in the fields of view of the camera. We first address the case where spatial and temporal overlap can be assumed. Since the cameras are moving and often widely separated, direct appearance-based or proximity-based constraints cannot be used. Instead, we exploit geometric constraints on the relationship between the motion of each object across cameras, to test multiple correspondence hypotheses, without assuming any prior calibration information. Here, there are three contributions. First, we present a statistically and geometrically meaningful means of evaluating a hypothesized correspondence between multiple objects in multiple cameras. Second, since multiple cameras exist, ensuring coherency in association, i.e. transitive closure is maintained between more than two cameras, is an essential requirement. To ensure such coherency we pose the problem of object associating across cameras as a k-dimensional matching and use an approximation to find the association. We show that, under appropriate conditions, re-entering objects can also be re-associated to their original labels. Third, we show that as a result of associating objects across the cameras, a concurrent visualization of multiple aerial video streams is possible. Results are shown on a number of real and controlled scenarios with multiple objects observed by multiple cameras, validating our qualitative models. Finally, we present a unifying framework for object association across multiple cameras and for estimating inter-camera homographies between (spatially and temporally) overlapping and non-overlapping cameras, whether they are moving or non-moving. By making use of explicit polynomial models for the kinematics of objects, we present algorithms to estimate inter-frame homographies. Under an appropriate measurement noise model, an EM algorithm is applied for the maximum likelihood estimation of the inter-camera homographies and kinematic parameters. Rather than fit curves locally (in each camera) and match them across views, we present an approach that simultaneously refines the estimates of inter-camera homographies and curve coefficients globally. We demonstrate the efficacy of the approach on a number of real sequences taken from aerial cameras, and report quantitative performance during simulations.


If this is your thesis or dissertation, and want to learn how to access it or for more information about readership statistics, contact us at

Graduation Date





Shah, Mubarak


Doctor of Philosophy (Ph.D.)


College of Engineering and Computer Science

Degree Program

Computer Science








Length of Campus-only Access


Access Status

Doctoral Dissertation (Open Access)