Research Interests:
The early implementation of the Epipolar-Plane Image Adysis depth measuring technique demondrated tlie feasibi1it.y and benefits of tlie approach, but was developed for a restricted camera geometry. To enhance tlie applicability of the... more
The early implementation of the Epipolar-Plane Image Adysis depth measuring technique demondrated tlie feasibi1it.y and benefits of tlie approach, but was developed for a restricted camera geometry. To enhance tlie applicability of the approach, we have developed a generalization of t.lie analysis that a) enables varying view direction, b) operates sequeiitially, while the sensor is in motion. and c) provides spatiallycoherent descriptions of observed ohjects. To achieve this grneralization it was necessary to develop an explicit. description of the evolution of images over time. This evolution produces two-dimensional manifolds in space-time - these represent explicitly both the spatial and temporal structure of the temporally-evolving imagery, and we term them spaliot~mporul surfaces. A battery ol hear sequential filters operates on these surfaces, tracking and estimating paramet.ers of features in the scene. The product of the analysis is a set of evolving three-dimensional contours describing the tliree-dimensional contours in the scene.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
... Urbana enjoyable. Dave Waltz has served me wonderfully as an advisor, supporter, andburc iucratic untangler. ... This report is based on a Ph.D. thesis submitted to the University of Illinois at Urbana-Champaign in Sept.nber of 1981... more
... Urbana enjoyable. Dave Waltz has served me wonderfully as an advisor, supporter, andburc iucratic untangler. ... This report is based on a Ph.D. thesis submitted to the University of Illinois at Urbana-Champaign in Sept.nber of 1981 ([Baker 1981b]). ...
Research Interests:
ABSTRACT The past few years have seen a growing interest in the application of three-dimensional image processing. With the increasing demand for 3-D spatial information for tasks of passive navigation Generrgy 1980, Moravec 1980,... more
ABSTRACT The past few years have seen a growing interest in the application of three-dimensional image processing. With the increasing demand for 3-D spatial information for tasks of passive navigation Generrgy 1980, Moravec 1980, automatic surveillance Henderson 1979, aerial cartography Kelly 1977, Panton 1978, and inspection in industrial automation, the importance of effective stereo analysis has been made quite clear. A particular challenge is to provide reliable and accurate depth data for input to object or terrain modelling systems (such as Brooks 1981b). This paper describes an algorithm for such stereo sensing. It uses an edge-based line-by-line stereo correspondence scheme, and appears to be fast, robust, and parallel implementable. The processing consists of extracting edge descriptions for a stereo pair of images, linking these edges to their nearest neighbors to obtain the edges to their nearest neighbors to obtain the edge connectivity structure, correlating the edge descriptions on the basis of local edge properties, then cooperatively removing those edge correspondences determined to be in error-those which violate the connectivity structure of the two images. A futher correspondence process, using a technique similar to that used for the edges, is applied to the image intensity values over intervals defined by the edge correspondence. The result of the processing is a full image array disparity map of the scene viewed. (Author)
Research Interests:
ABSTRACT Embodiments of the present invention relate to a system and method for analysing, designing and manufacturing a body to determine potential discontinuities within the body when subjected to an action.
Research Interests:
New video applications are becoming possible with the advent of several enabling technologies: multicamera capture, increased PC bus bandwidth, multicore processors, and advanced graphics cards. We present a commercially -available... more
New video applications are becoming possible with the advent of several enabling technologies: multicamera capture, increased PC bus bandwidth, multicore processors, and advanced graphics cards. We present a commercially -available multicamera system and a software architecture that, coupled with industry trends, create a situation in which video capture, processing, and display are all increasingly scalable in the number of video streams. Leveraging this end-to-end scalability, we introduce a novel method of generating high-resolution, panoramic video. While traditional point-based mosaicking requires significant image overlap, we gain significant advantage by calibrating using shared observations of lines to constrain the placement of images. Two non-overlapping cameras do not share any scene points; however, seeing different parts of the same line does constrain their spatial alignment. Using lines allows us to reduce overlap in the source images, thereby maximizing final mosaic ...
Research Interests:
Research Interests:
This book describes what must be today's most widely known stereoscopic correspondence system --- one based on the Marr-Poggio theory of stereopsis ([Marr 1977]).
Research Interests:
Research Interests:
We present approach to robust real-time person tracking in crowded and/or unknown environments using multimodal integration. We combine stereo, color, and face detection modules into a single robust system, and show an initial application... more
We present approach to robust real-time person tracking in crowded and/or unknown environments using multimodal integration. We combine stereo, color, and face detection modules into a single robust system, and show an initial application for an interactive display where the user sees his face distorted into various comic poses in real-time. Stereo processing is used to isolate the figure of
Research Interests:
Research Interests:
Research Interests:
Research Interests:
ABSTRACT In this paper we address calibration of camera arrays for life-size 3D video acquisition and display where mosaicking and multi-viewpoint stereo are combined to provide an immersive experience which, by its size, resolution, and... more
ABSTRACT In this paper we address calibration of camera arrays for life-size 3D video acquisition and display where mosaicking and multi-viewpoint stereo are combined to provide an immersive experience which, by its size, resolution, and three-dimensionality, is meant to rival being there. This coupling of multiview and mosaicking requires integration of numerous synchronized video streams in a single presentation, aligned for both panoramic blending and epipolar rectification. The calibration framework we have developed extends the classical checkerboard approach through a modular multistage pipeline performing global optimization across intrinsics, extrinsics, panoramas, multi-view epipolar alignments, and color correction. We demonstrate the methodology on several multiview camera arrays with various configurations aimed at mosaicking and epipolar light-field analysis. The results of this analysis have driven real-time life-sized panoramic 3D displays of captured events such as a concert, a fashion show, and sports activity.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
We describe methods, accomplishments, and direction in a laboratory-corporate collaborative project over this past year and a half. With the goal of taking new immersive technologies to a growing customer base through in-situ... more
We describe methods, accomplishments, and direction in a laboratory-corporate collaborative project over this past year and a half. With the goal of taking new immersive technologies to a growing customer base through in-situ demonstrations and experiments, we are combining novel capture and display capabilities in delivering life-sized immersive 3D entertainment experiences. We describe the adaptations and innovations needed in delivering
Research Interests:
Advances in building high-performance camera arrays have opened the opportunityand challengeof using these devices for synchronized 3D and multi-viewpoint capture [2]. A requirement of using camera arrays for metric work is that their... more
Advances in building high-performance camera arrays have opened the opportunityand challengeof using these devices for synchronized 3D and multi-viewpoint capture [2]. A requirement of using camera arrays for metric work is that their relative poses be known. With a ...
Research Interests:
Research Interests:
Research Interests:
International Journal of Computer Vision, 3, 51-71 (1989) © 1989 Kluwer Academic Publishers, Boston ... for building an explicit description of the spatial structure and temporal evolution of ... cone, a surface or two-dimensional (2D)... more
International Journal of Computer Vision, 3, 51-71 (1989) © 1989 Kluwer Academic Publishers, Boston ... for building an explicit description of the spatial structure and temporal evolution of ... cone, a surface or two-dimensional (2D) manifold in a three-dimensional (3D) space, would ...
Research Interests:
... in spatiotemporal analysis that use image-plane velocities for measuring arbitrary flows (for example Heeger [7]), or that combine the measured flow with assumptions of constant 3D motion and ... This is the camera geometry normally... more
... in spatiotemporal analysis that use image-plane velocities for measuring arbitrary flows (for example Heeger [7]), or that combine the measured flow with assumptions of constant 3D motion and ... This is the camera geometry normally chosen for computer stereo vision work ...