Surface Reconstruction Through Sequential Tracking
Twenty-Second Asilomar Conference on Signals, Systems and Computers
The early implementation of the Epipolar-Plane Image Adysis depth measuring technique demondrated... 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.
The light field encompasses all visual information of a scene. It describes light propagation in ... more The light field encompasses all visual information of a scene. It describes light propagation in every direction through every point in space. Through densely sampling the light field, complementary information such as 3D shape and surface properties of complex objects can be reconstructed. We will present approaches that allow an accurate and realistic capture of complex objects. Industrial applications as well as captures for realistic content visualisations will be presented.
Spie Mobile Multimedia Image Processing Security and Applications 2010, Apr 1, 2010
Camera phones are ubiquitous, and consumers have been adopting them faster than any other technol... more Camera phones are ubiquitous, and consumers have been adopting them faster than any other technology in modern history. When connected to a network, though, they are capable of more than just picture taking: Suddenly, they gain access to the power of the cloud. We exploit this capability by providing a series of image-based personal advisory services. These are designed to work with any handset over any cellular carrier using commonly available Multimedia Messaging Service (MMS) and Short Message Service (SMS) features. Targeted at the unsophisticated consumer, these applications must be quick and easy to use, not requiring download capabilities or preplanning. Thus, all application processing occurs in the back-end system (i.e., as a cloud service) and not on the handset itself. Presenting an image to an advisory service in the cloud, a user receives information that can be acted upon immediately. Two of our examples involve color assessment-selecting cosmetics and home décor paint palettes; the third provides the ability to extract text from a scene. In the case of the color imaging applications, we have shown that our service rivals the advice quality of experts. The result of this capability is a new paradigm for mobile interactions-image-based information services exploiting the ubiquity of camera phones.
Proceedings of the 7th International Joint Conference on Artificial Intelligence Volume 2, 1981
... Urbana enjoyable. Dave Waltz has served me wonderfully as an advisor, supporter, andburc iucr... 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]). ...
ABSTRACT The past few years have seen a growing interest in the application of three-dimensional ... 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)
ABSTRACT Embodiments of the present invention relate to a system and method for analysing, design... more 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.
IEEE International Conference on Image Processing 2005, 2005
Little prior image processing work has addressed estimation and classification of skin color in a... more Little prior image processing work has addressed estimation and classification of skin color in a manner that is independent of camera and illuminant. To this end, we first present new methods for 1) fast, easy-to-use image color correction, with specialization toward skin tones, and 2) fully automated estimation of facial skin color, with robustness to shadows, specularities, and blemishes. Each of these is validated independently against ground truth, and then combined with a classification method that successfully discriminates skin color across a population of people imaged with several different cameras. We also evaluate the effects of image quality and various algorithmic choices on our classification performance. We believe our methods are practical for relatively untrained operators, using inexpensive consumer equipment.
Analysis of synchronized real-time multi-camera video can be facilitated by calibration tailored ... more Analysis of synchronized real-time multi-camera video can be facilitated by calibration tailored to its intended use. Calibration methods appropriate for two-view stereo processing become less so for tasks such as dense lineararray synchronous imaging for metric reconstruction or stereoscopic visualization where additional constraints apply. Calibrating for the construction of an Epipolar-Plane Image (EPI) volume, we introduce a novel method-based on a rank constraint on image homologies-for simultaneous high quality epipole estimation. Epipoles form the basis for recovering the fundamental matrices and, eventually, epipolar rectification parameters for the system. We present this new approach, discuss its characteristics in comparison with traditional metric multi-camera calibration, and show its utility in 3D display.
Uploads
Papers by Harlyn Baker