TY - INPR A1 - Grundhöfer, Anselm A1 - Bimber, Oliver T1 - Real-Time Adaptive Radiometric Compensation N2 - Recent radiometric compensation techniques make it possible to project images onto colored and textured surfaces. This is realized with projector-camera systems by scanning the projection surface on a per-pixel basis. With the captured information, a compensation image is calculated that neutralizes geometric distortions and color blending caused by the underlying surface. As a result, the brightness and the contrast of the input image is reduced compared to a conventional projection onto a white canvas. If the input image is not manipulated in its intensities, the compensation image can contain values that are outside the dynamic range of the projector. They will lead to clipping errors and to visible artifacts on the surface. In this article, we present a novel algorithm that dynamically adjusts the content of the input images before radiometric compensation is carried out. This reduces the perceived visual artifacts while simultaneously preserving a maximum of luminance and contrast. The algorithm is implemented entirely on the GPU and is the first of its kind to run in real-time. KW - Maschinelles Sehen KW - CGI KW - Bildbasiertes Rendering KW - Display KW - Projektionsverfahren KW - Radiometrische Kompensation KW - Projektion KW - Projekor-Kamera System KW - Bildkorrektur KW - Visuelle Wahrnehmung KW - radiometric compensation KW - projection KW - projector-camera systems KW - image correction KW - visual perception Y1 - 2006 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20111215-7848 ER - TY - RPRT A1 - Exner, David A1 - Bruns, Erich A1 - Kurz, Daniel A1 - Grundhöfer, Anselm A1 - Bimber, Oliver T1 - Fast and Reliable CAMShift Tracking N2 - CAMShift is a well-established and fundamental algorithm for kernel-based visual object tracking. While it performs well with objects that have a simple and constant appearance, it is not robust in more complex cases. As it solely relies on back projected probabilities it can fail in cases when the object's appearance changes (e.g. due to object or camera movement, or due to lighting changes), when similarly colored objects have to be re-detected or when they cross their trajectories. We propose extensions to CAMShift that address and resolve all of these problems. They allow the accumulation of multiple histograms to model more complex object appearance and the continuous monitoring of object identi- ties to handle ambiguous cases of partial or full occlusion. Most steps of our method are carried out on the GPU for achieving real-time tracking of multiple targets simultaneously. We explain an ecient GPU implementations of histogram generation, probability back projection, im- age moments computations, and histogram intersection. All of these techniques make full use of a GPU's high parallelization. KW - Bildverarbeitung KW - CAMShift KW - Kernel-Based Tracking KW - GPU Programming KW - CAMShift KW - Kernel-Based Tracking KW - GPU Programming Y1 - 2009 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20091217-14962 ER - TY - RPRT A1 - Amano, Toshiyuki A1 - Bimber, Oliver A1 - Grundhöfer, Anselm T1 - Appearance Enhancement for Visually Impaired with Projector Camera Feedback N2 - Visually impaired is a common problem for human life in the world wide. The projector-based AR technique has ability to change appearance of real object, and it can help to improve visibility for visually impaired. We propose a new framework for the appearance enhancement with the projector camera system that employed model predictive controller. This framework enables arbitrary image processing such as photo-retouch software in the real world and it helps to improve visibility for visually impaired. In this article, we show the appearance enhancement result of Peli's method and Wolffshon's method for the low vision, Jefferson's method for color vision deficiencies. Through experiment results, the potential of our method to enhance the appearance for visually impaired was confirmed as same as appearance enhancement for the digital image and television viewing. KW - Maschinelles Sehen KW - Projector Camera System KW - Model Predictive Control KW - Visually Impaired Y1 - 2010 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20100106-14974 ER -