4 results
Search Results
Now showing 1 - 4 of 4
Item Unified Skeletal Animation Reconstruction with Multiple Kinects(The Eurographics Association, 2014) Ahmed, Naveed; Eric Galin and Michael WandWe present a new method for reconstructing a unified skeletal animation with multiple Kinects. Our method is able to reconstruct the unified skeletal animation from Kinect data over 360 degrees. We make use of all three streams: RGB, depth and skeleton, along with the joint tracking confidence state from Microsoft Kinect SDK to find the correctly oriented skeletons and merge them together to get a uniform animation. Our method is easy to implement and provides a simple solution of creating a 360 degree plausible unified skeletal animation that would not be possible to capture with a single Kinect due to occlusions, tracking failures, and field of view constraints.Item A Tone Reproduction Operator for All Luminance Ranges Considering Human Color Perception(The Eurographics Association, 2014) Mikamo, Michihiro; Raytchev, Bisser; Tamaki, Toru; Kaneda, Kazufumi; Eric Galin and Michael WandIn this paper, we present a novel tone reproduction operator that is able to handle the color shift that occurs in photopic, mesopic, and scotopic vision, using a model based on a two-stage model of human color vision and psychophysical data obtained from measurements of human color perception. Since conventional methods are limited to generating images under a certain visual condition, it is difficult to apply just one operator to deal with scenes with continuous change within a wide luminance range, such as various scenes in movies. To overcome this problem, we have developed a model based on psychophysical data involving wavelength discrimination within a wide luminance range, which provides us with clues about the change of color perception. That is, the spectral sensitivity shifts toward the short wavelengths and decreases according to the adaptation light levels. By integrating the wavelength discrimination into our model, the proposed operator enables us to compute the transition of color perception under a wide range of viewing conditions.Item Learning Strategies to Select Point Cloud Descriptors for 3D Object Classification: A Proposal(The Eurographics Association, 2014) Garstka, Jens; Peters, Gabriele; Mathias Paulin and Carsten DachsbacherWe propose a reinforcement learning approach for an adaptive selection and application of 3D point cloud feature descriptors for the purpose of 3D object classification. The result of the learning process is an autonomously learned strategy of selection of descriptors with the property that the successive application of these descriptors to a 3D point cloud yields high classification rates among a large number of object classes. The order in which the descriptors are applied to an unfamiliar point cloud depends on the features calculated in previous steps of the descriptor sequence, i.e., the sequence of descriptors depends on the object to be classified, thus it is highly adaptive. Our approach starts with a given number of descriptors and object classes, but it is able to adapt dynamically to changes in the environment. For example, further descriptors can be added during the learning process, and new object classes are created autonomously if necessary.Item HDR Imaging Using Augmented Lagrange Multipliers (ALM)(The Eurographics Association, 2014) Bhardwaj, Adit; Raman, Shanmuganathan; Mathias Paulin and Carsten DachsbacherWe consider the High Dynamic Range (HDR) imaging problem for real world scenes. We can change either the exposure time or the aperture while capturing multiple images of the scene to generate an HDR image. This paper addresses the HDR imaging problem for static and dynamic scenes when we do not have any knowledge of the camera settings. We have proposed a novel threshold for Augmented Lagrange Multipliers (ALM) framework which enables us to process the images getting rid of artifacts due to moving objects and defocus blur.