22 Hits in 5.2 sec

Quadrotor Helicopter Flight Control Using Hough Transform and Depth Map from a Microsoft Kinect Sensor

John Stowers, Michael P. Hayes, Andrew Bainbridge-Smith
2011 IAPR International Workshop on Machine Vision Applications  
The Microsoft Kinect is a new, low cost game controller peripheral that calculates a depth map of the environment with good accuracy and high rate.  ...  In this paper we use the calibrated output of the depth sensor to obtain an accurate absolute depth map.  ...  Figure 6 shows the algorithm applied to a single image from a sequence captured during flight.  ... 
dblp:conf/mva/StowersHB11 fatcat:vkwr4b6csvgbneu7fnr7baceym

Fast and accurate environment modeling using three-dimensional occupancy grids

Katrin Pirker, Matthias Ruther, Horst Bischof, Gerald Schweighofer
2011 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)  
In our experiments we compare our method with a state-of-the-art mapping procedure. Our results demonstrate that we achieve better results.  ...  Building a dense and accurate environment model out of range image data faces problems like sensor noise, extensive memory consumption or computation time.  ...  We captured a total of 181 depth images with a resolution of axis at 4 • .  ... 
doi:10.1109/iccvw.2011.6130377 dblp:conf/iccvw/PirkerRBS11 fatcat:rjjaiuosyrgora6bmyipm6s3jy

Tracking Large Variable Numbers of Objects in Clutter

M. Betke, D.E. Hirsh, A. Bagchi, N.I. Hristov, N.C. Makris, T.H. Kunz
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
We propose statistical data association techniques for visual tracking of enormously large numbers of objects.  ...  We do not assume any prior knowledge about the numbers involved, and the objects may appear or disappear anywhere in the image frame and at any time in the sequence.  ...  We thank Lisa Premerlani, Shuang Tang, and Marianne Procopio for data analysis and implementation support, and Edward Lee, Jonathan Reichard, and Luise Allen for data collection.  ... 
doi:10.1109/cvpr.2007.382994 dblp:conf/cvpr/BetkeHBHMK07 fatcat:uqcwbeuxvfaflp55er2sm5ss4y

Rufael Mekuria

2017 ACM SIGMultimedia Records  
Plenoptic cameras try to capture the light fields produced by the 3D scene by capturing for each (x,y,z) the luminance radiated in different directions ( , ) over any range of wavelengths λ at every time  ...  Vasuvedan et al. proposed a 3D tele-immersion system for capturing and rendering. This system can in real-time reconstruct humans in the scene with high level of detail [53] .  ...  Appendix A 3D Audio Visual Capture Model -Components and interfaces of a 3D A/V system Legend a.  ... 
doi:10.1145/3129151.3129159 fatcat:sws54gzf4jaszoq7s43wjlgtju

Biologically Inspired Visual Control of Flying Robots [article]

John Ross Stowers, University Of Canterbury
All algorithms ran on the robot, in real-time or better, and hypotheses were always verified with flight experiments.  ...  The scope of this thesis is experimenting with biologically inspired visual control of flying robots through information processing, models of the environment, and flight behaviour.  ...  Images are captured at 640 × 480 pixels, at 15 times per second. Each image is taken with a 15 ms shutter time. The camera is fitted to look directly at the ground.  ... 
doi:10.26021/2224 fatcat:c5n62vr5hrfirk5kvmvqsdt5fq

Foundations for Meaning and Understanding in Human-centric AI [article]

Steels, Luc (ed.)
2022 Zenodo  
A short conclusion identifying key research topics for meaning-based human-centric AI.  ...  Our explorations have yielded a wealth of insights: about understanding in general and the role of narratives in this process, about possible applications of meaningful AI in a diverse set of human-centred  ...  and rhetorics in economics and economic a↵airs; reminding me not to lose sight of a fundamental aspect of this ambitious project, its focus on the human beings, and on their use of language for (re)constructing  ... 
doi:10.5281/zenodo.6666819 fatcat:ia3wwkrfrrcmhfpxobqxvwtesi

Functional Animation [article]

Morten Lund
2016 The PhD Series of the Faculty of the Humanities  
Clay animation share the model and reuse properties with computerbased animation, but is based on camera-technology for capture of frames.  ...  as decisive for the success of this access to large datastructures.  ...  The method was to create samples of movement and then compare these samples. A state of the art investigation establishes a baseline for current standard within an area.  ... 
doi:10.5278/ fatcat:rqtof5pwfncfdhoxe3v5wt5ivy

Artificial Intelligence: An Introductory Course

1986 Telematics and informatics  
He would also like to thank three generations of students for their tolerance to a lecturer on natural language processing whose professional competence (if any) is mainly in the theory of computation.  ...  Thanks also to Mark Adler for translating LOGO programs into LISP.  ...  This might be a fair representation of a system that answers questions about a scene it sees through a TV camera or even about some specific body of data like airline timetables.  ... 
doi:10.1016/s0736-5853(86)80074-0 fatcat:c7ibfuwojfe7rh7kablclo7a24

ACM Classification 1998 I.3 Computer Graphics Visualization of Large and Unstructured Data Sets-IRTG Workshop

Ariane Middel, Inga Scheler, Hans Hagen, Ariane Middel, Inga Scheler, Hans Hagen, Dorothea Wagner, Daniel Burkhart, Bernd Hamann, Georg Umlauf, Fang Chen, Hans Hagen (+57 others)
2010 Ariane Middel   unpublished
For example, environmental monitoring systems are capable of measuring data at a very high resolution and in a large number of frequency bands.  ...  After three days of presentations and discussions the graduates spent their time on writing papers that cover the outcome of the program and give surveys on related topics.  ...  Acknowledgements This work is supported by International Research and Training Group at University of Kaiserslautern (IRTG) and Deutsche Forschungsgemeinschaft (DFG , German research foundation).  ... 

40 Years EMISA - Komplettband

2019 Entwicklungsmethoden für Informationssysteme und deren Anwendung: Fachtagung  
This led to a very varied programme, which is shown on the pages 195ff. Some reactions from participants: "Nochmals ganz herzlichen Dank für die schöne Tagung -ein ganz aussergewöhnliches Event!"  ...  This LNI volume contains the full papers selected from the submissions through a review process (three peer reviews per paper), shorter and longer contributions from the invited speakers, provided they  ...  It has been a joy to work with you on so many interesting research challenges for the past five years.  ... 
dblp:conf/emisa/X19 fatcat:nhx5xarczram7hhq4wkuwsipqa

Improved persistent grid mapping

Peter Houska, Michael Wimmer
The perspective mapping of the grid results in a view-dependent, continuous level-of-detail approximation of the terrain dataset.  ...  more faithful mipmap selection when sampling the heightmap, local terrain edge search for vertices within a certain proximity to the camera, and exploiting temporal coherence between frames.  ...  The approved original version of this thesis is available in print at TU Wien Bibliothek. Bibliography  ... 
doi:10.34726/hss.2019.27468 fatcat:bhcxwj2uq5ehtc54imsrfbatmm

Kompression, Modellierung und Echtzeit-Rendering von realistischen Material und Objekten

Nicolas Menzel, Multimedia Graphik, Guthe, Michael (Prof. Dr.)
The realism of a scene basically depends on the quality of the geometry, the illumination and the materials that are used.  ...  These deviations may be subtle, but also substantial, allowing for a wide spectrum of material appearances.  ...  Instead, the full dynamic range of a scene can be obtained by taking multiple photographs, each one with a different exposure time.  ... 
doi:10.17192/z2012.0791 fatcat:u2d324m46raplmswnraui3m5f4

Interactive restriction of a mobile robot's workspace in traditional and smart home environments [article]

Dennis Sprute, Universitäts- Und Landesbibliothek Sachsen-Anhalt, Martin-Luther Universität, Klaus Tönnies
For this purpose, a human has to specify restriction areas in an interaction process with a robot.  ...  Experimental results show that the laser pointer approach mostly features an acceptable performance on the user requirements but without a significant improvement with respect to a state-of-the-art solution  ...  Typical sensors are camera sensors integrated in the environment to capture images of the scene.  ... 
doi:10.25673/35091 fatcat:kjmlo4m2x5hebpsvtwkccfmvee

Geometric optimization and querying : exact & approximate [article]

Domagoj Matijevi, Universität Des Saarlandes, Universität Des Saarlandes
Given a stage represented by a line segment L and a set of lightsources represented by a set of points S in the plane, assign powers to the lightsources such that every point on the stage receives a sufficient  ...  By assuming that the amount of light arriving from a fixed lightsource decreases rapidly with the distance from the lightsource, this becomes an interesting geometric optimization problem.  ...  Part II Efficient Geometric Queries using WSPD Acknowledgments We would like to thank Sören Laue for a helpful conversations related to proof of Lemma 3.6 and Alexandra Zhilyakova for helping with  ... 
doi:10.22028/d291-25999 fatcat:25lpoednu5duzmsz6twex3hfvq

Virtual reality simulation of a smart eating table for handicapped people

Salih Rashid Majeed, Universitätsbibliothek Siegen
It is in line with the significant developments in the sector of artificial intelligent and robotic fields that have enabled the emergence of a new smart robot generation.  ...  We improved this arm by adding two systems, one for semantic camera system and one for sound. This will help people who cannot use their hands. An external micropho [...]  ...  labeled synthetic dataset, The 3D CAD models are generated and loaded in a calibrated environment on the simulator using Blender, a subset of the objects is chosen for generating a scene, the scenes are  ... 
doi:10.25819/ubsi/6401 fatcat:r5tp5jfz4zggxhvbbzrj2ytz2y
« Previous Showing results 1 — 15 out of 22 results