Filters








10,031 Hits in 4.7 sec

Fast synthetic vision, memory, and learning models for virtual humans

J.J. Kuffner, J.-C. Latombe
Proceedings Computer Animation 1999  
This paper presents a simple and efficient method of modeling synthetic vision, memory, and learning for autonomous animated characters in real-time virtual environments.  ...  The synthetic vision and memory update rules can handle dynamic environments where objects appear, disappear, or move around unpredictably.  ...  Acknowledgments The authors wish to thank the Stanford Computer Graphics Laboratory for allowing them to utilize their rendering hardware and video equipment during these experiments.  ... 
doi:10.1109/ca.1999.781205 dblp:conf/ca/KuffnerL99 fatcat:ti5lbhljxjgrxctbkhs22s4azm

An artificial life environment for autonomous virtual agents with multi-sensorial and multi-perceptive features

Toni Conde, Daniel Thalmann
2004 Computer Animation and Virtual Worlds  
We have developed three novel methodologies to map the information coming from the virtual sensors of vision, audition and touch as well as that of the virtual environment in the form of a 'cognitive map  ...  The acquisition steps of signals, filtering, selection and simplification intervening before proprioception, active and predictive perception are integrated into virtual sensors and a virtual environment  ...  It uses a 2-level hierarchical approach: Synthetic World In synthetic vision, the vision models for an AVA are different from those used in behavioral robotics.  ... 
doi:10.1002/cav.34 fatcat:bjzak32hbvbivptxhr5uohpn6e

Synthetic vision-based perceptual attention for augmented reality agents

Sejin Oh, Woonhyuk Baek, Woontack Woo
2010 Computer Animation and Virtual Worlds  
We describe our model for synthetic vision-based perceptual attention for autonomous agents in augmented reality (AR) environments.  ...  Since virtual and physical objects coexist in their environment, such agents must adaptively perceive and attend to objects relevant to their goals.  ...  ACKNOWLEDGMENTS This research was supported in part by the CTI development project, and in part by the CT R&D Program 2010 of KOCCA and MCST, South Korea.  ... 
doi:10.1002/cav.368 fatcat:dokmpdmz2bftjmfflpntykhi4a

Synthetic Vision and Memory for Autonomous Virtual Humans

C. Peters, C. O'Sullivan
2002 Computer graphics forum (Print)  
A memory model based on "stage theory", the dominant view of memory from the field of cognitive psychology, is presented for application to autonomous virtual humans.  ...  The virtual human senses external stimuli through a synthetic vision system. The vision system incorporates multiple modes of vision in order to accommodate a perceptual attention approach.  ...  Kuffner and Latombe [5] provide real-time synthetic vision, memory and learning, and apply it to the navigation of animated characters, using the synthetic vision system from [7] . Badler et al.  ... 
doi:10.1111/1467-8659.00632 fatcat:v7qpvpmel5g6bmkvemdqhjze24

Autonomous virtual actors based on virtual sensors [chapter]

Daniel Thalmann, Hansrudi Noser, Zhiyong Huang
1997 Lecture Notes in Computer Science  
After a brief description of the perception action principles with a few simple examples, we emphasize the concept of virtual sensors for virtual humans.  ...  In particular, we describe in details our experiences in implementing virtual vision, tactile and audition.  ...  The research was supported by the Swiss National Science Research Foundation, the Federal Office for Education and Science, and is part of the Esprit Project HUMANOID and HUMANOID-2.  ... 
doi:10.1007/bfb0030568 fatcat:wrdxm7nob5cv7ltnbzmea5adc4

Towards Autonomous, Perceptive, and Intelligent Virtual Actors [chapter]

Daniel Thalmann, Hansrudi Noser
1999 Lecture Notes in Computer Science  
We emphasize the concept of virtual sensors for virtual humans.  ...  In particular, we describe our experiences in implementing virtual sensors such as vision sensors , tactile sensors, and hearing sensors.  ...  The research was supported by the Swiss National Science Research Foundation and the Federal Office for Education and Science.  ... 
doi:10.1007/3-540-48317-9_19 fatcat:mlppq6jcmnaptcd2oulnpcy4i4

Towards Autonomous Synthetic Actors [chapter]

Hansrudi Noser, Daniel Thalmann
1998 Cyberworlds  
In particular, the paper describes an animation approach where synthetic vision is used for navigation by a synthetic actor.  ...  With such a system, we should be able to create simulations of situations such as virtual humans moving in a complex environment they may know and recognize, or playing ball games based on their visual  ...  The authors are grateful to Olivier Renault for the development of local navigation and Zhyang Huang and Mrs. Japon for the tennis sequence.  ... 
doi:10.1007/978-4-431-67941-7_9 fatcat:2okokefxyzht7n2v47c5eerv5y

Using a virtual world for robot planning

D. Paul Benjamin, John V. Monaco, Yixia Lin, Christopher Funk, Damian Lyons, Jerome J. Braun
2012 Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2012  
As the robot runs, its virtual model diverges from physical reality, and errors grow.  ...  The software components of this architecture include PhysX for the virtual world, OpenCV and the Point Cloud Library for visual processing, and the Soar cognitive architecture that controls the perceptual  ...  Finally, it permits us to test our architecture on robotic versions of well-known cognitive tasks and explore how robot learning might be related to human learning.  ... 
doi:10.1117/12.923446 fatcat:2sjh4iu2yfeobi6gjkzrbfyggm

Using Synthetic Vision for Autonomous Non-Player Characters

Sebastian Enrique, Alan Watt, Steve Maddock, Fabio Policarpo
2006 Inteligencia Artificial  
In this paper, we discuss the role and utility of synthetic vision in computer games.  ...  We present an implementation of a synthetic vision module based on two viewports rendered in real-time, one representing static information and the other dynamic, with false colouring being used for object  ...  However, despite the ease of producing a synthetic vision, it seems to be only an occasionally employed model in computer games and virtual reality.  ... 
doi:10.4114/ia.v7i21.818 fatcat:ymiuat67ujcapoputhowmgc274

Digital actors for interactive television

N. Magnenat Thalmann, D. Thalmann
1995 Proceedings of the IEEE  
In particular, we describe the integration of motion control techniques, autonomy based on synthetic sensors and facial communication.  ...  An integrated and functional system for the animation of digital actors is presented.  ...  Acknowledgments The authors would like to thank Ronan Boulic, Zhyong Huang, Prem Kalra, Hansrudi Noser and Igor Pandzic for their participation to the projects.  ... 
doi:10.1109/5.390120 fatcat:5krpvuebbva4jbksi6oh45yufe

Design of Neuromorphic Cognitive Module based on Hierarchical Temporal Memory and Demonstrated on Anomaly Detection

Marek Otahal, Michal Najman, Olga Stepankova
2016 Procedia Computer Science  
HTM is framed within other common AI/ML approaches and we conclude that HTM is a plausible and useful model for designing a direct brain-extension module and draft a design of a neuromorphic interface  ...  We propose to design such neuro-module using Hierarchical Temporal Memory (HTM) which is a biologically-inspired model of the mammalian neocortex.  ...  HTM is a memory-based learning system which performs unsupervised on-line learning and continuous predictions; where the role of time is implicit 2 and allows for contextual Anomaly Detection (AD).  ... 
doi:10.1016/j.procs.2016.07.430 fatcat:3dtif4xxd5c7niwsgyjyi52cva

Human Action Recognition Based on Body Segmentation Models

Catherine Huyghe, Nacim Ihaddadene, Thomas Haessle, Chabane Djeraba
2021 2021 International Conference on Content-Based Multimedia Indexing (CBMI)  
Human action recognition in videos is an important issue in computer vision.  ...  We propose an approach based on the integration of partial or global human body segmentation in the classification process to deal with partial movements and immobility.  ...  To perform this segmentation, we relied on existing depth learning models for human part segmentation and in particular on "Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation  ... 
doi:10.1109/cbmi50038.2021.9461874 fatcat:bi6totnnsrc35pbi6eatq3b5ni

Navigation for digital actors based on synthetic vision, memory, and learning

Hansrudi Noser, Olivier Renault, Daniel Thalmann, Nadia Magnenat Thalmann
1995 Computers & graphics  
This paper describes an animation approach where synthetic vision is used for navigation by a digital actor.  ...  path searching, obstacle avoidance, and internal knowledge representation with learning and forgetting characteristics.  ...  Acknowledgments The authors are grateful to Hans Martin Werner and Russell Turner for reviewing the English text. This research was sponsored by the Swiss National Foundation for Scientific Research.  ... 
doi:10.1016/0097-8493(94)00117-h fatcat:zpeuss766fh2rbnldupg6h5cty

Methodology for Building Synthetic Datasets with Virtual Humans [article]

Shubhajit Basak, Hossein Javidnia, Faisal Khan, Rachel McDonnell, Michael Schukat
2020 arXiv   pre-print
Recent advances in deep learning methods have increased the performance of face detection and recognition systems.  ...  In particular, we make use of a 3D morphable face model for the rendering of multiple 2D images across a dataset of 100 synthetic identities, providing full control over image variations such as pose,  ...  This synthetic data can be used for machine learning tasks in several ways: • Synthetically generated data can be used to train the model directly and subsequently applied the model to real-world data.  ... 
arXiv:2006.11757v1 fatcat:njk7mbtmszc3tjqsq3gxa6q6fm

Complex Deep Learning and Evolutionary Computing Models in Computer Vision

Li Zhang, Chee Peng Lim, Jungong Han
2019 Complexity  
In this special issue, recent advances with respect to mathematical modeling, simulation, and/or analysis of deep learning and evolutionary computing models for undertaking complex phenomena in computer  ...  . e advent of deep learning and associated paradigms such as evolutionary computing models has propelled computer vision to the next level, solving a variety of complex problems in diverse applications  ...  and less preprocessing than some existing machine learning models.  ... 
doi:10.1155/2019/1671340 fatcat:wars4wlyxbc5rgf2huppco2gmu
« Previous Showing results 1 — 15 out of 10,031 results