21,907 Hits in 9.2 sec

Entropy-Based Active Vision for a Humanoid Soccer Robot [chapter]

Andreas Seekircher, Tim Laue, Thomas Röfer
2011 Lecture Notes in Computer Science  
In this paper, we show how the estimation of a robot's world model can be improved by actively sensing the environment through considering the current world state estimate through minimizing the entropy  ...  Being originally computationally expensive, this approach is optimized to become executable in real-time on a robot with limited resources.  ...  Acknowledgements The authors would like to thank Armin Burchardt for his work at the ground truth system and all members of the team B-Human for providing the software base for this work.  ... 
doi:10.1007/978-3-642-20217-9_1 fatcat:djkm3s5e6ve3jfif2mkpdnomhm

On Foveated Gaze Control and Combined Gaze and Locomotion Planning [chapter]

Kolja Kuhnlenz, Georgios Lidoris, Dirk Wollherr, Martin Buss
2007 Humanoid Robots: New Developments  
This book presents a series of researches inspired by this ideal, carried through by various researchers worldwide, looking for to analyze and to discuss diverse subjects related to humanoid robots.  ...  The presented contributions explore aspects about robotic hands, learning, language, vision and locomotion.  ...  To incorporate the uncertainty about the state of the environment, (Moorehead et al., 2001) try to minimize the uncertainty of the robot about grid cells, by using entropy as a criterion.  ... 
doi:10.5772/4886 fatcat:a5ohookwn5acnjoj7huh27nrja

Active Monte Carlo Localization in Outdoor Terrains Using Multi-level Surface Maps [chapter]

Rainer Kümmerle, Patrick Pfaff, Rudolph Triebel, Wolfram Burgard
2007 Autonome Mobile Systeme 2007  
In contrast to passive approaches our approach actively selects the orientation of the laser range finder to improve the localization results.  ...  It applies a particle filter to estimate the full sixdimensional state of the robot.  ...  Whereas their approach is able to increase the efficiency of the localization by minimizing the expected entropy, Markov localization has high computational demands.  ... 
doi:10.1007/978-3-540-74764-2_5 dblp:conf/ams/KummerlePTB07 fatcat:bodm6ad7rvennhyveetckuninq

Learning efficient policies for vision-based navigation

Armin Hornung, Hauke Strasdat, Maren Bennewitz, Wolfram Burgard
2009 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems  
The learned policy minimizes the time to reach the destination and implicitly takes the impact of motion blur on observations into account.  ...  However, fast movements of a mobile robot typically reduce the performance of vision-based localization systems due to motion blur.  ...  Kwok and Fox [10] apply reinforcement learning to increase the performance of soccer-playing robots by active sensing. A camera is used for the localization of relevant objects on the soccer field.  ... 
doi:10.1109/iros.2009.5354634 dblp:conf/iros/HornungSBB09 fatcat:owpyyk4q4zabhiqdff52a5soly

Learning Dynamic Event Descriptions in Image Sequences

Harini Veeraraghavan, Nikolaos Papanikolopoulos, Paul Schrater
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
Experimental results demonstrating the efficacy of the learning algorithm and the event detection method applied to real-world video sequences are presented.  ...  Concretely we introduce a stochastic context-free grammar approach for representing the events and learn the event descriptors using an entropy minimization-based semisupervised method.  ...  Examples of the HMM-based approaches applied to detecting activities in video sequences include [7, 1, 5] .  ... 
doi:10.1109/cvpr.2007.383075 dblp:conf/cvpr/VeeraraghavanPS07 fatcat:u6m4r3ddhvefxc7hppv5qfz3xi

Efficient vision-based navigation

Armin Hornung, Maren Bennewitz, Hauke Strasdat
2010 Autonomous Robots  
We present a reinforcement learning approach to determine a navigation policy to reach the destination reliably and, at the same time, as fast as possible.  ...  In this article, we present a novel approach to learning efficient navigation policies for mobile robots that use visual features for localization.  ...  We apply Sarsa(λ ) RL (Wiering and Schmidhuber 1998) to determine the optimal policy which minimizes the time to reach the destination.  ... 
doi:10.1007/s10514-010-9190-3 fatcat:r6uuakouoje25dwk56pphjgary

Fast parametric viewpoint estimation for active object detection

Robert Eidenberger, Thilo Grundmann, Wendelin Feiten, Raoul Zoellner
2008 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems  
Most current solutions to active perception planning struggle with complex state representations or fast and efficient sensor parameter selection strategies.  ...  This paper presents an exclusively parametric approach for the state estimation and decision making process to achieve very low computational complexity and short calculation times.  ...  Since, the computational time is very short, the algorithm can be applied to real, everyday environments.  ... 
doi:10.1109/mfi.2008.4648083 dblp:conf/mfi/EidenbergerGFZ08 fatcat:tjage7sifngzvdnosiuuodgzom

Automated Camera Selection and Control for Better Training Support [chapter]

Adrian Ilie, Greg Welch
2013 Lecture Notes in Computer Science  
This need is being met by two related research efforts: approaches for automated camera selection and control, and computer vision-based approaches for automated extraction of relevant training feedback  ...  Physical training ranges have been shown to be critical in helping trainees integrate previously-perfected skills.  ...  ., Program Manager, led by Amela Sadagic (PI) at the Naval Post-graduate School, Greg Welch (PI) at UNC, and Rakesh Kumar (PI) and Hui Cheng (Co-PI) at Sarnoff.  ... 
doi:10.1007/978-3-642-39454-6_6 fatcat:kix6txcu65bcpaan5j6jdnnwdi

Topology-independent shape modeling scheme

Ravikanth Malladi, James A. Sethian, Baba C. Vemuri, Baba C. Vemuri
1993 Geometric Methods in Computer Vision II  
Our technique can be applied to model arbitrarily complex shapes, shapes with protrusions, and to situations where no a priori assumption about the object's topology can be made.  ...  Our method is based on the level set ideas developed by Osher & Sethian to follow propagating solid/liquid interfaces with curvature-dependent speeds.  ...  By adding suitable energy terms to the minimization, the user pushes the model out of a local minimum toward the desired solution.  ... 
doi:10.1117/12.146630 fatcat:s53bzzo45fhgxbglyrxoi7oiyi

Vision based approach for active selection of robot's localization action

E. Frontoni, A. Mancini, P. Zingaretti
2007 2007 Mediterranean Conference on Control & Automation  
Also better performances in computational time due to improvements in the vision system are shown.  ...  Results, obtained in a real scenario using a real robot, show improved performances in the number of steps needed to correctly localize the robot and in the localization error, compared with the classic  ...  CONCLUSIONS The paper advocates a new active vision based approach to mobile robot localization. In active localization the robot controls its various effectors to most efficiently localize itself.  ... 
doi:10.1109/med.2007.4433677 fatcat:xflnsufoyfcjlkp2bq3c7pol74

UAS see-and-avoid strategy using a fuzzy logic controller optimized by Cross-Entropy in Scaling Factors and Membership Functions

Changhong Fu, Miguel A. Olivares-Mendez, Pascual Campoy, Ramon Suarez-Fernandez
2013 2013 International Conference on Unmanned Aircraft Systems (ICUAS)  
This work aims to develop a novel Cross-Entropy (CE) optimization-based fuzzy controller for Unmanned Aerial Monocular Vision-IMU System (UAMVIS) to solve the seeand-avoid problem using its accurate autonomous  ...  localization information.  ...  ACKNOWLEDGMENT The work reported in this paper is the consecution of several research stages at the Computer Vision Group -Universidad Politécnica de Madrid.  ... 
doi:10.1109/icuas.2013.6564730 fatcat:6u3fiolrejbbdkhgpaase5fzay

Exploring information theory for vision-based volumetric mapping

R. Rocha, J. Dias, A. Carvalho
2005 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems  
The proposed framework was validated through experiments with a real mobile robot equipped with stereo-vision, in order to be further used on cooperative volumetric mapping with teams of mobile robots.  ...  Each mobile robot uses an entropy gradient-based exploration strategy, with the aim of maximizing information gain when building and improving a 3-D map upon measurements yielded by an on-board stereo-vision  ...  In a seminal work [11] , they used entropy minimization to actively localize a robot by minimizing the expected future uncertainty. Extensive research has been devoted to SLAM (e.g.  ... 
doi:10.1109/iros.2005.1545338 dblp:conf/iros/RochaDC05 fatcat:ydyfex5ytjfbdepx23db76buya

A Machine Vision Anomaly Detection System to Industry 4.0 Based on Variational Fuzzy Autoencoder

Wei Jiang, Konstantinos Demertzis
2022 Computational Intelligence and Neuroscience  
Using fuzzy entropy and Euclidean fuzzy similarity measurement maximizes the possibility of using nonlinear transformation through deterministic functions, thus creating an entirely realistic vision system  ...  One of the most important methods of active cybersecurity in Industry 4.0 is the detection of anomalies, i.e., the identification of objects, observations, events, or behaviors that do not conform to the  ...  Another way to export useful features is by applying sparse restrictions to the network.  ... 
doi:10.1155/2022/1945507 pmid:35341162 pmcid:PMC8942635 fatcat:642lw7f5tvgxjf4efqeti4zc24

Survey and Comparative Analysis on Entropy Usage for Several Applications in Computer Vision

Nitin Chamoli, Sneh Kukreja, Monika Semwal
2014 International Journal of Computer Applications  
A comparative analysis of different forms of entropy accordingly to their suitability for various applications has been discussed.  ...  The usage of entropy in the fields of image thresholding, image reconstruction, image segmentation, and incorporation of entropy in tackling real life problems have been mentioned categorically.  ...  [22] were the first ones to use entropy, and applied maximum entropy in astronomy imagery.  ... 
doi:10.5120/17088-7620 fatcat:v6y3q7hrrbgs5gbq4slnk3esiq

Ceiling mosaics through information-based SLAM

Jose Pascual Roda, Juan Manuel Saez, Francisco Escolano
2007 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems  
the entropy of the map.  ...  The only sensor of the robot is a digital camera oriented to the ceiling of the map, which is used to approximate the Simultaneous Localization and Mapping (SLAM) problem.  ...  Global rectification is performed by an entropy minimization algorithm, combined with a compression scheme to ensure the scalability of the problem.  ... 
doi:10.1109/iros.2007.4399134 dblp:conf/iros/RodaSE07 fatcat:4nvyigfetnf3jkbthyffvkd5v4
« Previous Showing results 1 — 15 out of 21,907 results