Filters








387 Hits in 3.4 sec

Robust color segmentation for the RoboCup domain

Z. Wasik, A. Saffiotti
Object recognition supported by user interaction for service robots  
We present a hybrid method for color segmentation based on seeded region growing (SRG) in which the initial seeds are provided by a conservative threshold color segmentation.  ...  Color segmentation is crucial in robotic applications, such as RoboCup, where the relevant objects can be distinguished by their color.  ...  For this reason, they are widely used in robotic applications, including the RoboCup domain.  ... 
doi:10.1109/icpr.2002.1048386 dblp:conf/icpr/WasikS02 fatcat:25l3tsdhezhilp4lfqghagw2uy

Self-Localization in the RoboCup Environment [chapter]

Luca Iocchi, Daniele Nardi
2000 Lecture Notes in Computer Science  
The technique is adequate for indoor office-like environments, and specifically for those environments that can be represented by a set of segments.  ...  In this paper we present a self-localization method that is based on the Hough Transform for matching a geometric reference map with a representation of range information acquired by the robot's sensors  ...  Furthermore, we believe that the RoboCup environment is a good benchmark for the use of the method in real office-like environments, since several features are in common with the RoboCup environment: segment-based  ... 
doi:10.1007/3-540-45327-x_26 fatcat:yj46fqn6rramzof6tgmwjncufq

A Robust and Calibration-Free Vision System for Humanoid Soccer Robots [chapter]

Ingmar Schwarz, Matthias Hofmann, Oliver Urbann, Stefan Tasse
2015 Lecture Notes in Computer Science  
It is real-time capable, robust towards lighting changes and designed to minimize calibration. We describe the structure of the processor along with major ideas behind object recognition.  ...  This paper presents a vision system which is designed to be used by the research community in the Standard Platform League 1 (SPL) and potentially in the Humanoid League 2 (HL) of the RoboCup.  ...  We exploit domain knowledge to achieve lighting-independence, and ensure robustness against motion blur and colorimetric shift.  ... 
doi:10.1007/978-3-319-29339-4_20 fatcat:vh2c7tgzqbdmxk2x3rat4u65qm

Using Saliency-Based Visual Attention Methods for Achieving Illumination Invariance in Robot Soccer [chapter]

F. Serhan Daniş, Tekin Meriçli, H. Levent Akın
2013 Lecture Notes in Computer Science  
In this paper, we investigate the suitability of biologically inspired saliency-based visual attention models for developing robust vision systems for soccer playing robots while focusing on the illumination  ...  However, the current vision systems are still brittle and they require exhaustive and repeated color calibration procedures to perform acceptably well.  ...  Using color segmentation as the basis of the developed vision systems still appears to be the most popular approach among the teams of various RoboCup leagues although most of the color segmentation based  ... 
doi:10.1007/978-3-642-39250-4_25 fatcat:vvfnaltvmfctbjrdibuijzjz34

Recognition of standard platform RoboCup goals

José María Cañas Plaza, Eduardo Perdices García, Tomás González Sánchez, Domenec Puig Valls
2010 Journal of Physical Agents (JoPha)  
In this way, this paper introduces a fast and robust methodology based on Artificial Vision techniques for the recognition of the goals utilized in the RoboCup Standard Platform League.  ...  First, 2D images captured by the front camera mounted in the head of a Nao robot are used to recognize the goals through a color based geometrical segmentation method.  ...  [8] developed a fast and robust color image segmentation method yielding significant regions in the context of the RoboCup.  ... 
doi:10.14198/jopha.2010.4.1.03 fatcat:k7a4ioh6cjdfrmhwxjw4it2rqi

A Vision Based System for Goal-Directed Obstacle Avoidance [chapter]

Jan Hoffmann, Matthias Jüngel, Martin Lötzsch
2005 Lecture Notes in Computer Science  
We present a complete system for obstacle avoidance for a mobile robot. It was used in the RoboCup 2003 obstacle avoidance challenge in the Sony Four Legged League.  ...  Obstacles are detected on a level surface of known color(s).  ...  They are subdivided into segments using a simple threshold edge detection algorithm. The average color of each segment is assigned to a color class based on a color look-up table.  ... 
doi:10.1007/978-3-540-32256-6_35 fatcat:r52vbdpoufc63ou2lziwressou

Real-time vision on a mobile robot platform

M. Sridharan, P. Stone
2005 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems  
The constraints imposed on the problem as a result of having to perform all processing, including segmentation and object detection, in real-time onboard the robot eliminate the possibility of using some  ...  stateof-the-art methods that otherwise might apply.  ...  A variety of previous approaches have been implemented on the Aibo robots for use in the RoboCup domain including the use of decision trees [23] the creation of axis-parallel rectangles in the color  ... 
doi:10.1109/iros.2005.1545540 dblp:conf/iros/SridharanS05 fatcat:xrrdo2hcivbyllvhiyknmz6b44

A Deep Learning Approach for Object Recognition with NAO Soccer Robots [chapter]

Dario Albani, Ali Youssef, Vincenzo Suriani, Daniele Nardi, Domenico Daniele Bloisi
2017 Lecture Notes in Computer Science  
The approach is designed to be used by NAO robots and is made of two stages: Image region segmentation for reducing the search space and Deep Learning for validation.  ...  The used data set is made available for the community.  ...  In this paper, we propose a method for validating the results provided by color segmentation approaches.  ... 
doi:10.1007/978-3-319-68792-6_33 fatcat:xrwkdq5u65gvpnc7477bqxzhyy

From Vision to Realtime Motion Control for the RoboCup Domain

Dennis Bruijnen, Wouter Aangenent, Jeroen van Helvoort, Rene van de Molengraft
2007 Control Applications (CCA), Proceedings of the IEEE International Conference on  
The vision module includes: (i) color calibration using a union of convex hulls to select an area in the 3D-colorspace, (ii) automatic calibration of the mapping from the camera image to the field via  ...  Vision is only used to compensate for slow drift caused by slip in the wheel-surface contact.  ...  Color Segmentation The RoboCup domain typically uses color segmentation based on rectangular thresholds because of its simplicity and computational cheap implementation [2] .  ... 
doi:10.1109/cca.2007.4389288 dblp:conf/IEEEcca/BruijnenAHM07 fatcat:ktofijk6u5bz5frc4mhr4kn63q

From Vision to Realtime Motion Control for the RoboCup Domain

Dennis Bruijnen, Wouter Aangenent, Jeroen van Helvoort, Rene van de Molengraft
2007 Control Applications (CCA), Proceedings of the IEEE International Conference on  
The vision module includes: (i) color calibration using a union of convex hulls to select an area in the 3D-colorspace, (ii) automatic calibration of the mapping from the camera image to the field via  ...  Vision is only used to compensate for slow drift caused by slip in the wheel-surface contact.  ...  Color Segmentation The RoboCup domain typically uses color segmentation based on rectangular thresholds because of its simplicity and computational cheap implementation [2] .  ... 
doi:10.1109/isic.2007.4359659 fatcat:ai2gq5unsra55csprqzwccfj74

RoboCup@Home: Demonstrating Everyday Manipulation Skills in RoboCup@Home

Jorg Stuckler, Dirk Holz, Sven Behnke
2012 IEEE robotics & automation magazine  
We thank the members of team NimbRo Kathrin Gr€ ave, David Droeschel, Jochen Kl€ aß, Michael Schreiber, and Ricarda Steffens for their dedicated efforts before and during the competition.  ...  Acknowledgments This research has been partially funded by the FP7 ICT-2007.2.2 project ECHORD (grant agreement 231143) experiment ActReMa.  ...  While the annual RoboCup competitions are best known for their soccer leagues, they also feature two leagues in other domains-the RoboCup Rescue league for robots supporting first responders and RoboCup  ... 
doi:10.1109/mra.2012.2191993 fatcat:pz2vpa66l5b5npuubrprhunphy

Agilo RoboCuppers: RoboCup Team Description [chapter]

Sebastian Buck, Robert Hanek, Michael Klupsch
2001 Lecture Notes in Computer Science  
A fast feature extraction based on the image processing library HALCON provides the data necessary for the onboard scene interpretation.  ...  This paper describes the Agilo RoboCuppers 1 -the RoboCup team of the image understanding group (FG BV) at the Technische Universität München.  ...  These constraints are matched with the extracted image features such as color regions and line segments (see Fig. 2 (b) and 4) .  ... 
doi:10.1007/3-540-45324-5_88 fatcat:xq4egpzgozfunpvmqb74mtt6cm

Color Classification and Object Recognition for Robot Soccer Under Variable Illumination [chapter]

Nathan Lovell, Vladimir Estivill-Castro
2007 Robotic Soccer  
The object recognition system is efficient for the RoboCup environment and is robust to changes in color intensity and temperature.  ...  It is apparent then that edge detection, rather than color segmentation, is a better basis for object recognition systems if robustness to dynamic lighting conditions is a requirement.  ... 
doi:10.5772/5125 fatcat:esoobe5lx5fi5eemahqausbq34

The 2012 UT Austin Villa Code Release [chapter]

Samuel Barrett, Katie Genter, Yuchen He, Todd Hester, Piyush Khandelwal, Jacob Menashe, Peter Stone
2014 Lecture Notes in Computer Science  
This architecture is designed to be flexible and robust while enabling easy testing and debugging of code. The vision code was designed for easy use in creating color tables and debugging problems.  ...  This code release will provide a solid foundation for new RoboCup teams and for researchers that use the Naos.  ...  We thank all the previous team members for their important contributions, especially Michael Quinlan and Mohan Sridharan.  ... 
doi:10.1007/978-3-662-44468-9_49 fatcat:hn727zrfkbgaddwnj6oxabx5cy

Humanoid Robot Detection Using Deep Learning: A Speed-Accuracy Tradeoff [chapter]

Mohammad Javadi, Sina Mokhtarzadeh Azar, Sajjad Azami, Saeed Shiry Ghidary, Soroush Sadeghnejad, Jacky Baltes
2018 Lecture Notes in Computer Science  
Recent advances in computer vision have made the detection of landmarks on the soccer field easier for teams.  ...  The approach performs edge based image segmentation in order to reduce the search space and then a CNN validates the detection in the second stage.  ...  For image segmentation, despite the fact that color segmentation is common in RoboCup Soccer Leagues [3] , Ma et al.  ... 
doi:10.1007/978-3-030-00308-1_28 fatcat:5vxuaqyud5bidet2jsqk52wa34
« Previous Showing results 1 — 15 out of 387 results