Filters








164 Hits in 4.6 sec

Energy Efficient Robot Rendezvous

Pawel Zebrowski, Yaroslav Litus, Richard T. Vaughan
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
The second method is a computationally cheap heuristic that computes a local heading for each robot: by iterating this method, all robots arrive at the globally optimal location.  ...  The first method computes an approximate globally optimal meeting point using numerical simplex minimization.  ...  Local Rendezvous Method The local method works by computing the conjugate gradient and prescribing the direction each robot should move in based on this gradient.  ... 
doi:10.1109/crv.2007.27 dblp:conf/crv/ZebrowskiLV07 fatcat:ssz5uc7edrfpjnxb5ueaiwzwfa

Camera Sensor Model for Visual SLAM

Jing Wu, Hong Zhang
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
We conclude that the error distribution of a camera sensor follows a Gaussian distribution, based on the Geary's test, and the magnitude of the error variance is linearly related to the range between the  ...  camera and the features being observed.  ...  Acknowledgments The authors would like to thank Xiang Wang and Jon Klippenstein for their discussions and insightful comments.  ... 
doi:10.1109/crv.2007.14 dblp:conf/crv/WuZ07 fatcat:bsv6wclxqra4fo6agsrqqm5wdm

Extrinsic Recalibration in Camera Networks

Chris Hermans, Maarten Dumont, Philippe Bekaert
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
Recalibration is done using pairs of essential matrices, based on image point correspondences. Unlike other approaches, we do not explicitly compute any 3D structure for our calibration purposes.  ...  In this paper we present an efficient algorithm to detect when the extrinsic parameters of a camera are no longer valid, and reintegrate the displaced camera into the previously calibrated camera network  ...  Acknowledgments The authors acknowledge financial support on a structural basis from the European Regional Development Fund (ERDF) and the Flemish Government.  ... 
doi:10.1109/crv.2007.31 dblp:conf/crv/HermansDB07 fatcat:au5qr7envrbtxdguewp3jkxyiq

Special Session: Second Workshop on Face Processing in Video

2005 The 2nd Canadian Conference on Computer and Robot Vision (CRV'05)  
We would also like to thank the organizers of CRV 2005 and the IEEE for helping us organize this workshop and prepare the proceedings.  ...  We would like to take this opportunity to thank the program committee for their insightful and thorough review of the submissions to this workshop.  ...  In computer vision and pattern recognition considerable progress has been made in the design of systems that can automatically analyze faces from stills.  ... 
doi:10.1109/crv.2005.77 dblp:conf/crv/X05b fatcat:esbaijko7jfwvgzbbjeqzh3ydq

Computing View-normalized Body Parts Trajectories

Frederic Jean, Robert Bergevin, Alexandra Branzan Albu
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
The proposed approach first extracts the 2D trajectories of both feet and of the head from tracked silhouettes. On that basis, it segments the walking trajectory into piecewise linear segments.  ...  This paper proposes an approach to compute viewnormalized body part trajectories of pedestrians from monocular video sequences.  ...  Acknowledgements: This work is supported by NSERC and FQRNT grants and by Precarn inc.  ... 
doi:10.1109/crv.2007.19 dblp:conf/crv/JeanBA07 fatcat:3c3zk4inffbqvbyxkt7lfpbw64

Surface-Based GICP

Michiel Vlaminck, Hiep Luong, Wilfried Philips
2018 2018 15th Conference on Computer and Robot Vision (CRV)  
Doing so, we are able to deal better with the artefacts that are typically present in lidar point clouds, including an inhomogeneous and sparse point density, noise and missing data.  ...  Experiments on lidar sequences of the KITTI benchmark demonstrate that we are able to substantially reduce the positional error compared to the original GICP algorithm.  ...  The kernel weights are then computed for each point as follows: w j = e − 1 2σ i (fj −fi) 2 (14) Using these weights, the distance kernel weighted centroid and covariance,x i and Σ w i , can be computed  ... 
doi:10.1109/crv.2018.00044 dblp:conf/crv/VlaminckLP18 fatcat:csvrn7jodbccbij5fusxzy57t4

Efficient indexing for strongly similar subimage retrieval

Gerhard Roth, William Scott
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
In subimage search, the user selects an image region and the retrieval system attempts to find matching subimages in an image database that are strongly similar.  ...  The effectiveness of the approach is demonstrated experimentally on a variety of image databases.  ...  A descriptor is computed from the gradients of the image patch around the interest point at the computed scale and orientation.  ... 
doi:10.1109/crv.2007.24 dblp:conf/crv/RothS07 fatcat:kvup7rb2j5hrlhz4p6yd3jwtce

A non-myopic approach to visual search

Julia Vogel, Kevin Murphy
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
We demonstrate this in simulation using POMDP models, focussing on two special cases: where the target object is contained within the related object, and where the target object is spatially adjacent to  ...  Instead it is more efficient and leads to higher detection accuracy to first look for other related objects, that are easier to detect.  ...  Acknowledgments We would like to thank Pantelis Elinas, Per-Erik Forssen, Jim Little, and Rob Sim for helpful comments on earlier drafts of the manuscript.  ... 
doi:10.1109/crv.2007.5 dblp:conf/crv/VogelM07 fatcat:zodbnnqpn5hnpjuvedgiw2xzle

Extending Graph-Cut to Continuous Value Domain Minimization

Michael Felsberg
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
Many practical problems in the area of computer vision are continuous-valued, and discrete optimization methods of graph-cut type cannot be applied directly.  ...  The first method is an add-on for multiple-label graph-cut. In the second one, binary graph-cut is firstly used to generate regions of support within different ranges of the signal.  ...  In many practical problems of computer vision, as for instance disparity estimation, we would like to have machine accuracy representation for the estimate.  ... 
doi:10.1109/crv.2007.29 dblp:conf/crv/Felsberg07 fatcat:e4v6scpa45cavnrbw4ofvqujqm

Screen-Camera Calibration using a Spherical Mirror

Yannick Francken, Chris Hermans, Philippe Bekaert
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
Recent developments in the consumer market have indicated that the average user of a personal computer is likely to also own a webcam.  ...  In addition, if the user provides the algorithm with the exact radius of the sphere in millimeters, the scale of the computed solution is uniquely defined.  ...  Acknowledgments The authors acknowledge financial support on a structural basis from the European Regional Development Fund (ERDF), the Flemish Government and the Flemish Interdisciplinary institute for  ... 
doi:10.1109/crv.2007.59 dblp:conf/crv/FranckenHB07 fatcat:srgof5mmwvbx5myq7thfkzd5rm

Using a Raster Display for Photometric Stereo

Nathan Funk, Yee-Hong Yang
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
Experiments on synthetic and real images demonstrate how the depth map of an object can be recovered using only a camera and a computer monitor.  ...  The setup has the advantage over other alternatives in that it is relatively inexpensive and uses commonly available components.  ...  Acknowledgements We would like to express our sincere thanks for the financial support provided by NSERC and iCORE.  ... 
doi:10.1109/crv.2007.66 dblp:conf/crv/FunkY07 fatcat:oyiafqlngbegzftod7x2kdzrhm

Quantitative Evaluation of Feature Extractors for Visual SLAM

Jonathan Klippenstein, Hong Zhang
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
We present results from a typical indoor environment in the form of recall/precision curves, and also investigate the effect of increasing distance between image viewpoints on extractor performance.  ...  We conclude by presenting guidelines for selecting a feature extractor for visual SLAM based on our experiments.  ...  Acknowledgments Research was supported in part by the Natural Sciences and Engineering Research Council of Canada (NSERC) and the Informatics Circle of Research Excellence (iCORE).  ... 
doi:10.1109/crv.2007.52 dblp:conf/crv/KlippensteinZ07 fatcat:ujbbeymkgfdzxojdqlteo73lza

INVICON: A Toolkit for Knowledge-Based Control of Vision Systems

Olena Borzenko, Yves Lesperance, Michael Jenkin
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
To perform as desired in a dynamic environment a vision system must adapt to a variety of operating conditions by selecting vision modules, tuning their parameters, and controlling image acquisition.  ...  This paper presents the IN-VICON toolkit, based on the IndiGolog agent programming language with elements from control theory.  ...  Tools for Vision and Robotics. One limitation of IN- VICON is that it only supports the vision controller-side of system development.  ... 
doi:10.1109/crv.2007.41 dblp:conf/crv/BorzenkoLJ07 fatcat:nfbbpzv7l5fdfl4qv3o55kdsam

Dense Stereo Range Sensing with Marching Pseudo-Random Patterns

Danick Desjardins,, Pierre Payeur
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
Pseudo-random codes are used to create artificial textures on a scene which are extracted and grouped in a confidence map to ensure reliable feature matching between pairs of images taken from two cameras  ...  Depth estimation is performed on corresponding points with progressive refinement as the pseudo-random pattern projection is marched over the scene to increase the density of matched features, and achieve  ...  The authors gratefully acknowledge the financial support from Ontario Centres of Excellence (CITO) and the collaboration of Neptec Design Group.  ... 
doi:10.1109/crv.2007.22 dblp:conf/crv/DesjardinsP07 fatcat:kug7zo7mcfe6dlrp3futdvmc3e

Figure-ground segmentation using a hierarchical conditional random field

Jordan Reynolds, Kevin Murphy
2007 Fourth Canadian Conference on Computer and Robot Vision (CRV '07)  
We demonstrate good results for detecting and segmenting cows, cats and cars on the very challenging Pascal VOC dataset.  ...  Since our classifiers only rely on color and texture, they can handle deformable (non-rigid) objects such as animals, even under severe occlusion and rotation.  ...  and Daniel Eaton for their comments on the paper.  ... 
doi:10.1109/crv.2007.32 dblp:conf/crv/ReynoldsM07 fatcat:7r7sod6bzjevjhzbwkvwlv63bm
« Previous Showing results 1 — 15 out of 164 results