-
Theodore T. Blackmon,
Scott Thayer,
James Teza,
Vincent Broz,
James Osborn, and
Martial Hebert.
Virtual Reality Mapping System for Chernobyl Accident Site Assessment.
In Proceedings of the SPIE,
volume 3644,
pages 338-345,
February 1999.
Abstract: "Initiated by the Department of Energy's International Nuclear Safety Program, an effort is underway to deliver and deploy a telerobotic diagnostic system for structural evaluation and monitoring within the Chernobyl Unit-4 shelter. A mobile robot, named Pioneer, will enter the damaged Chernobyl structure and deploy devices to measure radiation, temperature, and humidity; acquire core samples of concrete structures for subsequent engineering analysis; and make photo-realistic three-dimensional (3-D) maps of the building interior. This paper details the later element, dubbed "C-Map", the Chernobyl Mapping System. C-Map consists of an automated 3-D modeling system using stereo computer vision along with an interactive, virtual reality (VR) software program to acquire and analyze the photo-realistic 3-D maps of the damaged building interior."
@inproceedings{Blackmon_1999_3747,
author = "Theodore T. Blackmon and Scott Thayer and James Teza and Vincent Broz and James Osborn and Martial Hebert",
title = "Virtual Reality Mapping System for Chernobyl Accident Site Assessment",
booktitle = "Proceedings of the SPIE",
month = "February",
year = "1999",
volume = "3644",
pages = "338-345",
abstract="Initiated by the Department of Energy's International Nuclear Safety Program, an effort is underway to deliver and deploy a telerobotic diagnostic system for structural evaluation and monitoring within the Chernobyl Unit-4 shelter. A mobile robot, named Pioneer, will enter the damaged Chernobyl structure and deploy devices to measure radiation, temperature, and humidity; acquire core samples of concrete structures for subsequent engineering analysis; and make photo-realistic three-dimensional (3-D) maps of the building interior. This paper details the later element, dubbed "C-Map", the Chernobyl Mapping System. C-Map consists of an automated 3-D modeling system using stereo computer vision along with an interactive, virtual reality (VR) software program to acquire and analyze the photo-realistic 3-D maps of the damaged building interior."
}
-
Vincent Broz,
Owen Carmichael,
Scott Thayer,
James Osborn, and
Martial Hebert.
ARTISAN: An Integrated Scene Mapping and Object Recognition System.
In American Nuclear Society 8th Intl. Topical Meeting on Robotics and Remote Systems,
April 1999.
American Nuclear Society.
(url)
(pdf)
Keywords:
3-D perception,
geometric modeling.
Abstract: "Integration of three-dimensional textured scene mapping and object recognition presents many opportunities for assisted automation. We present Artisan, a software package that synthesizes these elements to form a user-friendly whole. Artisan uses a variety of 3-D sensors, including laser range scanners and stereo systems, to acquire both image and range data. Artisan automatically finds the transformations between data taken at multiple sensor viewpoints using matching algorithms. The data from these viewpoints are then merged together to form an integrated textured map of the entire scene. Other user or sensor input can also inserted into the scene. Using object recognition with an expandable library of objects, Artisan can identify and locate simple and complex scene features. With this identity and transformation information, it is able to support many operations, including semi-automatic robotic teleoperation and navigation. After mapping and recognition, the identity, position, and orientation of the objects in the scene can be automatically transferred from the Artisan system into other software, including robotic teleoperation packages. Numerous opportunities for automation exist during the operations stage as a result of this increased world knowledge."
@inproceedings{1999-broz-amns,
author = "Vincent Broz and Owen Carmichael and Scott Thayer and James Osborn and Martial Hebert",
title = "ARTISAN: An Integrated Scene Mapping and Object Recognition System",
booktitle = "American Nuclear Society 8th Intl. Topical Meeting on Robotics and Remote Systems",
month = "April",
year = "1999",
publisher = "American Nuclear Society",
pdf="http://www.ri.cmu.edu/pub_files/pub2/broz_vincent_1999_1/broz_vincent_1999_1.pdf",
keywords="3-D perception, geometric modeling",
abstract="Integration of three-dimensional textured scene mapping and object recognition presents many opportunities for assisted automation. We present Artisan, a software package that synthesizes these elements to form a user-friendly whole. Artisan uses a variety of 3-D sensors, including laser range scanners and stereo systems, to acquire both image and range data. Artisan automatically finds the transformations between data taken at multiple sensor viewpoints using matching algorithms. The data from these viewpoints are then merged together to form an integrated textured map of the entire scene. Other user or sensor input can also inserted into the scene. Using object recognition with an expandable library of objects, Artisan can identify and locate simple and complex scene features. With this identity and transformation information, it is able to support many operations, including semi-automatic robotic teleoperation and navigation. After mapping and recognition, the identity, position, and orientation of the objects in the scene can be automatically transferred from the Artisan system into other software, including robotic teleoperation packages. Numerous opportunities for automation exist during the operations stage as a result of this increased world knowledge.",
url="http://www.ri.cmu.edu/pubs/pub_3507.html"
}
-
Owen Carmichael and
Martial Hebert.
3-D Cueing: A Data Filter For Object Recognition.
In IEEE Conference on Robotics and Automation (ICRA '99),
volume 2,
pages 944 - 950,
May 1999.
(url)
(pdf)
Keywords:
3-D perception,
geometric modeling.
Abstract: "Presents a method for quickly filtering range data points to make object recognition in large 3-D data sets feasible. The general approach, called "3-D cueing", uses shape signatures from object models as the basis for a fast, probabilistic classification system which rates scene points in terms of their likelihood of belonging to a model. This algorithm which could be used as a front-end for any traditional 3-D matching technique, is demonstrated using several models and cluttered scenes in which the model occupies between 1 percent and 50 percent of the data points."
@inproceedings{Carmichael_1999_2967,
author = "Owen Carmichael and Martial Hebert",
title = "3-D Cueing: A Data Filter For Object Recognition",
booktitle = "IEEE Conference on Robotics and Automation (ICRA '99)",
month = "May",
year = "1999",
volume = "2",
pages = "944 - 950",
pdf ="http://www.ri.cmu.edu/pub_files/pub2/carmichael_owen_1999_2/carmichael_owen_1999_2.pdf",
url="http://www.ri.cmu.edu/pubs/pub_2967.html",
keywords="3-D perception, geometric modeling",
abstract="Presents a method for quickly filtering range data points to make object recognition in large 3-D data sets feasible. The general approach, called "3-D cueing", uses shape signatures from object models as the basis for a fast, probabilistic classification system which rates scene points in terms of their likelihood of belonging to a model. This algorithm which could be used as a front-end for any traditional 3-D matching technique, is demonstrated using several models and cluttered scenes in which the model occupies between 1 percent and 50 percent of the data points."
}
-
Owen Carmichael,
Daniel Huber, and
Martial Hebert.
Large Data Sets and Confusing Scenes in 3-D surface Matching and Recognition.
In Proceedings of the Second International Conference on 3-D Digital Imaging and Modeling (3-DIM'99),
pages 358-367,
October 1999.
(url)
(pdf)
Keywords:
3-D perception,
geometric modeling.
Abstract: "In this paper, we report on recent extensions to a surface matching algorithm based on local 3-D signatures. This algorithm was previously shown to be effective in view registration of general surfaces and in object recogni-tion from 3-D model data bases. We describe extensions to the basic matching algorithm which will enable it to address several challenging, and often overlooked, problems encountered with real data. First, we describe extensions that allow us to deal with data sets with large variations in resolution and with large data sets for which computational efficiency is a major issue. The applicability of the enhanced matching algorithm is illustrated by an example application: the construction of large terrain maps and the construction of accurate 3-D models from unregistered views. Second, we describe extensions that facilitate the use of 3-D object recognition in cases in which the scene con-tains a large amount of clutter (e.g., the object occupies 1 of the scene) and in which the scene presents a high degree of confusion (e.g., the model shape is close to other shapes in the scene.) Those last two extensions involve learning recognition strategies from the descrip-tion of the model and from the performance of the recog-nition algorithm using Bayesian and memory-based learning techniques, respectively."
@inproceedings{Carmichael_1999_3196,
author = "Owen Carmichael and Daniel Huber and Martial Hebert",
title = "Large Data Sets and Confusing Scenes in 3-D surface Matching and Recognition",
booktitle = "Proceedings of the Second International Conference on 3-D Digital Imaging and Modeling (3-DIM'99)",
month = "October",
year = "1999",
pages = "358-367",
pdf ="http://www.ri.cmu.edu/pub_files/pub2/carmichael_owen_1999_1/carmichael_owen_1999_1.pdf",
url="http://www.ri.cmu.edu/pubs/pub_3196.html",
abstract="In this paper, we report on recent extensions to a surface matching algorithm based on local 3-D signatures. This algorithm was previously shown to be effective in view registration of general surfaces and in object recogni-tion from 3-D model data bases. We describe extensions to the basic matching algorithm which will enable it to address several challenging, and often overlooked, problems encountered with real data. First, we describe extensions that allow us to deal with data sets with large variations in resolution and with large data sets for which computational efficiency is a major issue. The applicability of the enhanced matching algorithm is illustrated by an example application: the construction of large terrain maps and the construction of accurate 3-D models from unregistered views. Second, we describe extensions that facilitate the use of 3-D object recognition in cases in which the scene con-tains a large amount of clutter (e.g., the object occupies 1 of the scene) and in which the scene presents a high degree of confusion (e.g., the model shape is close to other shapes in the scene.) Those last two extensions involve learning recognition strategies from the descrip-tion of the model and from the performance of the recog-nition algorithm using Bayesian and memory-based learning techniques, respectively.",
keywords="3-D perception, geometric modeling"
}
-
Peng Chang and
John Krumm.
Object Recognition with Color Cooccurrence Histogram.
In Proceedings of CVPR '99,
1999.
@inproceedings{Chang_1999_2657,
author = "Peng Chang and John Krumm",
title = "Object Recognition with Color Cooccurrence Histogram",
booktitle = "Proceedings of CVPR '99",
year = "1999"
}
-
Martial Hebert,
Robert MacLachlan, and
Peng Chang.
Experiments with Driving Modes for Urban Robots.
In Proceedings of SPIE,
1999.
(pdf)
@inproceedings{Hebert_1999_4045,
author = "Martial Hebert and Robert MacLachlan and Peng Chang",
title = "Experiments with Driving Modes for Urban Robots",
booktitle = "Proceedings of SPIE",
year = "1999",
pdf ="http://www.ri.cmu.edu/pub_files/pub3/hebert_martial_1999_1/hebert_martial_1999_1.pdf"
}
-
Daniel Huber and
Martial Hebert.
A New Approach to 3-D Terrain Mapping.
In Proceedings of the 1999 IEEE/RSJ International Conference on Intelligent Robotics and Systems (IROS '99),
pages 1121-1127,
October 1999.
IEEE.
(pdf)
Keywords:
Terrain modeling,
3-D modeling,
registration.
@inproceedings{Huber_1999_3191,
author = "Daniel Huber and Martial Hebert",
title = "A New Approach to 3-D Terrain Mapping",
booktitle = "Proceedings of the 1999 IEEE/RSJ International Conference on Intelligent Robotics and Systems (IROS '99)",
month = "October",
year = "1999",
pages = "1121-1127",
publisher = "IEEE",
pdf ="http://www.ri.cmu.edu/pub_files/pub2/huber_daniel_f_1999_1/huber_daniel_f_1999_1.pdf",
keywords="Terrain modeling, 3-D modeling, registration"
}
-
P. Lee,
W. A. Cassidy,
D. Apostolopoulos,
D. Bassi,
L. Bravo,
H. Cifuentes,
M. Deans,
A. Foessel,
S. Moorehead,
M. Parris,
C. Puebla,
Liam Pedersen,
M. Sibenac,
F. Valdes,
N. Vandapel, and
W. Whittaker.
Search for Meteorites at Martin Hills and Pirrit Hills, Antarctica.
In Lunar and Planetary Science Conference XXX,
1999.
@inproceedings{Lee_1999_3113,
author = "P. Lee and W. A. Cassidy and D. Apostolopoulos and D. Bassi and L. Bravo and H. Cifuentes and M. Deans and A. Foessel and S. Moorehead and M. Parris and C. Puebla and Liam Pedersen and M. Sibenac and F. Valdes and N. Vandapel and W. Whittaker",
title = "Search for Meteorites at Martin Hills and Pirrit Hills, Antarctica",
booktitle = "Lunar and Planetary Science Conference XXX",
year = "1999"
}
-
Shyjan Mahamud and
Martial Hebert.
Efficient Recovery of Low-dimensional Structure from High-dimensional Data.
In IEEE International Conference on Computer Vision (ICCV),
September 1999.
IEEE.
(url)
(pdf)
Abstract: "Many modeling tasks in computer vision. e.g. structure from motion, shape/reflectance from shading, filter synthesis have a low-dimensional intrinsic structure even though the dimension of the input data can be relatively large. We propose a simple but surprisingly effective iterative randomized algorithm that drastically reduces the time required for recovering the intrinsic structure. The computational cost depends only on the intrinsic dimension of the structure of the task. It is based on the recently proposed Cascade Basis Reduction (CBR) algorithm that was developed in the context of steerable filters. A key feature of our algorithm compared with CBR is that an arbitrary apriori basis for the task is not required. This allows us to extend the applicability of the algorithm to tasks beyond steerable filters. We prove the convergence for the new algorithm and show that in practice the new algorithm is much faster than CBR for the same modeling error. We demonstrate this speed-up for the construction of a steerable basis for Gabor filters. We also demonstrate the generality of the new algorithm by applying it to to an example from structure from motion without missing data."
@inproceedings{Mahamud_1999_2606,
author = "Shyjan Mahamud and Martial Hebert",
title = "Efficient Recovery of Low-dimensional Structure from High-dimensional Data",
booktitle = "IEEE International Conference on Computer Vision (ICCV)",
month = "September",
year = "1999",
publisher = "IEEE",
pdf ="http://www.ri.cmu.edu/pub_files/pub1/mahamud_shyjan_1999_1/mahamud_shyjan_1999_1.pdf",
url="http://www.ri.cmu.edu/pubs/pub_2606.html",
abstract="Many modeling tasks in computer vision. e.g. structure from motion, shape/reflectance from shading, filter synthesis have a low-dimensional intrinsic structure even though the dimension of the input data can be relatively large. We propose a simple but surprisingly effective iterative randomized algorithm that drastically reduces the time required for recovering the intrinsic structure. The computational cost depends only on the intrinsic dimension of the structure of the task. It is based on the recently proposed Cascade Basis Reduction (CBR) algorithm that was developed in the context of steerable filters. A key feature of our algorithm compared with CBR is that an arbitrary apriori basis for the task is not required. This allows us to extend the applicability of the algorithm to tasks beyond steerable filters. We prove the convergence for the new algorithm and show that in practice the new algorithm is much faster than CBR for the same modeling error. We demonstrate this speed-up for the construction of a steerable basis for Gabor filters. We also demonstrate the generality of the new algorithm by applying it to to an example from structure from motion without missing data."
}
-
Shyjan Mahamud,
Karvel K. Thornber, and
Lance R. Williams.
Segmentation of Salient Closed Contours from Real Images.
In IEEE International Conference on Computer Vision (ICCV),
September 1999.
IEEE.
(url)
(pdf)
Abstract: "Using a saliency measure based on the global property of contour closure, we have developed a method that reliably segments out salient contours bounding unknown objects from real edge images. The measure also incorporates the Gestalt principles of proximity and smooth continuity that previous methods have exploited. Unlike previous measures, we incorporate contour closure by finding the eigen-solution associated with a stochastic process that models the distribution of contours passing through edges in the scene. The segmentation algorithm utilizes the saliency measure to identify multiple closed contours by finding strongly-connected components on an induced graph. The determination of strongly-connected components is a direct consequence of the property of closure. We report for the first time, results on large real images for which segmentation takes an average of about 10 secs per object on a general-purpose workstation. The segmentation is made efficient for such large images by exploiting the inherent symmetry in the task."
@inproceedings{Mahamud_1999_2607,
author = "Shyjan Mahamud and Karvel K. Thornber and Lance R. Williams",
title = "Segmentation of Salient Closed Contours from Real Images",
booktitle = "IEEE International Conference on Computer Vision (ICCV)",
month = "September",
year = "1999",
publisher = "IEEE",
pdf ="http://www.ri.cmu.edu/pub_files/pub2/mahamud_shyjan_1999_1/mahamud_shyjan_1999_1.pdf",
url ="http://www.ri.cmu.edu/pubs/pub_2607.html",
abstract="Using a saliency measure based on the global property of contour closure, we have developed a method that reliably segments out salient contours bounding unknown objects from real edge images. The measure also incorporates the Gestalt principles of proximity and smooth continuity that previous methods have exploited. Unlike previous measures, we incorporate contour closure by finding the eigen-solution associated with a stochastic process that models the distribution of contours passing through edges in the scene. The segmentation algorithm utilizes the saliency measure to identify multiple closed contours by finding strongly-connected components on an induced graph. The determination of strongly-connected components is a direct consequence of the property of closure. We report for the first time, results on large real images for which segmentation takes an average of about 10 secs per object on a general-purpose workstation. The segmentation is made efficient for such large images by exploiting the inherent symmetry in the task."
}
-
Dongmei Zhang and
Martial Hebert.
Harmonic Maps and Their Applications in Surface Matching.
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR '99),
volume 2,
1999.
(pdf)
@inproceedings{Zhang_1999_3231,
author = "Dongmei Zhang and Martial Hebert",
title = "Harmonic Maps and Their Applications in Surface Matching",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition (CVPR '99)",
year = "1999",
volume = "2",
pdf = "http://www.ri.cmu.edu/pub_files/pub2/zhang_dongmei_1999_1/zhang_dongmei_1999_1.pdf"
}
-
Dongmei Zhang and
Martial Hebert.
Experimental analysis of Harmonic Shape Images.
In Proceedings of the Second International Conference on 3-D Digital Imaging and Modeling,
pages 209 - 218,
October 1999.
(pdf)
@inproceedings{Zhang_1999_3599,
author = "Dongmei Zhang and Martial Hebert",
title = "Experimental analysis of Harmonic Shape Images",
booktitle = "Proceedings of the Second International Conference on 3-D Digital Imaging and Modeling",
month = "October",
year = "1999",
pages = "209 - 218",
pdf ="http://www.ri.cmu.edu/pub_files/pub2/zhang_dongmei_1999_3/zhang_dongmei_1999_3.pdf"
}