-
Peng Chang and
Martial Hebert.
Omni-directional structure from motion.
In Proceedings of the 2000 IEEE Workshop on Omnidirectional Vision,
pages 127 - 133,
June 2000.
(pdf)
@inproceedings{Chang_2000_3597,
author = "Peng Chang and Martial Hebert",
title = "Omni-directional structure from motion",
booktitle = "Proceedings of the 2000 IEEE Workshop on Omnidirectional Vision",
month = "June",
year = "2000",
pages = "127 - 133",
pdf ="http://www.ri.cmu.edu/pub_files/pub2/chang_peng_2000_1/chang_peng_2000_1.pdf"
}
-
Matthew Deans and
Martial Hebert.
Invariant filtering for simultaneous localization and mapping.
In IEEE International Conference on Robotics and Automation,
pages 1042-7,
April 2000.
(pdf)
@inproceedings{Deans_2000_3455,
author = "Matthew Deans and Martial Hebert",
title = "Invariant filtering for simultaneous localization and mapping",
booktitle = "IEEE International Conference on Robotics and Automation",
month = "April",
year = "2000",
pages = "1042-7",
pdf ="http://www.ri.cmu.edu/pub_files/pub2/deans_matthew_2000_2/deans_matthew_2000_2.pdf"
}
-
Matthew Deans and
Martial Hebert.
Experimental Comparison of Techniques for Localization and Mapping using a Bearings Only Sensor.
In Proc. of the ISER '00 Seventh International Symposium on Experimental Robotics,
December 2000.
(pdf)
@inproceedings{Deans_2000_3453,
author = "Matthew Deans and Martial Hebert",
title = "Experimental Comparison of Techniques for Localization and Mapping using a Bearings Only Sensor",
booktitle = "Proc. of the ISER '00 Seventh International Symposium on Experimental Robotics",
month = "December",
year = "2000",
pdf ="http://www.ri.cmu.edu/pub_files/pub2/deans_matthew_2000_3/deans_matthew_2000_3.pdf"
}
-
Martial Hebert.
Active and passive range sensing for robotics.
In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '00),
volume 1,
pages 102 - 110,
April 2000.
(pdf)
@inproceedings{Hebert_2000_3595,
author = "Martial Hebert",
title = "Active and passive range sensing for robotics",
booktitle = "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '00)",
month = "April",
year = "2000",
volume = "1",
pages = "102 - 110",
pdf="http://www.ri.cmu.edu/pub_files/pub2/hebert_martial_2000_1/hebert_martial_2000_1.pdf"
}
-
Daniel Huber,
Owen Carmichael, and
Martial Hebert.
3-D map reconstruction from range data.
In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '00),
volume 1,
pages 891 - 897,
April 2000.
(url)
(pdf)
Keywords:
3-D perception,
geometric modeling.
Abstract: "We present techniques for building models of complex environments from range data gathered at multiple viewpoints. The challenges in this problem are: the matching of unregistered views without prior knowledge of pose, the use of very large data sets, and the manipulation of data sets of different resolutions and from different sensors. Our approach is unique in that no prior knowledge of the relative viewpoints is needed in order to register the data. We show results in building maps of interior environment from range finding data, building large terrain maps from ground-based and from aerial data, and from an operational for mapping from stereo data for hazardous environment characterization. The paper summarizes the major results obtained so far in this area."
@inproceedings{Huber_2000_3556,
author = "Daniel Huber and Owen Carmichael and Martial Hebert",
title = "3-D map reconstruction from range data",
booktitle = "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '00)",
month = "April",
year = "2000",
volume = "1",
pages = "891 - 897",
pdf ="http://www.ri.cmu.edu/pub_files/pub2/huber_daniel_f_2000_1/huber_daniel_f_2000_1.pdf",
keywords="3-D perception, geometric modeling",
abstract="We present techniques for building models of complex environments from range data gathered at multiple viewpoints. The challenges in this problem are: the matching of unregistered views without prior knowledge of pose, the use of very large data sets, and the manipulation of data sets of different resolutions and from different sensors. Our approach is unique in that no prior knowledge of the relative viewpoints is needed in order to register the data. We show results in building maps of interior environment from range finding data, building large terrain maps from ground-based and from aerial data, and from an operational for mapping from stereo data for hazardous environment characterization. The paper summarizes the major results obtained so far in this area.",
url="http://www.ri.cmu.edu/pubs/pub_3556.html"
}
-
Shyjan Mahamud and
Martial Hebert.
Iterative projective reconstruction from multiple views.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR '00),
volume 2,
pages 430 - 437,
June 2000.
(url)
(pdf)
Abstract: "We propose an iterative method for the recovery of the projective structure and motion from multiple images. It has been recently noted that by scaling the measurement matrix by the true projective depths, recovery of the structure and motion is possible by factorization. The reliable determination of the projective depths is crucial to the success of this approach. The previous approach recovers these projective depths using pairwise constraints among images. We first discuss a few important drawbacks with this approach. We then propose an iterative method where we simultaneously recover both the projective depths as well as the structure and motion that avoids some of these drawbacks by utilizing all of the available data uniformly. The new approach makes use of a subspace constraint on the projections of a 3-D point onto an arbitrary number of images. The projective depths are readily determined by solving a generalized eigenvalue problem derived from the subspace constraint. We also formulate a dual subspace constraint on all the points in a given image, which can be used for verifying the projective geometry of a scene or object that was modeled. We prove the monotonic convergence of the iterative scheme to a local maximum. We show the robustness of the approach on both synthetic and real data despite large perspective distortions and varying initializations."
@inproceedings{Mahamud_2000_3596,
author = "Shyjan Mahamud and Martial Hebert",
title = "Iterative projective reconstruction from multiple views",
booktitle = "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR '00)",
month = "June",
year = "2000",
volume = "2",
pages = "430 - 437",
pdf ="http://www.ri.cmu.edu/pub_files/pub2/mahamud_shyjan_2000_1/mahamud_shyjan_2000_1.pdf",
url="http://www.ri.cmu.edu/pubs/pub_3596.html",
abstract="We propose an iterative method for the recovery of the projective structure and motion from multiple images. It has been recently noted that by scaling the measurement matrix by the true projective depths, recovery of the structure and motion is possible by factorization. The reliable determination of the projective depths is crucial to the success of this approach. The previous approach recovers these projective depths using pairwise constraints among images. We first discuss a few important drawbacks with this approach. We then propose an iterative method where we simultaneously recover both the projective depths as well as the structure and motion that avoids some of these drawbacks by utilizing all of the available data uniformly. The new approach makes use of a subspace constraint on the projections of a 3-D point onto an arbitrary number of images. The projective depths are readily determined by solving a generalized eigenvalue problem derived from the subspace constraint. We also formulate a dual subspace constraint on all the points in a given image, which can be used for verifying the projective geometry of a scene or object that was modeled. We prove the monotonic convergence of the iterative scheme to a local maximum. We show the robustness of the approach on both synthetic and real data despite large perspective distortions and varying initializations."
}
-
Henry Schneiderman and
Takeo Kanade.
A histogram-based method for detection of faces and cars.
In Proceedings of the 2000 International Conference on Image Processing (ICIP '00),
volume 3,
pages 504 - 507,
September 2000.
(url)
Abstract: "We describe a statistical method for 3-D object detection. We represent the statistics of both object appearance and "non-object" appearance using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect human faces that vary from frontal view to full profile view and the first algorithm that can reliably detect cars over a wide range of viewpoints."
@inproceedings{Schneiderman_2000_3530,
author = "Henry Schneiderman and Takeo Kanade",
title = "A histogram-based method for detection of faces and cars",
booktitle = "Proceedings of the 2000 International Conference on Image Processing (ICIP '00)",
month = "September",
year = "2000",
volume = "3",
pages = "504 - 507",
url = "http://www.ri.cmu.edu/pubs/pub_3530.html",
abstract="We describe a statistical method for 3-D object detection. We represent the statistics of both object appearance and "non-object" appearance using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect human faces that vary from frontal view to full profile view and the first algorithm that can reliably detect cars over a wide range of viewpoints."
}
-
Henry Schneiderman and
Takeo Kanade.
A Statistical Model for 3-D Object Detection Applied to Faces and Cars.
In IEEE Conference on Computer Vision and Pattern Recognition,
June 2000.
IEEE.
(url)
Abstract: "In this paper, we describe a statistical method for 3-D object detection. We represent the statistics of both object appearance and "non-object" appearance using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect human faces with out-of-plane rotation and the first algorithm that can reliably detect passenger cars over a wide range of viewpoints"
@inproceedings{Schneiderman_2000_3294,
author = "Henry Schneiderman and Takeo Kanade",
title = "A Statistical Model for 3-D Object Detection Applied to Faces and Cars",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition",
month = "June",
year = "2000",
publisher = "IEEE",
url="http://www.ri.cmu.edu/pubs/pub_3294.html",
abstract="In this paper, we describe a statistical method for 3-D object detection. We represent the statistics of both object appearance and "non-object" appearance using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect human faces with out-of-plane rotation and the first algorithm that can reliably detect passenger cars over a wide range of viewpoints"
}
-
Scott Thayer,
Bruce Digney,
M Bernardine Dias,
Anthony (Tony) Stentz,
Bart Nabbe, and
Martial Hebert.
Distributed Robotic Mapping of Extreme Environments.
In Proceedings of SPIE: Mobile Robots XV and Telemanipulator and Telepresence Technologies VII,
volume 4195,
November 2000.
(pdf)
Keywords:
multi-robot coordination,
robotic Mapping,
mobile robots.
@inproceedings{Thayer_2000_3506,
author = "Scott Thayer and Bruce Digney and M Bernardine Dias and Anthony (Tony) Stentz and Bart Nabbe and Martial Hebert",
title = "Distributed Robotic Mapping of Extreme Environments",
booktitle = "Proceedings of SPIE: Mobile Robots XV and Telemanipulator and Telepresence Technologies VII",
month = "November",
year = "2000",
volume = "4195",
pdf = "http://www.ri.cmu.edu/pub_files/pub2/thayer_scott_2000_1/thayer_scott_2000_1.pdf",
keywords="multi-robot coordination, robotic Mapping, mobile robots"
}