-
Cristian Dima,
Martial Hebert, and
Anthony (Tony) Stentz.
Enabling Learning From Large Datasets: Applying Active Learning to Mobile Robotics.
In International Conference on Robotics and Automation,
April 2004.
IEEE.
(pdf)
@inproceedings{Dima_2004_4681,
author = "Cristian Dima and Martial Hebert and Anthony (Tony) Stentz",
title = "Enabling Learning From Large Datasets: Applying Active Learning to Mobile Robotics",
booktitle = "International Conference on Robotics and Automation",
month = "April",
year = "2004",
publisher = "IEEE",
pdf ="http://www.ri.cmu.edu/pub_files/pub4/dima_cristian_2004_2/dima_cristian_2004_2.pdf"
}
-
Cristian Dima,
Nicolas Vandapel, and
Martial Hebert.
Classifier Fusion for Outdoor Obstacle Detection.
In International Conference on Robotics and Automation,
April 2004.
IEEE.
(pdf)
Keywords:
mobile robotics,
obstacle detection.
@inproceedings{Dima_2004_4680,
author = "Cristian Dima and Nicolas Vandapel and Martial Hebert",
title = "Classifier Fusion for Outdoor Obstacle Detection",
booktitle = "International Conference on Robotics and Automation",
month = "April",
year = "2004",
publisher = "IEEE",
pdf ="http://www.ri.cmu.edu/pub_files/pub4/dima_cristian_2004_1/dima_cristian_2004_1.pdf",
keywords ="mobile robotics, obstacle detection"
}
-
Andrea Frome,
Daniel Huber,
Ravi Kolluri,
Thomas Bulow, and
Jitendra Malik.
Recognizing Objects in Range Data Using Regional Point Descriptors.
In Proceedings of the European Conference on Computer Vision (ECCV),
May 2004.
Keywords:
shape contexts,
spin images,
3-D recognition.
@inproceedings{Frome_2004_4611,
author = "Andrea Frome and Daniel Huber and Ravi Kolluri and Thomas Bulow and Jitendra Malik",
title = "Recognizing Objects in Range Data Using Regional Point Descriptors",
booktitle = "Proceedings of the European Conference on Computer Vision (ECCV)",
month = "May",
year = "2004",
keywords="shape contexts, spin images, 3-D recognition"
}
-
G. Godin,
J-F. Lalonde, and
L. borgeat.
Dual-Resolution Stereoscopic Display with Scene-Adaptive Fovea Boundarie.
In International Immersive Projection Technology Workshop,
2004.
(url)
|
Annotation: We present a multi-projector stereoscopic display which incorporates a high-resolution inset image, or fovea. The system uses four projectors, and the image warping required for on-screen image alignment and foveation is applied as part of the rendering pass. We discuss the problem of ambiguous depth perception between the boundaries of the inset in each eye and the underlying scene, and present a solution where the inset boundaries are dynamically adapted as a function of the scene geometry. An efficient real-time method for boundary adaptation is introduced. It is applied as a post-rendering step, does not require direct geometric computations on the scene, and is therefore practically independent of the size and complexity of the model. .
|
@InProceedings{godin-iipt-04,
author = {G. Godin and J-F. Lalonde and L. borgeat},
title = {Dual-Resolution Stereoscopic Display with Scene-Adaptive Fovea Boundarie},
booktitle = {International Immersive Projection Technology Workshop},
year = 2004,
annote = {We present a multi-projector stereoscopic display which incorporates a high-resolution inset image, or fovea. The system uses four projectors, and the image warping required for on-screen image alignment and foveation is applied as part of the rendering pass. We discuss the problem of ambiguous depth perception between the boundaries of the inset in each eye and the underlying scene, and present a solution where the inset boundaries are dynamically adapted as a function of the scene geometry. An efficient real-time method for boundary adaptation is introduced. It is applied as a post-rendering step, does not require direct geometric computations on the scene, and is therefore practically independent of the size and complexity of the model. },
url ="http://iit-iti.nrc-cnrc.gc.ca/publications/nrc-46571_e.html",
keywords=""
}
-
G. Godin,
J-F. Lalonde, and
L. borgeat.
Projector-based dual-resolution stereoscopic display.
In IEEE Virtual Reality,
2004.
|
Annotation: We present a stereoscopic display system which incorporates a high-resolution inset image, or fovea. We describe the specific problem of false depth cues along the boundaries of the inset image, and propose a solution in which the boundaries of the inset image are dynamically adapted as a function of the geometry of the scene. This method produces comfortable stereoscopic viewing at a low additional computational cost. The four projectors need only be approximately aligned: a single drawing pass is required, regardless of projector alignment, since the warping is applied as part of the 3-D rendering process.
|
@InProceedings{godin-vr-04,
author = {G. Godin and J-F. Lalonde and L. borgeat},
title = {Projector-based dual-resolution stereoscopic display},
booktitle = {IEEE Virtual Reality},
year = 2004,
annote = {We present a stereoscopic display system which incorporates a high-resolution inset image, or fovea. We describe the specific problem of false depth cues along the boundaries of the inset image, and propose a solution in which the boundaries of the inset image are dynamically adapted as a function of the geometry of the scene. This method produces comfortable stereoscopic viewing at a low additional computational cost. The four projectors need only be approximately aligned: a single drawing pass is required, regardless of projector alignment, since the warping is applied as part of the 3-D rendering process},
keywords="",
url=""
}
-
Derek Hoiem,
Rahul Sukthankar,
Henry Schneiderman, and
Larry Huston.
Object-Based Image Retrieval using the Statistical Structure of Images.
In IEEE Conference on Computer Vision and Pattern Recognition,
June 2004.
(url)
Keywords:
object recognition,
statistical modeling.
Abstract: "We propose a new Bayesian approach to object-based image retrieval with relevance feedback. Although estimating the object posterior probability density from few examples seems infeasible, we are able to approximate this density by exploiting statistics of the image database domain. Unlike previous approaches that assume an arbitrary distribution for the unconditional density of the feature vector (the density of the features taken over the entire image domain), we learn both the structure and the parameters of this density. These density estimates enable us to construct a Bayesian classifier. Using this Bayesian classifier, we perform a windowed scan over images for objects of interest and employ the user?s feedback on the search results to train a second classifier that focuses on eliminating difficult false positives. We have incorporated this algorithm into an object-based image retrieval system. We demonstrate the effectiveness of our approach with experiments using a set of categories from the Corel database."
@inproceedings{Hoiem_2004_4644,
author = "Derek Hoiem and Rahul Sukthankar and Henry Schneiderman and Larry Huston",
title = "Object-Based Image Retrieval using the Statistical Structure of Images",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition",
month = "June",
year = "2004",
keywords="object recognition, statistical modeling",
abstract="We propose a new Bayesian approach to object-based image retrieval with relevance feedback. Although estimating the object posterior probability density from few examples seems infeasible, we are able to approximate this density by exploiting statistics of the image database domain. Unlike previous approaches that assume an arbitrary distribution for the unconditional density of the feature vector (the density of the features taken over the entire image domain), we learn both the structure and the parameters of this density. These density estimates enable us to construct a Bayesian classifier. Using this Bayesian classifier, we perform a windowed scan over images for objects of interest and employ the user?s feedback on the search results to train a second classifier that focuses on eliminating difficult false positives. We have incorporated this algorithm into an object-based image retrieval system. We demonstrate the effectiveness of our approach with experiments using a set of categories from the Corel database.",
url ="http://www.ri.cmu.edu/pubs/pub_4644.html"
}
-
Daniel Huber,
Anuj Kapuria,
Raghavendra Rao Donamukkala, and
Martial Hebert.
Parts-based 3-D object classification.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 04),
June 2004.
Note: This work was supported by the DARPA E3-D program (F33615-02-C-1265).
(pdf)
Keywords:
object classification,
parts-based classification,
generic object recognition,
3-D recognition.
@inproceedings{Huber_2004_4691,
author = "Daniel Huber and Anuj Kapuria and Raghavendra Rao Donamukkala and Martial Hebert",
title = "Parts-based 3-D object classification",
booktitle = "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 04)",
month = "June",
year = "2004",
note = "This work was supported by the DARPA E3-D program (F33615-02-C-1265).",
pdf ="http://www.ri.cmu.edu/pub_files/pub4/huber_daniel_2004_1/huber_daniel_2004_1.pdf",
keywords="object classification, parts-based classification, generic object recognition, 3-D recognition"
}
-
Yanxi Liu,
Leonid Teverovskiy,
Owen Carmichael,
R. Kikinis,
M. Shenton,
C.S. Carter,
V.A. Stenger,
S. Davis,
Howard Aizenstein,
Jim Becker,
Oscar Lopez, and
Carolyn Meltzer.
Discriminative MR Image Feature Analysis for Automatic Schizophrenia and Alzheimer's Disease Classification.
In Proceedings of the 7th International Conference on MedicalImage Computing and Computer Aided Intervention (MICCAI '04),
October 2004.
(url)
Keywords:
medical applications,
medical imaging.
@inproceedings{Liu_2004_4678,
author = "Yanxi Liu and Leonid Teverovskiy and Owen Carmichael and R. Kikinis and M. Shenton and C.S. Carter and V.A. Stenger and S. Davis and Howard Aizenstein and Jim Becker and Oscar Lopez and Carolyn Meltzer",
title = "Discriminative MR Image Feature Analysis for Automatic Schizophrenia and Alzheimer's Disease Classification",
booktitle = "Proceedings of the 7th International Conference on MedicalImage Computing and Computer Aided Intervention (MICCAI '04)",
month = "October",
year = "2004",
url="http://www.ri.cmu.edu/pubs/pub_4678.html",
keywords="medical applications, medical imaging"
}
-
Bart Nabbe,
Sanjiv Kumar, and
Martial Hebert.
Path Planning with Hallucinated Worlds.
In Proceedings: IEEE/RSJ International Conference on Intelligent Robots and Systems,
October 2004.
IEEE.
(url)
(pdf)
Abstract: "We describe an approach that integrate mid-range sensing into a dynamic path planning algorithm. The algorithm is based on measuring the reduction in path cost that would be caused by taking a sensor reading from candidate locations. The planner uses this measure in order to decide where to take the next sensor reading. Ideally, one would like to evaluate a path based on a map that is as close as possible to the true underlying world. In practice, however, the map is only sparsely populated by data derived from sensor readings. A key component of the approach described in this paper is a mechanism to infer (or "hallucinate") more complete maps from sparse sensor readings. We show how this hallucination mechanism is integrated with the planner to produce better estimates of the gain in path cost occurred when taking sensor readings. We show results on a real robot as well as a statistical analysis on a large set of randomly generated path planning problems on elevation maps from real terrain."
@inproceedings{Nabbe_2004_4821,
author = "Bart Nabbe and Sanjiv Kumar and Martial Hebert",
title = "Path Planning with Hallucinated Worlds",
booktitle = "Proceedings: IEEE/RSJ International Conference on Intelligent Robots and Systems",
month = "October",
year = "2004",
publisher = "IEEE",
keywords="",
abstract="We describe an approach that integrate mid-range sensing into a dynamic path planning algorithm. The algorithm is based on measuring the reduction in path cost that would be caused by taking a sensor reading from candidate locations. The planner uses this measure in order to decide where to take the next sensor reading. Ideally, one would like to evaluate a path based on a map that is as close as possible to the true underlying world. In practice, however, the map is only sparsely populated by data derived from sensor readings. A key component of the approach described in this paper is a mechanism to infer (or "hallucinate") more complete maps from sparse sensor readings. We show how this hallucination mechanism is integrated with the planner to produce better estimates of the gain in path cost occurred when taking sensor readings. We show results on a real robot as well as a statistical analysis on a large set of randomly generated path planning problems on elevation maps from real terrain.",
url="http://www.ri.cmu.edu/pubs/pub_4821.html",
pdf="http://www.ri.cmu.edu/pub_files/pub4/nabbe_bart_2004_1/nabbe_bart_2004_1.pdf"
}
-
Henry Schneiderman.
Learning a Restricted Bayesian Network for Object Detection.
In IEEE Conference on Computer Vision and Pattern Recognition,
June 2004.
IEEE.
(url)
Abstract: "Many classes of images have the characteristics of sparse structuring of statistical dependency and the presence of conditional independencies among various groups of variables. Such characteristics make it possible to construct a powerful classifier by only representing the stronger direct dependencies among the variables. In particular, a Bayesian network compactly represents such structuring. However, learning the structure of a Bayesian network is known to be NP complete. The high dimensionality of images makes structure learning especially challenging. This paper describes an algorithm that searches for the structure of a Bayesian network based classifier in this large space of possible structures. The algorithm seeks to optimize two cost functions: a localized error in the log-likelihood ratio function to restrict the structure and a global classification error to choose the final structure of the Network. The final network structure is restricted such that the search can take advantage of pre-computed estimates and evaluations. We use this method to automatically train detectors of frontal faces, eyes, and the iris of the human eye. In particular, the frontal face detector achieves state-of-the-art performance on the MIT-CMU test set for face detection."
@inproceedings{Schneiderman_2004_4688,
author = "Henry Schneiderman",
title = "Learning a Restricted Bayesian Network for Object Detection",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition",
month = "June",
year = "2004",
publisher = "IEEE",
url="http://www.ri.cmu.edu/pubs/pub_4688.html",
abstract="Many classes of images have the characteristics of sparse structuring of statistical dependency and the presence of conditional independencies among various groups of variables. Such characteristics make it possible to construct a powerful classifier by only representing the stronger direct dependencies among the variables. In particular, a Bayesian network compactly represents such structuring. However, learning the structure of a Bayesian network is known to be NP complete. The high dimensionality of images makes structure learning especially challenging. This paper describes an algorithm that searches for the structure of a Bayesian network based classifier in this large space of possible structures. The algorithm seeks to optimize two cost functions: a localized error in the log-likelihood ratio function to restrict the structure and a global classification error to choose the final structure of the Network. The final network structure is restricted such that the search can take advantage of pre-computed estimates and evaluations. We use this method to automatically train detectors of frontal faces, eyes, and the iris of the human eye. In particular, the frontal face detector achieves state-of-the-art performance on the MIT-CMU test set for face detection."
}
-
Henry Schneiderman.
Feature-Centric Evaluation for Efficient Cascaded Object Detection.
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
June 2004.
IEEE.
(url)
Abstract: "We describe a cascaded method for object detection. This approach uses a novel organization of the first cascade stage called "feature-centric" evaluation which re-uses feature evaluations across multiple candidate windows. We minimize the cost of this evaluation through several simplifications: (1) localized lighting normalization, (2) representation of the classifier as an additive model and (3) discrete-valued features. Such a method also incorporates a unique feature representation. The early stages in the cascade use simple fast feature evaluations and the later stages use more complex discriminative features. In particular, we propose features based on sparse coding and ordinal relationships among filter responses. This combination of cascaded feature-centric evaluation with features of increasing complexity achieves both computational efficiency and accuracy. We describe object detection experiments on ten objects including faces and automobiles. These results include 97% recognition at equal error rate on the UIUC image database for car detection."
@inproceedings{Schneiderman_2004_4687,
author = "Henry Schneiderman",
title = "Feature-Centric Evaluation for Efficient Cascaded Object Detection",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",
month = "June",
year = "2004",
publisher = "IEEE",
abstract="We describe a cascaded method for object detection. This approach uses a novel organization of the first cascade stage called "feature-centric" evaluation which re-uses feature evaluations across multiple candidate windows. We minimize the cost of this evaluation through several simplifications: (1) localized lighting normalization, (2) representation of the classifier as an additive model and (3) discrete-valued features. Such a method also incorporates a unique feature representation. The early stages in the cascade use simple fast feature evaluations and the later stages use more complex discriminative features. In particular, we propose features based on sparse coding and ordinal relationships among filter responses. This combination of cascaded feature-centric evaluation with features of increasing complexity achieves both computational efficiency and accuracy. We describe object detection experiments on ten objects including faces and automobiles. These results include 97% recognition at equal error rate on the UIUC image database for car detection.",
pdf="",
url="http://www.ri.cmu.edu/pubs/pub_4687.html"
}
-
Y. Shan,
B. Matei,
H. S. Sawhney,
R. Kumar,
Daniel Huber, and
Martial Hebert.
Linear Model Hashing and Batch RANSAC for Rapid and Accurate Object Recognition.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2004),
June 2004.
(pdf)
Keywords:
object recognition,
3-D recognition,
articulated ICP.
@inproceedings{shan-cvpr-04,
author = "Y. Shan and B. Matei and H. S. Sawhney and R. Kumar and Daniel Huber and Martial Hebert",
title = "Linear Model Hashing and Batch RANSAC for Rapid and Accurate Object Recognition",
booktitle = "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2004)",
month = "June",
year = "2004",
pdf = "http://www.ri.cmu.edu//pub_files/pub4/shan_y_2004_1/shan_y_2004_1.pdf",
keywords="object recognition, 3-D recognition, articulated ICP"
}
-
Nicolas Vandapel and
Martial Hebert.
Finding Organized Structures in 3-D Ladar Data.
In IEEE/RSJ International Conference on Intelligent Robots and Systems,
2004.
(pdf)
@inproceedings{vandapel-iros-04,
author = "Nicolas Vandapel and Martial Hebert",
title = "Finding Organized Structures in 3-D Ladar Data",
booktitle = "IEEE/RSJ International Conference on Intelligent Robots and Systems",
year = "2004",
pdf ="http://www.ri.cmu.edu/pub_files/pub4/vandapel_nicolas_2004_3/vandapel_nicolas_2004_3.pdf",
keywords=""
}
-
Nicolas Vandapel and
Martial Hebert.
Finding Organized Structures in 3-D LADAR Data.
In Army Science Conference,
November 2004.
(pdf)
Keywords:
concertina wire detection,
ladar.
Abstract: "In this paper, we address the problem of finding concertina wire in three-dimensional (3-D) data. Wire entanglements constitute a major obstacle to the mobility of Unmanned Ground Vehicle because of their widespread use and the difficulty to detect them. We pose the problem in term of finding thin structures organized in complex patterns. Such problem did not received as much attention as linear and planar structures segmentation. We are interested especially in the problems posed by repetitive and symmetric structures acquired with a laser range finder. The method relies on 3-D data projections along specific directions and 2-D histograms comparison. The sensitivity of the classification algorithm to the parameter settings is evaluated and a segmentation method proposed. This paper is an extended version of our IROS 2004 paper."
@inproceedings{Vandapel_2004_4778,
author = "Nicolas Vandapel and Martial Hebert",
title = "Finding Organized Structures in 3-D LADAR Data",
booktitle = "Army Science Conference",
month = "November",
year = "2004",
abstract ="In this paper, we address the problem of finding concertina wire in three-dimensional (3-D) data. Wire entanglements constitute a major obstacle to the mobility of Unmanned Ground Vehicle because of their widespread use and the difficulty to detect them. We pose the problem in term of finding thin structures organized in complex patterns. Such problem did not received as much attention as linear and planar structures segmentation. We are interested especially in the problems posed by repetitive and symmetric structures acquired with a laser range finder. The method relies on 3-D data projections along specific directions and 2-D histograms comparison. The sensitivity of the classification algorithm to the parameter settings is evaluated and a segmentation method proposed. This paper is an extended version of our IROS 2004 paper.",
pdf ="http://www.ri.cmu.edu/pub_files/pub4/vandapel_nicolas_2004_4/vandapel_nicolas_2004_4.pdf",
keywords="concertina wire detection, ladar"
}
-
Nicolas Vandapel,
Daniel Huber,
Anuj Kapuria, and
Martial Hebert.
Natural Terrain Classification using 3-D Ladar Data.
In IEEE International Conference on Robotics and Automation,
April 2004.
(pdf)
@inproceedings{vandapel-icra-04,
author = "Nicolas Vandapel and Daniel Huber and Anuj Kapuria and Martial Hebert",
title = "Natural Terrain Classification using 3-D Ladar Data",
booktitle = "IEEE International Conference on Robotics and Automation",
month = "April",
year = "2004",
pdf = "http://www.ri.cmu.edu/pub_files/pub4/vandapel_nicolas_2004_2/vandapel_nicolas_2004_2.pdf"
}