WorldCat Identities

Hebert, Martial

Overview
Works: 35 works in 102 publications in 4 languages and 1,126 library holdings
Genres: Conference papers and proceedings  Academic theses 
Roles: Author, Editor, 958, Other
Classifications: TA1634, 006.37
Publication Timeline
.
Most widely held works by Martial Hebert
Object representation in computer vision : International NSF-ARPA Workshop, New York City, NY, USA, December 5-7, 1994 : proceedings by Martial Hebert( Book )

19 editions published in 1995 in 3 languages and held by 326 WorldCat member libraries worldwide

This book documents the scientific outcome of the International NSF-ARPA Workshop on Object Representation in Computer Vision, held in New York City in December 1994 with invited participants chosen among the recognized experts in the field. The volume presents the complete set of papers in revised full-length versions. In addition, the first paper is a report on the workshop in which the panel discussions as well as the conclusions and recommendations reached by the workshop participants are summarized. Altogether the volume provides an excellent, in-depth view of the state of the art in this active area of research and applications
Object representation in computer vision II : ECCV '96 International Workshop, Cambridge, UK, April 13-14, 1996 : proceedings by Jean Ponce( Book )

18 editions published in 1996 in English and held by 236 WorldCat member libraries worldwide

"This book constitutes the strictly refereed post-workshop proceedings of the second International Workshop on Object Representation in Computer Vision, held in conjunction with ECCV '96 in Cambridge, UK, in April 1996. The 15 revised full papers contained in the book were selected from 45 submissions for presentation at the workshop. Also included are three invited contributions based on the talks by Takeo Kanade, Jan Koenderink, and Ram Nevatia as well as a workshop report by the volume editors summarizing several panel discussions and the general state of the art in the area."--PUBLISHER'S WEBSITE
Intelligent unmanned ground vehicles : autonomous navigation research at Carnegie Mellon by Martial Hebert( Book )

13 editions published in 1997 in English and held by 135 WorldCat member libraries worldwide

Intelligent Unmanned Ground Vehicles describes the technology developed and the results obtained by the Carnegie Mellon Robotics Institute in the course of the DARPA Unmanned Ground Vehicle (UGV) project. The goal of this work was to equip off-road vehicles with computer-controlled, unmanned driving capabilities. The book describes contributions in the area of mobility for UGVs including: tools for assembling complex autonomous mobility systems; on-road and off-road navigation; sensing techniques; and route planning algorithms. In addition to basic mobility technology, the book covers a number of integrated systems demonstrated in the field in realistic scenarios. The approaches presented in this book can be applied to a wide range of mobile robotics applications, from automated passenger cars to planetary exploration, and construction and agricultural machines. Intelligent Unmanned Ground Vehicles shows the progress that was achieved during this program, from brittle specially-built robots operating under highly constrained conditions, to groups of modified commercial vehicles operating in tough environments. One measure of progress is how much of this technology is being used in other applications. For example, much of the work in road-following, architectures and obstacle detection has been the basis for the Automated Highway Systems (AHS) prototypes currently under development. AHS will lead to commercial prototypes within a few years. The cross-country technology is also being used in the development of planetary rovers with a projected launch date within a few years. The architectural tools built under this program have been used in numerous applications, from an automated harvester to an autonomous excavator. The results reported in this work provide tools for further research development leading to practical, reliable and economical mobile robots
Proceedings / International NSF-ARPA Workshop : New York City, NY, USA, December 5 - 7, 1994 by National Science Foundation( Book )

1 edition published in 1995 in English and held by 12 WorldCat member libraries worldwide

Toward category-level object recognition by Jean Ponce( Book )

7 editions published in 2006 in English and held by 9 WorldCat member libraries worldwide

Although research in computer vision for recognizing 3D objects in photographs dates back to the 1960s, progress was relatively slow until the turn of the millennium, and only now do we see the emergence of effective techniques for recognizing object categories with different appearances under large variations in the observation conditions. Tremendous progress has been achieved in the past five years, thanks largely to the integration of new data representations, such as invariant semi-local features, developed in the computer vision community with the effective models of data distribution and classification procedures developed in the statistical machine-learning community. This volume is a post-event proceedings volume and contains selected papers based on presentations given, and vivid discussions held, during two workshops held in Taormina in 2003 and 2004. The main goals of these two workshops were to promote the creation of an international object recognition community, with common datasets and evaluation procedures, to map the state of the art and identify the main open problems and opportunities for synergistic research, and to articulate the industrial and societal needs and opportunities for object recognition research worldwide. The 30 thoroughly revised papers presented are organized in the following topical sections: recognition of specific objects, recognition of object categories, recognition of object categories with geometric relations, and joint recognition and segmentation
Reconnaissance de formes tridimensionnelles by Martial Hebert( Book )

3 editions published in 1983 in French and held by 6 WorldCat member libraries worldwide

Cette thèse présente un algorithme de reconnaissance permettant d'identifier des objets tridimensionnels placés dans une position quelconque et partiellement cachés. Le système utilise les données tridimensionnelles obtenues à partir d'un télémètre laser. Les surfaces ainsi mesurées sont segmentées en primitives simples. Le programme de reconnaissance compare cet ensemble de primitives à une description du modèle de référence. L'interprétation finale est obtenue en utilisant les contraintes géométriques liées à la rigidité des objets. Le système, qui a été expérimenté sur·des pièces industrielles, permet une identification rapide ainsi qu'une estimation précise de la position de la pièce reconnue
Representation and recognition of free-form surfaces by Hervé Delingette( Book )

2 editions published in 1992 in English and held by 5 WorldCat member libraries worldwide

Abstract: "We introduce a new surface representation for recognizing curved objects. Our approach begins by representing an object by a discrete mesh of points built from range data or from a geometric model of the object. The mesh is computed from the data by deforming a standard shaped mesh, for example, an ellipsoid, until it fits the surface of the object. We define local regularity constraints that the mesh must satisfy. We then define a canonical mapping between the mesh describing the object and a standard spherical mesh. A surface curvature index that is pose-invariant is stored at every node of the mesh. We use this object representation for recognition by comparing the spherical model of a reference object with the model extracted from a new observed scene
Task oriented vision by Katsushi Ikeuchi( Book )

1 edition published in 1991 in English and held by 5 WorldCat member libraries worldwide

Abstract: "This paper overviews two recently completed vision systems (a rock sampling system for planetary rovers and a bin-picking system for industrial robots). Then, we will examine the reason why these two systems have different architectures although their goals are roughly the same, picking up something by visual observation. Based on this discussion, we will develop the task-oriented vision paradigm, and examine the difference between the task-oriented vision paradigm and the traditional Marr's paradigm. We will also explore the research issues necessary for completing the task-oriented vision paradigm."
3-D vision techniques for autonomous vehicles by Martial Hebert( Book )

3 editions published in 1988 in English and held by 4 WorldCat member libraries worldwide

A Mobile robot needs an internal representation of its environment in order to accomplish its mission. Building such a representation involves transforming raw data from sensors into a meaningful geometric representation. In this paper, we introduce techniques for building terrain representations from range data for an outdoor mobile robot. We introduce three levels of representations that correspond to levels of planning: obstacle maps, terrain patches, and high resolution elevation maps. Since terrain representations from individual locations are not sufficient for many navigation tasks, we also introduce techniques for combining multiple maps. Combining maps may be achieved either by using features or the raw elevation data. Finally, we introduce algorithms for combining 3-D descriptions with descriptions from other sensors, such as color cameras. We examine the need for this type of sensor fusion when some semantic information has to be extracted from an observed scene and provide an example application of outdoor scene analysis. Many of the techniques presented in this paper have been tested in the field on three mobile robot systems developed at CMU. Keywords: Autonomous navigation; Three dimensional; Ground vehicles; Image processing; Optical processing. (sdw)
Combining shape and color information for 3D object recognition by Kazunori Higuchi( Book )

2 editions published in 1993 in English and held by 4 WorldCat member libraries worldwide

We show how this matching algorithm can be used for object recognition using both geometric and photometric information. In addition, we describe how the two types of information can be combined in a way that takes into account their actual distribution on the surface."
Spherical representations : from EGI to SAI by Katsushi Ikeuchi( Book )

2 editions published in 1995 in English and held by 4 WorldCat member libraries worldwide

Abstract: "One of the fundamental problems in representing a curved surface is how to define an intrinsic, i.e., viewer independent, coordinate system over a curved object surface. In order to establish point matching between model and observed feature distributions over the standard coordinate system, we need to set up a coordinate system that maps a point on a curved surface to a point on a standard coordinate system. This mapping should be independent of the viewing direction. Since the boundary of a 3-D object forms a closed surface, a coordinate system defined on the sphere is preferred. We have been exploring several intrinsic mappings from an object surface to a spherical surface. We have investigated several representations including: the EGI (Extended Gaussian Image), the DEGI (Distributed Extended Gaussian Image), the CEGI (Complex Extended Gaussian Image), and the SAI (Spherical Attribute Image). This paper summarizes our motivations to derive each representation and the lessons that we have learned through this endeavor."
On 3D shape similarity by Heung-Yeung Shum( Book )

2 editions published in 1995 in English and held by 4 WorldCat member libraries worldwide

Abstract: "We study the 3D shape similarity between closed surfaces. We represent a curved or polyhedral 3D object of genus zero using a mesh representation that has nearly uniform distribution with known connectivity among mesh nodes. We define a shape similarity metric based on the L₂ distance between the local curvature distributions over the mesh representations of the two objects. For both convex and concave objects, the shape metric can be computed in time O(n²), where n is the number of tessellation of sphere or the number of meshes which approximate the surface. Experiments show that our method produces good shape similarity measurements."
Building 3-D models from unregistered range images by Kazunori Higuchi( Book )

2 editions published in 1993 in English and held by 4 WorldCat member libraries worldwide

The meshes are built using an iterative fitting algorithm previously developed; the spherical images are built by mapping the nodes of the surface meshes to the nodes of a reference mesh on the unit sphere and by storing a measure of curvature at every node. We describe the algorithms used for building such models from range images and for matching them. We show results obtained using range images of complex objects."
Le mouvement en action : estimation du flot optique et localisation d'actions dans les vidéos by Philippe Weinzaepfel( )

1 edition published in 2016 in English and held by 3 WorldCat member libraries worldwide

With the recent overwhelming growth of digital video content, automatic video understanding has become an increasingly important issue.This thesis introduces several contributions on two automatic video understanding tasks: optical flow estimation and human action localization.Optical flow estimation consists in computing the displacement of every pixel in a video andfaces several challenges including large non-rigid displacements, occlusions and motion boundaries.We first introduce an optical flow approach based on a variational model that incorporates a new matching method.The proposed matching algorithm is built upon a hierarchical multi-layer correlational architecture and effectively handles non-rigid deformations and repetitive textures.It improves the flow estimation in the presence of significant appearance changes and large displacements.We also introduce a novel scheme for estimating optical flow based on a sparse-to-dense interpolation of matches while respecting edges.This method leverages an edge-aware geodesic distance tailored to respect motion boundaries and to handle occlusions.Furthermore, we propose a learning-based approach for detecting motion boundaries.Motion boundary patterns are predicted at the patch level using structured random forests.We experimentally show that our approach outperforms the flow gradient baseline on both synthetic data and real-world videos,including an introduced dataset with consumer videos.Human action localization consists in recognizing the actions that occur in a video, such as `drinking' or `phoning', as well as their temporal and spatial extent.We first propose a novel approach based on Deep Convolutional Neural Network.The method extracts class-specific tubes leveraging recent advances in detection and tracking.Tube description is enhanced by spatio-temporal local features.Temporal detection is performed using a sliding window scheme inside each tube.Our approach outperforms the state of the art on challenging action localization benchmarks.Second, we introduce a weakly-supervised action localization method, ie, which does not require bounding box annotation.Action proposals are computed by extracting tubes around the humans.This is performed using a human detector robust to unusual poses and occlusions, which is learned on a human pose benchmark.A high recall is reached with only several human tubes, allowing to effectively apply Multiple Instance Learning.Furthermore, we introduce a new dataset for human action localization.It overcomes the limitations of existing benchmarks, such as the diversity and the duration of the videos.Our weakly-supervised approach obtains results close to fully-supervised ones while significantly reducing the required amount of annotations
Object representation in computer vision I : International NSF-ARPA Workshop, New York City, NY, USA, December 5-7, 1994 : proceedings( Book )

2 editions published in 1995 in English and held by 3 WorldCat member libraries worldwide

A complete navigation system for goal acquisition in unknown environments by Anthony Stentz( Book )

2 editions published in 1994 in English and held by 3 WorldCat member libraries worldwide

With every image, the sensors provide new information about the world that can impact the robot's path to the goal. Some of the information is real, some arises from noise, and some arises from aliasing due to robot position error. Replanning may be needed for every image, and it may be nontrivial due to the unstructured nature of the environment. To address these problems, we have developed a complete system that integrates local and global navigation. This system is capable of finding a goal given no a priori map of the environment. It is robust to noise, vehicle position error, and is able to replan in real-time. We describe the system and present the results of experiments performed using a real robot."
Learning long-range vision for an offroad robot by Raia Thais Hadsell( Book )

1 edition published in 2008 in English and held by 3 WorldCat member libraries worldwide

Teaching a robot to perceive and navigate in an unstructured natural world is a difficult task. Without learning, navigation systems are short-range and extremely limited. With learning, the robot can be taught to classify terrain at longer distances, but these classifiers can be fragile as well, leading to extremely conservative planning. A robust, high-level learning-based perception system for a mobile robot needs to continually learn and adapt as it explores new environments. To do this, a strong feature representation is necessary that can encode meaningful, discriminative patterns as well as invariance to irrelevant transformations. A simple realtime classifier can then be trained on those features to predict the traversability of the current terrain
On 3D shape synthesis by Heung-Yeung Shum( Book )

2 editions published in 1995 in English and held by 3 WorldCat member libraries worldwide

Abstract: "We present a novel approach to 3D shape synthesis of closed surfaces. A curved or polyhedral 3D object of genus zero is represented by a curvature distribution on a spherical mesh that has nearly uniform distribution with known connectivity among mesh nodes. This curvature distribution, i.e., the result of forward mapping from shape space to curvature space, is used as the intrinsic shape representation because it is invariant to rigid transformation and scale factor. Furthermore, with regularity constraints on the mesh, the inverse mapping from curvature space to shape space always exists and can be recovered using an iterative method. Therefore, the task of synthesizing a new shape from two known objects becomes one of interpolating the two known curvature distributions, and then mapping the interpolated curvature distribution back to a 3D morph. Using the distance between two curvature distributions, we can quantitatively control the shape synthesis process to yeild [sic] smooth curvature migration. Experiments show that our method produces smooth and realistic shape morphs."
Refinement of seafloor elevation using acoustic backscatter by Andrew E Johnson( Book )

2 editions published in 1995 in English and held by 2 WorldCat member libraries worldwide

Abstract: "We propose an algorithm for the reconstruction of elevation and material property maps of the seafloor using a sidescan sonar backscatter image and sparse bathymetric points co-registered within the image. Given a path for the sensor, the reconstruction is corrected for the movement of the fish during the image generation process. To perform reconstruction, an arbitrary but computable scattering model is assumed for the seafloor backscatter. The algorithm uses the sparse bathymetric data to generate an initial estimate for the elevation map which is then iteratively refined to fit the backscatter image by minimizing a global error functional. Concurrently, the parameters of the scattering model are determined on a coarse grid in the image by fitting the assumed scattering model to the backscatter data. The elevation surface and the scattering parameter maps converge to their best fit shape and values given the backscatter data. The reconstruction is corrected for the movement of the sensor by initially doing local reconstructions in sensor coordinates and then transforming the local reconstructions to a global coordinate system and performing the reconstruction again. The algorithm supports different scattering models, so it can be applied to different underwater environments and sonar sensors. In addition to the elevation map of the seafloor, the parameters of the scattering model at every point in the image are generated. Since these parameters describe material properties of the seafloor, the maps of the scattering model parameters can be used to segment the seafloor by material type."
Real-time 3-D pose estimation using a high-speed range sensor by David A Simon( Book )

2 editions published in 1993 in English and held by 2 WorldCat member libraries worldwide

Abstract: "This report describes a system which can perform full 3-D pose estimation of a single arbitrarily shaped, rigid object at rates up to 10Hz. A triangular mesh model of the object to be tracked is generated offline using conventional range sensors. Real-time range data of the object is sensed by the CMU high speed VLSI range sensor. Pose estimation is performed by registering the real-time range data to the triangular mesh model using an enhanced implementation of the Iterative Closest Point (ICP) Algorithm introduced by Besl and McKay. The method does not require explicit feature extraction or specification of correspondence. Pose estimation accuracies on the order of 1mm in translation and 1 degree in rotation have been measured."
 
moreShow More Titles
fewerShow Fewer Titles
Audience Level
0
Audience Level
1
  Kids General Special  
Audience level: 0.72 (from 0.54 for Toward cat ... to 0.97 for Object rep ...)

Object representation in computer vision : International NSF-ARPA Workshop, New York City, NY, USA, December 5-7, 1994 : proceedingsProceedings / International NSF-ARPA Workshop : New York City, NY, USA, December 5 - 7, 1994Object representation in computer vision I : International NSF-ARPA Workshop, New York City, NY, USA, December 5-7, 1994 : proceedings
Alternative Names
Hebert, Martial H.

Hebert, Martial H. 1958-

Languages
Covers
Object representation in computer vision II : ECCV '96 International Workshop, Cambridge, UK, April 13-14, 1996 : proceedingsIntelligent unmanned ground vehicles : autonomous navigation research at Carnegie MellonProceedings / International NSF-ARPA Workshop : New York City, NY, USA, December 5 - 7, 1994Toward category-level object recognitionObject representation in computer vision I : International NSF-ARPA Workshop, New York City, NY, USA, December 5-7, 1994 : proceedings