Results 1 - 10 of 2,315

Bilateral Filtering for Gray and Color Images

by C. Tomasi , 1998
"... tomasi @ cs.stanford.edu Bilateral filtering smooths images while preserving edges, by means of a nonlinear combination of nearby image values. The method is noniterative, local, and sim-ple. It combines gray levels or colors based on both their geometric closeness and their photometric similariv, a ..."
Abstract - Cited by 1156 (2 self) - Add to MetaCart
tomasi @ cs.stanford.edu Bilateral filtering smooths images while preserving edges, by means of a nonlinear combination of nearby image values. The method is noniterative, local, and sim-ple. It combines gray levels or colors based on both their geometric closeness and their photometric similariv

Iterative point matching for registration of free-form curves and surfaces

by Zhengyou Zhang , 1994
"... A heuristic method has been developed for registering two sets of 3-D curves obtained by using an edge-based stereo system, or two dense 3-D maps obtained by using a correlation-based stereo system. Geometric matching in general is a difficult unsolved problem in computer vision. Fortunately, in ma ..."
Abstract - Cited by 660 (8 self) - Add to MetaCart
A heuristic method has been developed for registering two sets of 3-D curves obtained by using an edge-based stereo system, or two dense 3-D maps obtained by using a correlation-based stereo system. Geometric matching in general is a difficult unsolved problem in computer vision. Fortunately

Autograph: Toward automated, distributed worm signature detection

by Hyang-ah Kim - In Proceedings of the 13th Usenix Security Symposium , 2004
"... Today’s Internet intrusion detection systems (IDSes) monitor edge networks ’ DMZs to identify and/or filter malicious flows. While an IDS helps protect the hosts on its local edge network from compromise and denial of service, it cannot alone effectively intervene to halt and reverse the spreading o ..."
Abstract - Cited by 362 (3 self) - Add to MetaCart
Today’s Internet intrusion detection systems (IDSes) monitor edge networks ’ DMZs to identify and/or filter malicious flows. While an IDS helps protect the hosts on its local edge network from compromise and denial of service, it cannot alone effectively intervene to halt and reverse the spreading

Going out: Robust modelbased tracking for outdoor augmented reality

by Gerhard Reitmayr, Tom W. Drummond - Proceedings of 5th IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR , 2006
"... Figure 1: (Left) A user operating a handheld augmented reality unit tracked in an urban environment. (Middle) Live shot showing the unit tracking a building. (Right) Screenshot from a pose close to the left images with overlaid building outline. This paper presents a model-based hybrid tracking syst ..."
Abstract - Cited by 66 (3 self) - Add to MetaCart
model, and uses instead a coarse, but textured, 3D model. This yields several advantages: scale-based detail culling is automatic, appearance-based edge signatures can be used to improve matching and the models needed are more commonly available. The accuracy and robustness of the resulting system

3-D model-based tracking of humans in action: a multi-view approach

by D. M. Gavrila, L. S. Davis , 1996
"... We present a vision system for the 3-D model-based tracking of unconstrained human movement. Using image sequences acquired simultaneously from multiple views, we recover the 3-D body pose at each time instant without the use of markers. The pose recovery problem is formulated as a search problem ..."
Abstract - Cited by 355 (9 self) - Add to MetaCart
We present a vision system for the 3-D model-based tracking of unconstrained human movement. Using image sequences acquired simultaneously from multiple views, we recover the 3-D body pose at each time instant without the use of markers. The pose recovery problem is formulated as a search problem

Appearance-based minimalistic metric SLAM

by Paul E. Rybski, Stergios I. Roumeliotis, Maria Gini, Nikolaos Papanikolopoulos - IN PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON ROBOTICS AND INTELLIGENT SYSTEMS (IROS), LAS VEGAS, USA , 2003
"... This paper addresses the problem of Simultaneous Localization and Mapping (SLAM) for the case of very small, resource-limited robots which have poor odometry and can typically only carry a single monocular camera. We propose a modification to the standard SLAM algorithm in which the assumption that ..."
Abstract - Cited by 10 (2 self) - Add to MetaCart
that the robots can obtain metric distance/bearing information to landmarks is relaxed. Instead, the robot registers a distinctive sensor “signature”, based on its current location, which is used to match robot positions. In our formulation of this non-linear estimation problem, we infer implicit position

Learning Discriminative Appearance-Based Models Using Partial Least Squares

by William Robson Schwartz, Larry S. Davis
"... Appearance information is essential for applications such as tracking and people recognition. One of the main problems of using appearance-based discriminative models is the ambiguities among classes when the number of persons being considered increases. To reduce the amount of ambiguity, we propose ..."
Abstract - Cited by 70 (1 self) - Add to MetaCart
Appearance information is essential for applications such as tracking and people recognition. One of the main problems of using appearance-based discriminative models is the ambiguities among classes when the number of persons being considered increases. To reduce the amount of ambiguity, we

Semi-Autonomous Generation of Appearance-based Edge Models from Image Sequences

by Jeremiah Neubert, John Pretlove, Tom Drummond
"... Figure 1: Creation of 3D edge models directly from image sequences. The user indicates planar regions of an object to generate a polygon in (a). The planar regions are reconstructed, keyframes, consisting of sets of edgels (white lines) inside the planar region, are selected to capture viewpoint rel ..."
Abstract - Cited by 6 (0 self) - Add to MetaCart
and network connection. The process of creating the model requires minimal user interaction in the form of a few cues to identify planar regions on the object of interest. In addition the system selects a set of keyframes for each region to capture viewpoint based appearance changes. This work also presents a

Appearance-Based Mapping using Minimalistic Sensor Models

by Paul E. Rybski, Stergios Roumeliotis, Maria Gini, Nikolaos Papanikopoulos
"... This paper addresses the problem of localization and map construction by a mobile robot in an indoor environment. Instead of trying to build high-fidelity geometric maps, we focus on constructing topological maps as they are less sensitive to poor odometry estimates and position errors. We propose a ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
a modification to the standard SLAM algorithm in which the assumption that the robots can obtain metric distance/bearing information to landmarks is relaxed. Instead, the robot registers a distinctive sensor “signature”, based on its current location, which is used to match robot positions. In our

Appearance-based mapping using minimalistic sensor models

by Paul E. Rybski, Stergios Roumeliotis, Maria Gini, Nikolaos Papanikopoulos , 2008
"... This paper addresses the problem of localization and map construction by a mobile robot in an indoor environment. Instead of trying to build high-fidelity geometric maps, we focus on constructing topological maps as they are less sensitive to poor odometry estimates and position errors. We propose ..."
Abstract - Add to MetaCart
a modification to the standard SLAM algorithm in which the assumption that the robots can obtain metric distance/bearing information to landmarks is relaxed. Instead, the robot registers a distinctive sensor “signature”, based on its current location, which is used to match robot positions. In our
Results 1 - 10 of 2,315