Search For:

Displaying 1-50 out of 90 total
Inference of Integrated Surface, Curve, and Junction Descriptions From Sparse 3D Data
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chi-Keung Tang, Gérard Medioni
Issue Date:November 1998
pp. 1206-1223
<p><b>Abstract</b>—We are interested in descriptions of 3D data sets, as obtained from stereo or a 3D digitizer. We therefore consider as input a sparse set of points, possibly associated with certain orientation information. In this pape...
 
Towards a practical PTZ face detection and tracking system
Found in: 2013 IEEE Workshop on Applications of Computer Vision (WACV)
By Yinghao Cai,Gerard Medioni,Thang Ba Dinh
Issue Date:January 2013
pp. 31-38
We address the problem of automatic face detection and tracking in uncontrolled scenarios using a pan-tilt-zoom (PTZ) network camera, which could prove most helpful in forensic applications. The detected faces are associated with the corresponding people a...
 
Accurate Full Body Scanning from a Single Fixed 3D Camera
Found in: 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)
By Ruizhe Wang,Jongmoo Choi,Gerard Medioni
Issue Date:October 2012
pp. 432-439
3D body modeling has been a long studied topic in computer vision and computer graphics. While several solutions have been proposed using either multiple sensors or a moving sensor, we propose here an approach when the user turns, in a natural motion, in f...
 
Real-time 3-D face tracking and modeling from awebcam
Found in: Applications of Computer Vision, IEEE Workshop on
By Jongmoo Choi,Yann Dumortier,Sang-Il Choi,Muhammad Bilal Ahmad,Gerard Medioni
Issue Date:January 2012
pp. 33-40
We first infer a 3-D face model from a single frontal image using automatically extracted 2-D landmarks and deforming a generic 3-D model. Then, for any input image, we extract feature points and track them in 2-D. Given these correspondences, sometimes no...
 
Accurate efficient mosaicking for Wide Area Aerial Surveillance
Found in: Applications of Computer Vision, IEEE Workshop on
By Jan Prokaj,Gerard Medioni
Issue Date:January 2012
pp. 273-280
Wide Area Aerial Surveillance (WAAS) imagery is captured by an array of smaller sensors sharing an optical center, instead of one large sensor. It is desirable to generate a single image (mosaic) from the sensor array, since it simplifies higher level visi...
 
Aerial 3D reconstruction with line-constrained dynamic programming
Found in: Computer Vision, IEEE International Conference on
By Huei-Hung Liao, Yuping Lin,Gerard Medioni
Issue Date:November 2011
pp. 1855-1862
Aerial imagery of an urban environment is often characterized by significant occlusions, sharp edges, and textureless regions, leading to poor 3D reconstruction using conventional multi-view stereo methods. In this paper, we propose a novel approach to 3D ...
 
Dynamic Manifold Warping for view invariant action recognition
Found in: Computer Vision, IEEE International Conference on
By Dian Gong,Gerard Medioni
Issue Date:November 2011
pp. 571-578
We address the problem of learning view-invariant 3D models of human motion from motion capture data, in order to recognize human actions from a monocular video sequence with arbitrary viewpoint. We propose a Spatio-Temporal Manifold (STM) model to analyze...
 
Robust unsupervised motion pattern inference from video and applications
Found in: Computer Vision, IEEE International Conference on
By Xuemei Zhao,Gerard Medioni
Issue Date:November 2011
pp. 715-722
We propose an unsupervised learning framework to infer motion patterns in videos and in turn use them to improve tracking of moving objects in sequences from static cameras. Based on tracklets, we use a manifold learning method Tensor Voting to infer the l...
 
Scalable Object Classification Using Range Images
Found in: 3D Imaging, Modeling, Processing, Visualization and Transmission, International Conference on
By Eunyoung Kim,Gerard Medioni
Issue Date:May 2011
pp. 65-72
We present a novel scalable framework for free-form object classification in range images. The framework includes an automatic 3D object recognition system in range images and a scalable database structure to learn new instances and new categories efficien...
 
Color Constancy Using Standard Deviation of Color Channels
Found in: Pattern Recognition, International Conference on
By Anustup Choudhury, Gérard Medioni
Issue Date:August 2010
pp. 1722-1726
We address here the problem of color constancy and propose a new method to achieve color constancy based on the statistics of images with color cast. Images with color cast have standard deviation of one color channel significantly different from that of o...
 
3D Face Reconstruction Using a Single or Multiple Views
Found in: Pattern Recognition, International Conference on
By Jongmoo Choi, Gérard Medioni, Yuping Lin, Luciano Silva, Olga Regina, Mauricio Pamplona, Timothy C. Faltemier
Issue Date:August 2010
pp. 3959-3962
We present a 3D face reconstruction system that takes as input either one single view or several different views. Given a facial image, we first classify the facial pose into one of five predefined poses, then detect two anchor points that are then used to...
 
Dense Structure Inference for Object Classification in Aerial LIDAR Dataset
Found in: Pattern Recognition, International Conference on
By Eunyoung Kim, Gérard Medioni
Issue Date:August 2010
pp. 3049-3052
We present a framework to classify small freeform objects in 3D aerial scans of a large urban area. The system first identifies large structures such as the ground surface and roofs of buildings densely built in the scene, by fitting planar patches and gro...
 
Accurate 3D face reconstruction from weakly calibrated wide baseline images with profile contours
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuping Lin, Gerard Medioni, Jongmoo Choi
Issue Date:June 2010
pp. 1490-1497
We propose a method to generate a highly accurate 3D face model from a set of wide-baseline images in a weakly calibrated setup. Our approach is purely data driven, and produces faithful 3D models without any pre-defined models, unlike other statistical mo...
 
Multiple-Target Tracking by Spatiotemporal Monte Carlo Markov Chain Data Association
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Qian Yu, Gérard Medioni
Issue Date:December 2009
pp. 2196-2210
We propose a framework for tracking multiple targets, where the input is a set of candidate regions in each frame, as obtained from a state-of-the-art background segmentation module, and the goal is to recover trajectories of targets over time. Due to occl...
 
A GPU-based implementation of motion detection from a moving platform
Found in: Computer Vision and Pattern Recognition Workshop
By Qian Yu, Gerard Medioni
Issue Date:June 2008
pp. 1-6
We describe a GPU-based implementation of motion detection from a moving platform. Motion detection from a moving platform is inherently difficult as the moving camera induces 2D motion field in the entire image. A step compensating for camera motion is re...
 
Mutual information computation and maximization using GPU
Found in: Computer Vision and Pattern Recognition Workshop
By Yuping Lin, Gerard Medioni
Issue Date:June 2008
pp. 1-6
We present a GPU implementation to compute both mutual information and its derivatives. Mutual information computation is a highly demanding process due to the enormous number of exponential computations. It is therefore the bottleneck in many image regist...
 
3D face tracking and expression inference from a 2D sequence using manifold learning
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Wei-Kai Liao, Gerard Medioni
Issue Date:June 2008
pp. 1-8
We propose a person-dependent, manifold-based approach for modeling and tracking rigid and nonrigid 3D facial deformations from a monocular video sequence. The rigid and nonrigid motions are analyzed simultaneously in 3D, by automatically fitting and track...
 
Retinal image registration from 2D to 3D
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuping Lin, Gerard Medioni
Issue Date:June 2008
pp. 1-8
We propose a 2D registration method for multi-modal image sequences of the retinal fundus, and a 3D metric reconstruction of near planar surface from multiple views. There are two major contributions in our paper. For 2D registration, our method produces h...
 
Two-Frames Accurate Motion Segmentation Using Tensor Voting and Graph-Cuts
Found in: Motion and Video Computing, IEEE Workshop on
By Thang Dinh, Gerard Medioni
Issue Date:January 2008
pp. 1-8
Motion segmentation and motion estimation are important topics in computer vision. Tensor Voting is a process that addresses both issues simultaneously; but running time is a challenge. We propose a novel approach which can yield both the motion segmentati...
 
Integrated Detection and Tracking for Multiple Moving Objects using Data-Driven MCMC Data Association
Found in: Motion and Video Computing, IEEE Workshop on
By Qian Yu, Gerard Medioni
Issue Date:January 2008
pp. 1-8
We propose a framework to address the multiple target tracking problem, which is to recover trajectories of targets of interest over time from noisy observations. Due to occlusions by targets and static objects, parallax or other moving objects, foreground...
 
Inferring Segmented Dense Motion Layers Using 5D Tensor Voting
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Changki Min, Gérard Medioni
Issue Date:September 2008
pp. 1589-1602
We present a novel local spatiotemporal approach to produce motion segmentation and dense temporal trajectories from an image sequence. A common representation of image sequences is a 3D spatiotemporal volume, (x,y,t), and its corresponding mathematical fo...
 
3-D Metric Reconstruction and Registration of Images of Near-planar Surfaces
Found in: Computer Vision, IEEE International Conference on
By Tae Eun Choe, Gerard Medioni
Issue Date:October 2007
pp. 1-8
In this study, we address the problem of 3-D dense metric reconstruction and registration from multiple images, given that the observed surface is nearly planar. This is difficult, as classical methods work well only if the scene is truly planar (mosaicing...
 
Detecting Motion Regions in the Presence of a Strong Parallax from a Moving Camera by Multiview Geometric Constraints
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chang Yuan, Gerard Medioni, Jinman Kang, Isaac Cohen
Issue Date:September 2007
pp. 1627-1641
We present a method for detecting motion regions in video sequences observed by a moving camera, in the presence of strong parallax due to static 3D structures. The proposed method classifies each image pixel into planar background, parallax or motion regi...
 
Map-Enhanced UAV Image Sequence Registration and Synchronization of Multiple Image Sequences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuping Lin, Gerard Medioni
Issue Date:June 2007
pp. 1-7
Registering consecutive images from an airborne sensor into a mosaic is an essential tool for image analysts. Strictly local methods tend to accumulate errors, resulting in distortion. We propose here to use a reference image (such as a high resolution map...
 
Inferring 3D Volumetric Shape of Both Moving Objects and Static Background Observed by a Moving Camera
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Chang Yuan, Gerard Medioni
Issue Date:June 2007
pp. 1-8
We present a novel approach to inferring 3D volumetric shape of both moving objects and static background from video sequences shot by a moving camera, with the assumption that the objects move rigidly on a ground plane. The 3D scene is divided into a set ...
 
Multiple Target Tracking Using Spatio-Temporal Markov Chain Monte Carlo Data Association
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Qian Yu, Gerard Medioni, Isaac Cohen
Issue Date:June 2007
pp. 1-8
We propose a framework for general multiple target tracking, where the input is a set of candidate regions in each frame, as obtained from a state of the art background learning, and the goal is to recover trajectories of targets over time from noisy obser...
 
Map-Enhanced UAV Image Sequence Registration
Found in: Applications of Computer Vision, IEEE Workshop on
By Yuping Lin, Qian Yu, Gerard Medioni
Issue Date:February 2007
pp. 15
Registering consecutive images from an airborne sensor into a mosaic is an essential tool for image analysts. Strictly local methods tend to accumulate errors, resulting in distortion. We propose here to use a reference image (such as a high resolution map...
 
Map-Enhanced Detection and Tracking from a Moving Platform with Local and Global Data Association
Found in: Motion and Video Computing, IEEE Workshop on
By Qian Yu, Gerard Medioni
Issue Date:February 2007
pp. 3
We present an approach to detect and track moving objects from a moving platform. Moreover, given a global map, such as a satellite image, our approach can locate and track the targets in geo-coordinates, namely longitude and latitude. The map information ...
 
Real Time Limb Tracking with Adaptive Model Selection
Found in: Pattern Recognition, International Conference on
By Matheen Siddiqui, Gerard Medioni
Issue Date:August 2006
pp. 770-773
We describe an efficient and robust method of tracking human forearms as skin colored regions. Of special consideration in the design of this system are real-time and robustness issues. We approach this as 2D tracking problem using skin color and edge info...
 
Tensor Voting Accelerated by Graphics Processing Units (GPU)
Found in: Pattern Recognition, International Conference on
By Changki Min, Gerard Medioni
Issue Date:August 2006
pp. 1103-1106
This paper presents a new GPU-based tensor voting implementation which achieves significant performance improvement over the conventional CPU-based implementation. Although the tensor voting framework has been used for many vision problems, it is computati...
 
Optimal Global Mosaic Generation from Retinal Images
Found in: Pattern Recognition, International Conference on
By Tae Eun Choe, Isaac Cohen, Munwai Lee, Gerard Medioni
Issue Date:August 2006
pp. 681-684
We present a method to construct a mosaic from multiple color and fluorescein retinal images. A set of images taken from different views at different times is difficult to register sequentially due to variations in color and intensity across images. We pro...
 
Boosted Markov Chain Monte Carlo Data Association for Multiple Target Detection and Tracking
Found in: Pattern Recognition, International Conference on
By Qian Yu, Isaac Cohen, Gerard Medioni, Bo Wu
Issue Date:August 2006
pp. 675-678
In this paper, we present a probabilistic framework for automatic detection and tracking of objects. We address the data association problem by formulating the visual tracking as finding the best partition of a measurement graph containing all detected mov...
 
Multi-layer Mosaics in the Presence of Motion and Depth Effects
Found in: Pattern Recognition, International Conference on
By Changki Min, Qian Yu, Gerard Medioni
Issue Date:August 2006
pp. 992-995
In this paper, we present a new segmentation-based 2D mosaic framework. Most of current mosaic algorithms do not explicitly remove moving objects from images before registration, so that they often fail when the size of the moving objects is relatively lar...
 
Stereo Using Monocular Cues within the Tensor Voting Framework
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Philippos Mordohai, Gérard Medioni
Issue Date:June 2006
pp. 968-982
We address the fundamental problem of matching in two static images. The remaining challenges are related to occlusion and lack of texture. Our approach addresses these difficulties within a perceptual organization framework, considering both binocular and...
 
3-D Shape Reconstruction of Retinal Fundus
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tae Eun Choe, Isaac Cohen, Gerard Medioni
Issue Date:June 2006
pp. 2277-2284
We present a method for 3-D shape reconstruction of retinal fundus from fluorescein images. Our method extracts the location of vessels? bifurcation as a reliable feature for estimating the epipolar geometry using a plane-and-parallax approach. The propose...
 
Motion Segmentation by Spatiotemporal Smoothness Using 5D Tensor Voting
Found in: Computer Vision and Pattern Recognition Workshop
By Changki Min, Gerard Medioni
Issue Date:June 2006
pp. 199
Our goal is to recover temporal trajectories of all pixels in a reference image for the given image sequence, and segment the image based on motion similarities. These trajectories can be visualized by observing the 3D (x, y, t) spatiotemporal volume. The ...
 
3D Reconstruction of Background and Objects Moving on Ground Plane Viewed from a Moving Camera
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Chang Yuan, Gerard Medioni
Issue Date:June 2006
pp. 2261-2268
We present a novel method to obtain a 3D Euclidean reconstruction of both the background and moving objects in a video sequence. We assume that, multiple objects are moving rigidly on a ground plane observed by a moving camera. The video sequence is first ...
 
Performance of Geometrix ActiveID^TM 3D Face Recognition Engine on the FRGC Data
Found in: Computer Vision and Pattern Recognition Workshop
By Thomas Maurer, David Guigonis, Igor Maslov, Bastien Pesenti, Alexei Tsaregorodtsev, David West, Gerard Medioni
Issue Date:June 2005
pp. 154
<p>We present and analyze the performance of the Geometrix ActiveIDTM Biometric Identity System on the FRGC data from Experiment 3, consisting of 4007 3D faces. The performance is presented and analyzed for different facial expression categories. We ...
 
A Voting-Based Computational Framework for Visual Motion Analysis and Interpretation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Mircea Nicolescu, Gérard Medioni
Issue Date:May 2005
pp. 739-752
Most approaches for motion analysis and interpretation rely on restrictive parametric models and involve iterative methods which depend heavily on initial conditions and are subject to instability. Further difficulties are encountered in image regions wher...
 
Persistent Objects Tracking Across Multiple Non Overlapping Cameras
Found in: Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on
By Jinman Kang, Isaac Cohen, Gérard Medioni
Issue Date:January 2005
pp. 112-119
We present an approach for persistent tracking of moving objects observed by non-overlapping and moving cameras. Our approach robustly recovers the geometry of non-overlapping views using a moving camera that pans across the scene. We address the tracking ...
 
Simultaneous Two-View Epipolar Geometry Estimation and Motion Segmentation by 4D Tensor Voting
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Wai-Shun Tong, Chi-Keung Tang, Gérard Medioni
Issue Date:September 2004
pp. 1167-1184
We address the problem of simultaneous two-view epipolar geometry estimation and motion segmentation from nonstatic scenes. Given a set of noisy image pairs containing matches of n objects, we propose an unconventional, efficient, and robust method, 4D ten...
 
Dense Multiple View Stereo with General Camera Placement using Tensor Voting
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Philippos Mordohai, Gérard Medioni
Issue Date:September 2004
pp. 725-732
We present a computational framework for the inference of dense descriptions from multiple view stereo with general camera placement. Thus far research on dense multiple view stereo has evolved along three axes: computation of scene approximations in the f...
 
Non-Iterative Approach to Multiple 2D Motion Estimation
Found in: Pattern Recognition, International Conference on
By Eun-Young Kang, Isaac Cohen, Gerard Medioni
Issue Date:August 2004
pp. 791-794
We present an innovative method estimating multiple 2D motions from uncalibrated images. Our approach robustly and non-iteratively estimates multiple 2D parametric motions, affine or homography, from noisy initial matches without pre-specifying the number ...
 
3D Modeling from Turntable Sequences Using Dense Stereo Carving and Multi-View Consistency
Found in: Pattern Recognition, International Conference on
By Jordi Arnabat, Selma Casanovas, Gérard Medioni
Issue Date:August 2004
pp. 36-39
This paper addresses the problem of reconstructing a 3-D model, with texture, from a sequence of images of the object taken from a turntable. Previous approaches have successfully solved the problem either using active interaction techniques, like the lase...
 
Tracking Soccer Players using the Graph Representation
Found in: Pattern Recognition, International Conference on
By Pascual Figueroa, Neucimar Leite, Ricardo M. L. Barros, Isaac Cohen, Gerard Medioni
Issue Date:August 2004
pp. 787-790
In this work, we consider the problem of tracking soccer players during a game by using multiple cameras. The main goal consists in finding the position of the players on the pitch at each instance of time. The occlusion is treated by splitting segmented b...
 
Object Reacquisition Using Invariant Appearance Model
Found in: Pattern Recognition, International Conference on
By Jinman Kang, Isaac Cohen, Gérard Medioni
Issue Date:August 2004
pp. 759-762
We present an approach for reacquisition of detected moving objects. We address the tracking problem by modeling the appearance of the moving region using stochastic models. The appearance of the object is described by multiple models representing spatial ...
 
Detection and Tracking of Moving Objects from Overlapping EO and IR Sensors
Found in: Computer Vision and Pattern Recognition Workshop
By Jinman Kang, Kalpitkumar Gajera, Isaac Cohen, Gérard Medioni
Issue Date:July 2004
pp. 123
We present an approach for tracking moving objects observed by EO and IR sensors on a moving platform. Our approach detects and tracks the moving objects after accurately recovering the geometric relationship between different sensors. We address the track...
 
Matching and Interpretation of Planar Motion Using Tensor Voting
Found in: Computer Vision and Pattern Recognition Workshop
By Changki Min, Gérard Medioni
Issue Date:July 2004
pp. 57
An ellipse that is rotating within an image can be interpreted in different ways under different conditions. We are interested in the 'thin vs. fat ellipse' phenomenon; a thin rotating ellipse is perceived as undergoing rigid rotation, while a fat one is p...
 
An Overview of the 2004 Workshop on Perceptual Organization in Computer Vision
Found in: Computer Vision and Pattern Recognition Workshop
By Anthony Hoogs, Gerard Medioni
Issue Date:July 2004
pp. 42
The 2004 Workshop on POCV emphasized novel, far-reaching ideas in PO rather than extensive experimental validation. This was intended to stimulate more discussion and debate than is typically feasible at a conference such as CVPR. We facilitated this goal ...
   
Junction Inference and Classification for Figure Completion using Tensor Voting
Found in: Computer Vision and Pattern Recognition Workshop
By Philippos Mordohai, Gérard Medioni
Issue Date:July 2004
pp. 56
We address the issues associated with figure completion, a perceptual grouping task. Endpoints and junctions play a critical role in contour completion by the human visual system and should be an integral part of a computational process that attempts to em...
 
 1  2 Next >>