Search For:

Displaying 1-46 out of 46 total
A Geometric Particle Filter for Template-Based Visual Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Junghyun Kwon, Hee Seok Lee,Frank C. Park, Kyoung Mu Lee
Issue Date:April 2014
pp. 625-643
Existing approaches to template-based visual tracking, in which the objective is to continuously estimate the spatial transformation parameters of an object template over video frames, have primarily been based on deterministic optimization, which as is we...
 
Optical Flow via Locally Adaptive Fusion of Complementary Data Costs
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Tae Hyun Kim,Hee Seok Lee,Kyoung Mu Lee
Issue Date:December 2013
pp. 3344-3351
Many state-of-the-art optical flow estimation algorithms optimize the data and regularization terms to solve ill-posed problems. In this paper, in contrast to the conventional optical flow framework that uses a single or fixed data model, we study a novel ...
 
Joint Depth Map and Color Consistency Estimation for Stereo Images with Different Illuminations and Cameras
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yong Seok Heo, Kyoung Mu Lee, Sang Uk Lee
Issue Date:May 2013
pp. 1094-1106
In this paper, we propose a method that infers both accurate depth maps and color-consistent stereo images for radiometrically varying stereo images. In general, stereo matching and performing color consistency between stereo images are a chicken-and-egg p...
 
Stereo reconstruction using high order likelihood
Found in: Computer Vision, IEEE International Conference on
By Ho Yub Jung,Kyoung Mu Lee,Sang Uk Lee
Issue Date:November 2011
pp. 1211-1218
Under the popular Bayesian approach, a stereo problem can be formulated by defining likelihood and prior. Likelihoods are often associated with unary terms and priors are defined by pair-wise or higher order cliques in Markov random field (MRF). In this pa...
 
Simultaneous localization, mapping and deblurring
Found in: Computer Vision, IEEE International Conference on
By Hee Seok Lee,Junghyun Kwon,Kyoung Mu Lee
Issue Date:November 2011
pp. 1203-1210
Handling motion blur is one of important issues in visual SLAM. For a fast-moving camera, motion blur is an unavoidable effect and it can degrade the results of localization and reconstruction severely. In this paper, we present a unified algorithm to hand...
 
Hyper-graph matching via reweighted random walks
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jungmin Lee, Minsu Cho, Kyoung Mu Lee
Issue Date:June 2011
pp. 1633-1640
Establishing correspondences between two feature sets is a fundamental issue in computer vision, pattern recognition, and machine learning. This problem can be well formulated as graph matching in which nodes represent feature points while edges describe p...
 
A Unified Probabilistic Approach to Feature Matching and Object Segmentation
Found in: Pattern Recognition, International Conference on
By Tae Hoon Kim, Kyoung Mu Lee, Sang Uk Lee
Issue Date:August 2010
pp. 464-467
This paper deals with feature matching and segmentation of common objects in a pair of images, simultaneously. For the feature matching problem, the matching likelihoods of all feature correspondences are obtained by combining their discriminative power wi...
 
A Graph Matching Algorithm Using Data-Driven Markov Chain Monte Carlo Sampling
Found in: Pattern Recognition, International Conference on
By Jungmin Lee, Minsu Cho, Kyoung Mu Lee
Issue Date:August 2010
pp. 2816-2819
We propose a novel stochastic graph matching algorithm based on data-driven Markov Chain Monte Carlo (DDMCMC) sampling technique. The algorithm explores the solution space efficiently and avoid local minima by taking advantage of spectral properties of the...
 
Nonparametric higher-order learning for interactive segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tae Hoon Kim, Kyoung Mu Lee, Sang Uk Lee
Issue Date:June 2010
pp. 3201-3208
In this paper, we deal with a generative model for multilabel, interactive segmentation. To estimate the pixel likelihoods for each label, we propose a new higher-order formulation additionally imposing the soft label consistency constraint whereby the pix...
 
Mutual information-based stereo matching combined with SIFT descriptor in log-chromaticity color space
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yong Seok Heo, Kyoung Mu Lee, Sang Uk Lee
Issue Date:June 2009
pp. 445-452
Radiometric variations between input images can seriously degrade the performance of stereo matching algorithms. In this situation, mutual information is a very popular and powerful measure which can find any global relationship of intensities between two ...
 
Segment-based Foreground Object Disparity Estimation Using Zcam and Multiple-View Stereo
Found in: Intelligent Information Hiding and Multimedia Signal Processing, International Conference on
By Tae Hoon Kim, Hoyub Jung, Kyoung Mu Lee, Sang Uk Lee
Issue Date:August 2008
pp. 1251-1254
3D videos play an important role in adoption of 3DTV display modules for the masses because creating realistic contents for 3DTV is a hard and time-consuming process. In this paper, we consider the problem of generating three-view 3D video depth using a se...
 
Illumination and camera invariant stereo matching
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yong Seok Heo, Kyoung Mu Lee, Sang Uk Lee
Issue Date:June 2008
pp. 1-8
Color information can be used as a basic and crucial cue for finding correspondence in a stereo matching algorithm. In a real scene, however, image colors are affected by various geometric and radiometric factors. For this reason, the raw color recorded by...
 
Multiview normal field integration using level set methods
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ju Yong Chang, Kyoung Mu Lee, Sang Uk Lee
Issue Date:June 2007
pp. 1-8
In this paper, we propose a new method to integrate multiview normal fields using level sets. In contrast with conventional normal integration algorithms used in shape from shading and photometric stereo that reconstruct a 2.5D surface using a single-view ...
 
Simultaneous Depth Reconstruction and Restoration of Noisy Stereo Images using Non-local Pixel Distribution
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yong Seok Heo, Kyoung Mu Lee, Sang Uk Lee
Issue Date:June 2007
pp. 1-8
In this paper, we propose a new algorithm that solves both the stereo matching and the image denoising problem simultaneously for a pair of noisy stereo images. Most stereo algorithms employ L1 or L2 intensity error-based data costs in the MAP-MRF framewor...
 
Face Recognition Using Face-ARG Matching
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Bo-Gun Park, Kyoung-Mu Lee, Sang-Uk Lee
Issue Date:December 2005
pp. 1982-1988
In this paper, we propose a novel line feature-based face recognition algorithm. A face is represented by the Face-ARG model, where all the geometric quantities and the structural information are encoded in an Attributed Relational Graph (ARG) structure, t...
 
A Dense Stereo Matching Using Two-Pass Dynamic Programming with Generalized Ground Control Points
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jae Chul Kim, Kyoung Mu Lee, Byoung Tae Choi, Sang Uk Lee
Issue Date:June 2005
pp. 1075-1082
A method for solving dense stereo matching problem is presented in this paper. First, a new generalized ground control points (GGCPs) scheme is introduced, where one or more disparity candidates for the true disparity of each pixel are assigned by local ma...
 
Recognition and Reconstruction of 3-D Objects Using Model-Based Perceptual Grouping
Found in: Pattern Recognition, International Conference on
By In Kyu Park, Sang Uk Lee, Kyoung Mu Lee
Issue Date:September 2000
pp. 1720
In this paper, we address a new algorithm for recognition and reconstruction of 3-D polyhedral objects, based on perceptual grouping and graph search technique. Perceptual grouping is performed in a model-based framework, in which decision tree classifier ...
 
Interval Tracker: Tracking by Interval Analysis
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Junseok Kwon,Kyoung Mu Lee
Issue Date:June 2014
pp. 3494-3501
This paper proposes a robust tracking method that uses interval analysis. Any single posterior model necessarily includes a modeling uncertainty (error), and thus, the posterior should be represented as an interval of probability. Then, the objective of vi...
 
Segmentation-Free Dynamic Scene Deblurring
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Tae Hyun Kim,Kyoung Mu Lee
Issue Date:June 2014
pp. 2766-2773
Most state-of-the-art dynamic scene deblurring methods based on accurate motion segmentation assume that motion blur is small or that the specific type of motion causing the blur is known. In this paper, we study a motion segmentation-free dynamic scene de...
 
Scanline Sampler without Detailed Balance: An Efficient MCMC for MRF Optimization
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Wonsik Kim,Kyoung Mu Lee
Issue Date:June 2014
pp. 1354-1361
Markov chain Monte Carlo (MCMC) is an elegant tool, widely used in variety of areas. In computer vision, it has been used for the inference on the Markov random field model (MRF). However, MCMC less concerned than other deterministic approaches although it...
 
Dynamic Scene Deblurring
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Tae Hyun Kim,Byeongjoo Ahn,Kyoung Mu Lee
Issue Date:December 2013
pp. 3160-3167
Most conventional single image deblurring methods assume that the underlying scene is static and the blur is caused by only camera shake. In this paper, in contrast to this restrictive assumption, we address the deblurring problem of general dynamic scenes...
 
Wang-Landau Monte Carlo-Based Tracking Methods for Abrupt Motions
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Junseok Kwon, Kyoung Mu Lee
Issue Date:April 2013
pp. 1011-1024
We propose a novel tracking algorithm based on the Wang-Landau Monte Carlo (WLMC) sampling method for dealing with abrupt motions efficiently. Abrupt motions cause conventional tracking methods to fail because they violate the motion smoothness constraint....
 
A unified framework for event summarization and rare event detection
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Junseok Kwon, Kyoung Mu Lee
Issue Date:June 2012
pp. 1266-1273
In this paper, we have proposed an unified framework for event summarization and rare event detection and presented the graph-structure learning and editing method to solve these problems efficiently. The experimental results demonstrated that the proposed...
 
Robust visual tracking using autoregressive hidden Markov Model
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Dong Woo Park, Junseok Kwon, Kyoung Mu Lee
Issue Date:June 2012
pp. 1964-1971
Recent studies on visual tracking have shown significant improvement in accuracy by handling the appearance variations of the target object. Whereas most studies present schemes to extract the time-invariant characteristics of the target and adaptively upd...
 
Learning object relationships via graph-based context model
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Heesoo Myeong, Ju Yong Chang, Kyoung Mu Lee
Issue Date:June 2012
pp. 2727-2734
In this paper, we propose a novel framework for modeling image-dependent contextual relationships using graph-based context model. This approach enables us to selectively utilize the contextual relationships suitable for an input query image. We introduce ...
 
Mode-seeking on graphs via random walks
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Minsu Cho, Kyoung Mu Lee
Issue Date:June 2012
pp. 606-613
Mode-seeking has been widely used as a powerful data analysis technique for clustering and filtering in a metric feature space. We introduce a versatile and efficient mode-seeking method for “graph” representation where general embedding of relational data...
 
Progressive graph matching: Making a move of graphs via probabilistic voting
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Minsu Cho, Kyoung Mu Lee
Issue Date:June 2012
pp. 398-405
Graph matching is widely used in a variety of scientific fields, including computer vision, due to its powerful performance, robustness, and generality. Its computational complexity, however, limits the permissible size of input graphs in practice. Therefo...
 
Tracking by Sampling Trackers
Found in: Computer Vision, IEEE International Conference on
By Junseok Kwon, Kyoung Mu Lee
Issue Date:November 2011
pp. 1195-1202
We propose a novel tracking framework called visual tracker sampler that tracks a target robustly by searching for the appropriate trackers in each frame. Since the real-world tracking environment varies severely over time, the trackers should be adapted o...
 
Continuous Markov Random Field Optimization Using Fusion Move Driven Markov Chain Monte Carlo Technique
Found in: Pattern Recognition, International Conference on
By Wonsik Kim, Kyoung Mu Lee
Issue Date:August 2010
pp. 1364-1367
Many vision applications have been formulated as Markov Random Field (MRF) problems. Although many of them are discrete labeling problems, continuous formulation often achieves great improvement on the qualities of the solutions in some applications such a...
 
Co-recognition of Actions in Video Pairs
Found in: Pattern Recognition, International Conference on
By Young Min Shin, Minsu Cho, Kyoung Mu Lee
Issue Date:August 2010
pp. 456-459
In this paper, we present a method that recognizes single or multiple common actions between a pair of video sequences. We establish an energy function that evaluates geometric and photometric consistency, and solve the action recognition problem by optimi...
 
Unsupervised detection and segmentation of identical objects
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Minsu Cho, Young Min Shin, Kyoung Mu Lee
Issue Date:June 2010
pp. 1617-1624
We address an unsupervised object detection and segmentation problem that goes beyond the conventional assumptions of one-to-one object correspondences or modeltest settings between images. Our method can detect and segment identical objects directly from ...
 
Visual tracking decomposition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Junseok Kwon, Kyoung Mu Lee
Issue Date:June 2010
pp. 1269-1276
We propose a novel tracking algorithm that can work robustly in a challenging scenario such that several kinds of appearance and motion changes of an object occur at the same time. Our algorithm is based on a visual tracking decomposition scheme for the ef...
 
Monocular SLAM with locally planar landmarks via geometric rao-blackwellized particle filtering on Lie groups
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Junghyun Kwon, Kyoung Mu Lee
Issue Date:June 2010
pp. 1522-1529
We propose a novel geometric Rao-Blackwellized particle filtering framework for monocular SLAM with locally planar landmarks. We represent the states for the camera pose and the landmark plane normal as SE(3) and SO(3), respectively, which are both Lie gro...
 
Learning full pairwise affinities for spectral segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tae Hoon Kim, Kyoung Mu Lee
Issue Date:June 2010
pp. 2101-2108
This paper studies the problem of learning a full range of pairwise affinities gained by integrating local grouping cues for spectral segmentation. The overall quality of the spectral segmentation depends mainly on the pairwise pixel affinities. By employi...
 
Markov Chain Monte Carlo combined with deterministic methods for Markov random field optimization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Wonsik Kim, Kyoung Mu Lee
Issue Date:June 2009
pp. 1406-1413
Many vision problems have been formulated as energy minimization problems and there have been significant advances in energy minimization algorithms. The most widely-used energy minimization algorithms include graph cuts, belief propagation and tree-reweig...
 
Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive Basin Hopping Monte Carlo sampling
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Junseok Kwon, Kyoung Mu Lee
Issue Date:June 2009
pp. 1208-1215
We propose a novel tracking algorithm for the target of which geometric appearance changes drastically over time. To track it, we present a local patch-based appearance model and provide an efficient scheme to evolve the topology between local patches by o...
 
Visual tracking via geometric particle filtering on the affine group with optimal importance functions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Junghyun Kwon, Kyoung Mu Lee, F.C. Park
Issue Date:June 2009
pp. 991-998
We propose a geometric method for visual tracking, in which the 2-D affine motion of a given object template is estimated in a video sequence by means of coordinate-invariant particle filtering on the 2-D affine group Aff(2). Tracking performance is furthe...
 
Partially Occluded Object-Specific Segmentation in View-Based Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Minsu Cho, Kyoung Mu Lee
Issue Date:June 2007
pp. 1-7
We present a novel object-specific segmentation method which can be used in view-based object recognition systems. Previous object segmentation approaches generate inexact results especially in partially occluded and cluttered environment because their top...
 
Robust Stereo Matching Using Adaptive Normalized Cross-Correlation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yong Seok Heo, Kyoung Mu Lee, Sang Uk Lee
Issue Date:April 2011
pp. 807-822
A majority of the existing stereo matching algorithms assume that the corresponding color values are similar to each other. However, it is not so in practice as image color values are often affected by various radiometric factors such as illumination direc...
 
Learning Full Pairwise Affinities for Spectral Segmentation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Tae Hoon Kim, Kyoung Mu Lee, Sang Uk Lee
Issue Date:July 2013
pp. 1690-1703
Segmenting a single image into multiple coherent groups remains a challenging task in the field of computer vision. Particularly, spectral segmentation which uses the global information embedded in the spectrum of a given image's affinity matrix is a major...
 
Multi-image matching for a general motion stereo camera model
Found in: Image Processing, International Conference on
By Ku Ja Seong, Lee Kyoung Mu, Lee Sang Uk
Issue Date:October 1998
pp. 608
The aim of motion stereo is to extract the 3-D information of an object from images of a moving camera using the geometric relationships between corresponding points. This paper presents an accurate and robust motion stereo algorithm employing multiple ima...
 
Tracking by Sampling and IntegratingMultiple Trackers
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Junseok Kwon,Kyoung Mu Lee
Issue Date:July 2014
pp. 1428-1441
We propose the visual tracker sampler, a novel tracking algorithm that can work robustly in challenging scenarios, where several kinds of appearance and motion changes of an object can occur simultaneously. The proposed tracking algorithm accurately tracks...
 
Highly Nonrigid Object Tracking via Patch-Based Dynamic Appearance Modeling
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Junseok Kwon, Kyoung Mu Lee
Issue Date:October 2013
pp. 2427-2441
A novel tracking algorithm is proposed for targets with drastically changing geometric appearances over time. To track such objects, we develop a local patch-based appearance model and provide an efficient online updating scheme that adaptively changes the...
 
Tensor-Based High-Order Semantic Relation Transfer for Semantic Scene Segmentation
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Heesoo Myeong,Kyoung Mu Lee
Issue Date:June 2013
pp. 3073-3080
We propose a novel nonparametric approach for semantic segmentation using high-order semantic relations. Conventional context models mainly focus on learning pairwise relationships between objects. Pairwise relations, however, are not enough to represent h...
 
Minimum Uncertainty Gap for Robust Visual Tracking
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Junseok Kwon,Kyoung Mu Lee
Issue Date:June 2013
pp. 2355-2362
We propose a novel tracking algorithm that robustly tracks the target by finding the state which minimizes uncertainty of the likelihood at current state. The uncertainty of the likelihood is estimated by obtaining the gap between the lower and upper bound...
 
A genetic algorithm with local map for path planning in dynamic environments
Found in: Proceedings of the 11th Annual conference on Genetic and evolutionary computation (GECCO '09)
By Ivan Koryakovskiy, Kyoung Mu Lee, Nguyen Xuan Hoai
Issue Date:July 2009
pp. 46-52
In this paper, a new genetic algorithm (GA) for solving the path planning in dynamic environments is proposed. The new genetic algorithm uses local maps, therefore, does not require the knowledge of exact or estimated position of the destination point as o...
     
 1