Search For:

Displaying 1-42 out of 42 total
Color Image Labelling Using Linear Programming
Found in: Digital Image Computing: Techniques and Applications
By Hongdong Li, Chunhua Shen, Zhiying Wen
Issue Date:December 2007
pp. 239-244
This paper describes a linear programming (LP) algorithm for labelling (segmenting) a color image into multiple regions. Compared with the recently-proposed semi-definite programming (SDP) relaxation based algorithm, our algorithm has a simpler mathematica...
 
The 3D-3D Registration Problem Revisited
Found in: Computer Vision, IEEE International Conference on
By Hongdong Li, Richard Hartley
Issue Date:October 2007
pp. 1-8
We describe a new framework for globally solving the 3D-3D registration problem with unknown point correspondences. This problem is significant as it is frequently encountered in many applications. Existing methods are not fully satisfactory, mainly due to...
 
Efficient Computation of Relative Pose for Multi-camera Systems
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Laurent Kneip,Hongdong Li
Issue Date:June 2014
pp. 446-453
We present a novel solution to compute the relative pose of a generalized camera. Existing solutions are either not general, have too high computational complexity, or require too many correspondences, which impedes an efficient or accurate usage within Ra...
 
Go-ICP: Solving 3D Registration Efficiently and Globally Optimally
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jiaolong Yang,Hongdong Li,Yunde Jia
Issue Date:December 2013
pp. 1457-1464
Registration is a fundamental task in computer vision. The Iterative Closest Point (ICP) algorithm is one of the widely-used methods for solving the registration problem. Based on local iteration, ICP is however well-known to suffer from local minima. Its ...
 
Line Drawing Interpretation Using Belief Propagation
Found in: Digital Image Computing: Techniques and Applications
By Yansheng Ming,Hongdong Li,Jun Sun
Issue Date:December 2011
pp. 113-118
The interpretation of line drawings of trihedral planer objects is a classic problem. In this paper, it is formulated as a Bayesian inference problem. Given a line drawing image, a Markov random field can be built whose nodes represent the labels of edges....
 
Analysis on Tree Structure Selection for MRF Inference in Low-level Vision
Found in: Digital Image Computing: Techniques and Applications
By Jun Sun,Hongdong Li,Xuming He
Issue Date:December 2011
pp. 66-71
MRF inference on the 4-connected grid is popularly utilized for early vision tasks. But due to the loopy structure of the 4-connected grid, inference becomes complicated and less efficient. This paper present a theoretical analysis on what is an optimal sp...
 
Efficient Image Denoising by MRF Approximation with Uniform-Sampled Multi-spanning-tree
Found in: Image and Graphics, International Conference on
By Jun Sun,Hongdong Li,Xuming He
Issue Date:August 2011
pp. 88-93
Traditionally, image processing based on Markov Random Field (MRF) is often addressed on a 4-connected grid graph defined on the image. This structure is not computationally efficient. In our work, we develop a multiple-trees structure to approximate the 4...
 
Support vector regression for multi-view gait recognition based on local motion feature selection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Worapan Kusakunniran, Qiang Wu, Jian Zhang, Hongdong Li
Issue Date:June 2010
pp. 974-981
Gait is a well recognized biometric feature that is used to identify a human at a distance. However, in real environment, appearance changes of individuals due to viewing angle changes cause many difficulties for gait recognition. This paper re-formulates ...
 
Multi-view structure computation without explicitly estimating motion
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hongdong Li
Issue Date:June 2010
pp. 2777-2784
Most existing structure-from-motion methods follow a common two-step scheme, where relative camera motions are estimated in the first step and 3D structure is computed afterward in the second step. This paper presents a novel scheme which bypasses the moti...
 
A Direct Method to Self-Calibrate a Surveillance Camera by Observing a Walking Pedestrian
Found in: Digital Image Computing: Techniques and Applications
By Worapan Kusakunniran, Hongdong Li, Jian Zhang
Issue Date:December 2009
pp. 250-255
Recent efforts show that it is possible to calibrate a surveillance camera simply from observing a walking human. This procedure can be seen as a special application of the camera self-calibration technique. Several methods have been proposed along this li...
 
Handling Significant Scale Difference for Object Retrieval in a Supermarket
Found in: Digital Image Computing: Techniques and Applications
By Yuhang Zhang, Lei Wang, Richard Hartley, Hongdong Li
Issue Date:December 2009
pp. 468-475
We propose an object retrieval application which can retrieve user specified objects from a big supermarket. Significant and unpredictable scale difference between the query and the database image is the major obstacle encountered. The widely used local in...
 
Smooth Approximation of L_infinity-Norm for Multi-view Geometry
Found in: Digital Image Computing: Techniques and Applications
By Yuchao Dai, Hongdong Li, Mingyi He, Chunhua Shen
Issue Date:December 2009
pp. 339-346
Recently the $L_\infty$-norm optimization has been introduced to multi-view geometry to achieve global optimality. It is solved through solving a sequence of SOCP (second order cone programming) feasibility problems which needs sophisticated solvers and ti...
 
Automatic Gait Recognition Using Weighted Binary Pattern on Video
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Worapan Kusakunniran, Qiang Wu, Hongdong Li, Jian Zhang
Issue Date:September 2009
pp. 49-54
Human identification by recognizing the spontaneous gait recorded in real-world setting is a tough and not yet fully resolved problem in biometrics research. Several issues have contributed to the difficulties of this task. They include various poses, diff...
 
Efficient reduction of L-infinity geometry problems
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hongdong Li
Issue Date:June 2009
pp. 2695-2702
This paper presents a new method for computing optimal L<sub>infin</sub> solutions for vision geometry problems, particularly for those problems of fixed-dimension and of large-scale. Our strategy for solving a large L<sub>infin</sub&g...
 
Multi-view Human Motion Capture with an Improved Deformation Skin Model
Found in: Digital Image Computing: Techniques and Applications
By Yifan Lu, Lei Wang, Richard Hartley, Hongdong Li, Chunhua Shen
Issue Date:December 2008
pp. 420-427
Markerless human motion capture has received much attention in computer vision and computer graphics communities. A hierarchical skeleton template is frequently used to model the human body in literature, because it simplifies markerless human motion captu...
 
Motion estimation for multi-camera systems using global optimization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jae-Hak Kim, Hongdong Li, Richard Hartley
Issue Date:June 2008
pp. 1-8
We present a motion estimation algorithm for multicamera systems consisting of more than one calibrated camera securely attached on a moving object. So, they move all together, but do not require to have overlapping views across the cameras. The geometrica...
 
Optimizing over Radial Kernels on Compact Manifolds
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Sadeep Jayasumana,Richard Hartley,Mathieu Salzmann,Hongdong Li,Mehrtash Harandi
Issue Date:June 2014
pp. 3802-3809
We tackle the problem of optimizing over all possible positive definite radial kernels on Riemannian manifolds for classification. Kernel methods on Riemannian manifolds have recently become increasingly popular in computer vision. However, the number of k...
 
A Framework for Shape Analysis via Hilbert Space Embedding
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Sadeep Jayasumana,Mathieu Salzmann,Hongdong Li,Mehrtash Harandi
Issue Date:December 2013
pp. 1249-1256
We propose a framework for 2D shape analysis using positive definite kernels defined on Kendall's shape manifold. Different representations of 2D shapes are known to generate different nonlinear spaces. Due to the nonlinearity of these spaces, most existin...
 
Multi-view 3D Reconstruction from Uncalibrated Radially-Symmetric Cameras
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jae-Hak Kim,Yuchao Dai,Hongdong Li,Xin Du,Jonghyuk Kim
Issue Date:December 2013
pp. 1896-1903
We present a new multi-view 3D Euclidean reconstruction method for arbitrary uncalibrated radially-symmetric cameras, which needs no calibration or any camera model parameters other than radial symmetry. It is built on the radial 1D camera model [25], a un...
 
Projective Multiview Structure and Motion from Element-Wise Factorization
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yuchao Dai, Hongdong Li, Mingyi He
Issue Date:September 2013
pp. 2238-2251
The Sturm-Triggs type iteration is a classic approach for solving the projective structure-from-motion (SfM) factorization problem, which iteratively solves the projective depths, scene structure, and camera motions in an alternated fashion. Like many othe...
 
A Branch-and-Bound Approach to Correspondence and Grouping Problems
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By J. Bazin, Hongdong Li, In So Kweon,C. Demonceaux,P. Vasseur,K. Ikeuchi
Issue Date:July 2013
pp. 1565-1576
Data correspondence/grouping under an unknown parametric model is a fundamental topic in computer vision. Finding feature correspondences between two images is probably the most popular application of this research field, and is the main motivation of our ...
 
An Efficient Hidden Variable Approach to Minimal-Case Camera Motion Estimation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By R. Hartley, Hongdong Li
Issue Date:December 2012
pp. 2303-2314
In this paper, we present an efficient new approach for solving two-view minimal-case problems in camera motion estimation, most notably the so-called five-point relative orientation problem and the six-point focal-length problem. Our approach is based on ...
 
Connected contours: A new contour completion model that respects the closure effect
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Yansheng Ming, Hongdong Li, Xuming He
Issue Date:June 2012
pp. 829-836
Contour Completion plays an important role in visual perception, where the goal is to group fragmented low-level edge elements into perceptually coherent and salient contours. This process is often considered as guided by some middle-level Gestalt principl...
 
A simple prior-free method for non-rigid structure-from-motion factorization
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Yuchao Dai, Hongdong Li, Mingyi He
Issue Date:June 2012
pp. 2018-2025
This paper proposes a simple “prior-free” method for solving non-rigid structure-from-motion factorization problems. Other than using the basic low-rank condition, our method does not assume any extra prior knowledge about the nonrigid scene or about the c...
 
Pairwise Shape configuration-based PSA for gait recognition under small viewing angle change
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Worapan Kusakunniran, Qiang Wu, Jian Zhang, Hongdong Li
Issue Date:September 2011
pp. 17-22
Two main components of Procrustes Shape Analysis (PSA) are adopted and adapted specifically to address gait recognition under small viewing angle change: 1) Procrustes Mean Shape (PMS) for gait signature description; 2) Procrustes Distance (PD) for similar...
 
Multi-view Gait Recognition Based on Motion Regression Using Multilayer Perceptron
Found in: Pattern Recognition, International Conference on
By Worapan Kusakunniran, Qiang Wu, Jian Zhang, Hongdong Li
Issue Date:August 2010
pp. 2186-2189
It has been shown that gait is an efficient biometric feature for identifying a person at a distance. However, it is a challenging problem to obtain reliable gait feature when viewing angle changes because the body appearance can be different under the var...
 
Estimating Relative Camera Motion from the Antipodal-Epipolar Constraint
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By John Lim, Nick Barnes, Hongdong Li
Issue Date:October 2010
pp. 1907-1914
This paper introduces a novel antipodal-epipolar constraint on relative camera motion. By using antipodal points, which are available in large Field-of-View cameras, the translational and rotational motions of a camera are geometrically decoupled, allowing...
 
Two Efficient Algorithms for Outlier Removal in Multi-view Geometry Using L-Infinity Norm
Found in: Image and Graphics, International Conference on
By Yuchao Dai, Mingyi He, Hongdong Li
Issue Date:September 2009
pp. 325-330
L-Infinity norm has been recently introduced to multi-view geometry computation to achieve globally optimal computation. It however suffers from a serious sensitivity to outliers. A few remedies have been proposed but with high computational complexity. Th...
 
Motion Estimation for Nonoverlapping Multicamera Rigs: Linear Algebraic and {\rm L}_\infty Geometric Solutions
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jae-Hak Kim, Hongdong Li, Richard Hartley
Issue Date:June 2010
pp. 1044-1059
We investigate the problem of estimating the ego-motion of a multicamera rig from two positions of the rig. We describe and compare two new algorithms for finding the 6 degrees of freedom (3 for rotation and 3 for translation) of the motion. One algorithm ...
 
Self-Calibrating Cameras Using Semidefinite Programming
Found in: Digital Image Computing: Techniques and Applications
By Chunhua Shen, Hongdong Li, Michael J. Brooks
Issue Date:December 2008
pp. 436-441
Novel methods are proposed for self-calibrating a pure-rotating camera using semidefinite programming (SDP). Key to the approach is the use of the positive-definiteness requirement for the dual image of the absolute conic (DIAC). The problem is couched wit...
 
A linear approach to motion estimation using generalized camera models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hongdong Li, Richard Hartley, Jae-hak Kim
Issue Date:June 2008
pp. 1-8
A well-known theoretical result for motion estimation using the generalized camera model is that 17 corresponding image rays can be used to solve linearly for the motion of a generalized camera. However, this paper shows that for many common configurations...
 
Two-View Motion Segmentation from Linear Programming Relaxation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hongdong Li
Issue Date:June 2007
pp. 1-8
This paper studies the problem of multibody motion segmentation, which is an important, but challenging problem due to its well-known chicken-and-egg-type recursive character. We propose a new Mixture-of-Fundamental-matrices model to describe the multibody...
 
A practical algorithm for L triangulation with outliers
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hongdong Li
Issue Date:June 2007
pp. 1-8
This paper addresses the problem of robust optimal multi-view triangulation. We propose an abstract framework, as well as a practical algorithm, which finds the best 3D reconstruction with guaranteed global optimality even in the presence of outliers. Our ...
 
Classification-Based Likelihood Functions for Bayesian Tracking
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Chunhua Shen, Hongdong Li, Michael J. Brooks
Issue Date:November 2006
pp. 33
The success of any Bayesian particle filtering based tracker relies heavily on the ability of the likelihood function to discriminate between the state that fits the image well and those that do not. This paper describes a general framework for learning pr...
 
An LMI Approach for Reliable PTZ Camera Self-Calibration
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Hongdong Li, Chunhua Shen
Issue Date:November 2006
pp. 79
PTZ (Pan-Tilt-Zoom) cameras are widely used for large-area video surveillance. For many visual tracking and video analysis tasks, an accurate camera calibration is very important. Traditional off-line camera calibration algorithms are often not satisfactor...
 
Five-Point Motion Estimation Made Easy
Found in: Pattern Recognition, International Conference on
By Hongdong Li, Richard Hartley
Issue Date:August 2006
pp. 630-633
Estimating relative camera motion from two calibrated views is a classical problem in computer vision. The minimal case for such problem is the so-called five-point problem, for which the state-of-the-art solution is Nist?er?s algorithm [1][2]. However, du...
 
Video Local Pattern based Image Matching for Visual Mapping
Found in: Pattern Recognition, International Conference on
By Lei Wang, Hongdong Li, Richard Hartley
Issue Date:August 2006
pp. 67-70
Image matching plays an important role in visual mapping, a critical task of vision based mobile robot navigation. Based on the observation that the visual content in these video sequences generally changes in a slow and continuous mode, a concept of
 
Auto-Calibration of a Compound-Type Omnidirectional Camera
Found in: Digital Image Computing: Techniques and Applications
By Hongdong Li, Richard Hartley, Lei Wang
Issue Date:December 2005
pp. 26
We propose a method for auto-calibrating a compound-type omnidirectional camera (system). This camera produces spherical panoramic image through stitching some individual images captured by several modular cameras, each of which covers a different field of...
 
Efficient dense subspace clustering
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Pan Ji,Mathieu Salzmann, Hongdong Li
Issue Date:March 2014
pp. 461-468
In this paper, we tackle the problem of clustering data points drawn from a union of linear (or affine) subspaces. To this end, we introduce an efficient subspace clustering algorithm that estimates dense connections between the points lying in the same su...
   
Winding Number for Region-Boundary Consistent Salient Contour Extraction
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Yansheng Ming,Hongdong Li,Xuming He
Issue Date:June 2013
pp. 2818-2825
This paper aims to extract salient closed contours froman image. For this vision task, both region segmentation cues (e.g. color/texture homogeneity) and boundary detection cues (e.g. local contrast, edge continuity and contour closure) play important and ...
 
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Sadeep Jayasumana,Richard Hartley,Mathieu Salzmann,Hongdong Li,Mehrtash Harandi
Issue Date:June 2013
pp. 73-80
Symmetric Positive Definite (SPD) matrices have become popular to encode image information. Accounting for the geometry of the Riemannian manifold of SPD matrices has proven key to the success of many algorithms. However, most existing methods only approxi...
 
Feature Extraction Using Sequential Semidefinite Programming
Found in: Digital Image Computing: Techniques and Applications
By Chunhua Shen, Hongdong Li, Michael J. Brooks
Issue Date:December 2007
pp. 430-437
Many feature extraction approaches end up with a trace quotient formulation. Since it is difficult to directly solve the trace quotient problem, conventionally the trace quotient cost is replaced by an approximation such that the generalised eigen-decompos...
 
 1