Search For:

Displaying 1-43 out of 43 total
Fast Rotation Search with Stereographic Projections for 3D Registration
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Alvaro Joaquin Parra Bustos,Tat-Jun Chin,David Suter
Issue Date:June 2014
pp. 3930-3937
Recently there has been a surge of interest to use branch-and-bound (bnb) optimisation for 3D point cloud registration. While bnb guarantees globally optimal solutions, it is usually too slow to be practical. A fundamental source of difficulty is the searc...
 
Fast Supervised Hashing with Decision Trees for High-Dimensional Data
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Guosheng Lin,Chunhua Shen,Qinfeng Shi,Anton van den Hengel,David Suter
Issue Date:June 2014
pp. 1971-1978
Supervised hashing aims to map the original features to compact binary codes that are able to preserve label based similarity in the Hamming space. Non-linear hash functions have demonstrated their advantage over linear ones due to their powerful generaliz...
 
A General Two-Step Approach to Learning-Based Hashing
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Guosheng Lin,Chunhua Shen,David Suter,Anton van den Hengel
Issue Date:December 2013
pp. 2552-2559
Most existing approaches to hashing apply a single form of hash function, and an optimization process which is typically deeply coupled to this specific form. This tight coupling restricts the flexibility of the method to respond to the data, and can resul...
 
Simultaneously Fitting and Segmenting Multiple-Structure Data with Outliers
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Hanzi Wang,Tat-Jun Chin,David Suter
Issue Date:June 2012
pp. 1177-1192
We propose a robust fitting framework, called Adaptive Kernel-Scale Weighted Hypotheses (AKSWH), to segment multiple-structure data even in the presence of a large number of outliers. Our framework contains a novel scale estimator called Iterative Kth Orde...
 
An adversarial optimization approach to efficient outlier removal
Found in: Computer Vision, IEEE International Conference on
By Jin Yu,Anders Eriksson, Tat-Jun Chin,David Suter
Issue Date:November 2011
pp. 399-406
This paper proposes a novel adversarial optimization approach to efficient outlier removal in computer vision. We characterize the outlier removal problem as a game that involves two players of conflicting interests, namely, optimizer and outlier. Such an ...
 
Dynamic and hierarchical multi-structure geometric model fitting
Found in: Computer Vision, IEEE International Conference on
By Hoi Sim Wong,Tat-Jun Chin,Jin Yu,David Suter
Issue Date:November 2011
pp. 1044-1051
The ability to generate good model hypotheses is instrumental to accurate and robust geometric model fitting. We present a novel dynamic hypothesis generation algorithm for robust fitting of multiple structures. Underpinning our method is a fast guided sam...
 
Multi-structure model selection via kernel optimisation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tat-Jun Chin, David Suter, Hanzi Wang
Issue Date:June 2010
pp. 3586-3593
Our goal is to fit the multiple instances (or structures) of a generic model existing in data. Here we propose a novel model selection scheme to estimate the number of genuine structures present. In contrast to conventional model selection approaches, our ...
 
Object Detection Using a Cascade of Classifiers
Found in: Digital Image Computing: Techniques and Applications
By Nayyar A. Zaidi, David Suter
Issue Date:December 2008
pp. 600-605
Typical object detection systems work by training a classifier on features extracted at different scales ofan object. In this paper we investigate the performance of an object detection system in which different classifiers which are trained at various sca...
 
Multi-scale Conditional Random Fields for over-segmented irregular 3D point clouds classification
Found in: Computer Vision and Pattern Recognition Workshop
By Ee Hui Lim, David Suter
Issue Date:June 2008
pp. 1-7
In this paper, we propose using multi-scale Conditional Random Fields to classes 3D outdoor terrestrial laser scanned data. We improved Lim and Suter’s methods [1] by introducing regional edge potentials in addition to the local edge and node potentials in...
 
Improved building detection by Gaussian processes classification via feature space rescale and spectral kernel selection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By David Suter
Issue Date:June 2008
pp. 1-6
We use spectral analysis to facilitate Gaussian processes (GP) classification. Our solution provides two improvements: scaling of the data to achieve a more isotropic nature, as well as a method to choose the kernel to match certain data characteristics. G...
 
Out-of-Sample Extrapolation of Learned Manifolds
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Tat-Jun Chin, David Suter
Issue Date:September 2008
pp. 1547-1556
We investigate the problem of extrapolating the embedding of a manifold learned from finite samples to novel out-of-sample data. We concentrate on the manifold learning method called Maximum Variance Unfolding (MVU) for which the extrapolation problem is s...
 
Adaptive Object Tracking Based on an Effective Appearance Filter
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Hanzi Wang, David Suter, Konrad Schindler, Chunhua Shen
Issue Date:September 2007
pp. 1661-1667
We propose a similarity measure based on a Spatial-color Mixture of Gaussians (SMOG) appearance model for particle filters. This improves on the popular similarity measure based on color histograms because it considers not only the colors in a region but a...
 
Recognizing Human Activities from Silhouettes: Motion Subspace and Factorial Discriminative Graphical Model
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Liang Wang, David Suter
Issue Date:June 2007
pp. 1-8
We describe a probabilistic framework for recognizing human activities in monocular video based on simple silhouette observations in this paper. The methodology combines kernel principal component analysis (KPCA) based feature extraction and factorial cond...
 
Fast Sparse Gaussian Processes Learning for Man-Made Structure Classification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hang Zhou, David Suter
Issue Date:June 2007
pp. 1-6
Informative Vector Machine (IVM) is an efficient fast sparse Gaussian processs (GP) method previously suggested for active learning. It greatly reduces the computational cost of GP classification and makes the GP learning close to real time. We apply IVM f...
 
Analyzing Human Movements from Silhouettes Using Manifold Learning
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Liang Wang, David Suter
Issue Date:November 2006
pp. 7
A novel method for learning and recognizing sequential image data is proposed, and promising applications to vision-based human movement analysis are demonstrated. To find more compact representations of high-dimensional silhouette data, we exploit localit...
 
Improving the Speed of Kernel PCA on Large Scale Datasets
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Tat-Jun Chin, David Suter
Issue Date:November 2006
pp. 41
This paper concerns making large scale Kernel Principal Component Analysis (KPCA) feasible on regular hardware. The KPCA has been proven a useful non-linear feature extractor in several computer vision applications. The standard computation method for KPCA...
 
A Compact Architecture for Wireless Video Surveillance over CDMA Network
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Hang Zhou, David Suter
Issue Date:November 2006
pp. 102
Wireless video surveillance over CDMA network enables transfer of high quality live video via public wireless broadband, which is accessible anywhere with CDMA mobile phone network coverage. Real time video can be received on an internet connected PC, lapt...
 
Human Motion De-noising via Greedy Kernel Principal Component Analysis Filtering
Found in: Pattern Recognition, International Conference on
By Therdsak Tangkuampien, David Suter
Issue Date:August 2006
pp. 457-460
Kernel principal component analysis (KPCA) has been shown to be a powerful non-linear de-noising technique. A disadvantage of KPCA, however, is that the storage of the kernel matrix grows quadratically, and the evaluation cost grows linearly with the numbe...
 
Background Subtraction Based on a Robust Consensus Method
Found in: Pattern Recognition, International Conference on
By Hanzi Wang, David Suter
Issue Date:August 2006
pp. 223-226
Statistical background modeling is a fundamental and important part of many visual tracking systems and of other computer vision applications. In this paper, we presents an effective and adaptive background modeling method for detecting foreground objects ...
 
Informative Shape Representations for Human Action Recognition
Found in: Pattern Recognition, International Conference on
By Liang Wang, David Suter
Issue Date:August 2006
pp. 1266-1269
Shape and kinematics are two important cues in human movement analysis. Due to real difficulties in extracting kinematics from videos accurately, this paper proposes to address the problem of human action recognition by spatiotemporal shape analysis. Witho...
 
Efficient Visual Tracking by Probabilistic Fusion of Multiple Cues
Found in: Pattern Recognition, International Conference on
By Hanzi Wang, David Suter
Issue Date:August 2006
pp. 892-895
It has been shown that integrating multiple cues will increase the reliability and robustness of a vision system in situations that no single cue is reliable. In this paper, we propose a method by fusing multiple cues (i.e., the color cue and the edge cue)...
 
Two-View Multibody Structure-and-Motion with Outliers through Model Selection
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Konrad Schindler, David Suter
Issue Date:June 2006
pp. 983-995
Multibody structure-and-motion (MSaM) is the problem to establish the multiple-view geometry of several views of a 3D scene taken at different times, where the scene consists of multiple rigid objects moving relative to each other. We examine the case of t...
 
Incremental Kernel SVD for Face Recognition with Image Sets
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Tat-Jun Chin, Konrad Schindler, David Suter
Issue Date:April 2006
pp. 461-466
Non-linear subspaces derived using kernel methods have been found to be superior compared to linear subspaces in modeling or classification tasks of several visual phenomena. Such kernel methods include Kernel PCA, Kernel DA, Kernel SVD and Kernel QR. Sinc...
 
Face Recognition from Video by Matching Image Sets
Found in: Digital Image Computing: Techniques and Applications
By Tat-Jun Chin, James U, Konrad Schindler, David Suter
Issue Date:December 2005
pp. 28
As opposed to still-image based paradigms, video-based face recognition involves identifying a person from a video input. In video-based approaches, face detection and tracking are performed together with recognition, as usually the background is included ...
 
Development of Semi-Automatic Segmentation Methods for Measuring Tibial Cartilage Volume
Found in: Digital Image Computing: Techniques and Applications
By James Cheong, David Suter, Flavia Cicuttini
Issue Date:December 2005
pp. 45
Osteoarthritis is a chronic and crippling disease affecting an increasing number of people each year. With no known cure, it is expected to reach epidemic proportions in the coming years. Currently, there is strong interest in developing a fully automated ...
 
Two-View Multibody Structure-and-Motion with Outliers
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Konrad Schindler, David Suter
Issue Date:June 2005
pp. 676-683
Multi-body structure-and-motion (MSaM) is the problem to establish the multiple-view geometry of several views of a 3D scene taken at different times, where the scene consists of multiple rigid objects moving relative to each other. We examine the case of ...
 
Robust Adaptive-Scale Parametric Model Estimation for Computer Vision
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Hanzi Wang, David Suter
Issue Date:November 2004
pp. 1459-1474
Robust model fitting essentially requires the application of two estimators. The first is an estimator for the values of the model parameters. The second is an estimator for the scale of the noise in the (inlier) data. Indeed, we propose two novel robust t...
 
Recovering the Missing Components in a Large Noisy Low-Rank Matrix: Application to SFM
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Pei Chen, David Suter
Issue Date:August 2004
pp. 1051-1063
<p><b>Abstract</b>—In computer vision, it is common to require operations on matrices with
 
Variable Bandwidth QMDPE and Its Application in Robust Optical Flow Estimation
Found in: Computer Vision, IEEE International Conference on
By Hanzi Wang, David Suter
Issue Date:October 2003
pp. 178
Robust estimators, such as Least Median of Squared (LMedS) Residuals, M-estimators, the Least Trimmed Squares (LTS) etc., have been employed to estimate optical flow from image sequences in recent years. However, these robust estimators have a breakdown po...
 
Robust Model Based Motion Segmentation
Found in: Pattern Recognition, International Conference on
By Alireza Bab-Hadiashar, Niloofar Gheissari, David Suter
Issue Date:August 2002
pp. 20753
This paper presents a new algorithm for the motion segmentation task. The proposed algorithm addresses the important issue of the interconnectivity between data segmentation, model selection and noise scale estimation. The algorithm is tested on motion seg...
 
Application of Rigid Motion Geometry to Film Restoration
Found in: Pattern Recognition, International Conference on
By Samia Boukir, David Suter
Issue Date:August 2002
pp. 10360
Film restoration involves locating the position of artifacts and replacing the
 
Robust Range Segmentation
Found in: Pattern Recognition, International Conference on
By Alireza Bab-Hadiashar, David Suter
Issue Date:August 1998
pp. 969
No summary available.
 
Image Coordinate Transformation Based on DIV-CURL Vector Splines
Found in: Pattern Recognition, International Conference on
By Fang Chen, David Suter
Issue Date:August 1998
pp. 518
No summary available.
 
Using a Fast Multipole Method to Accelerate Spline Evaluations
Found in: Computing in Science and Engineering
By Fang Chen, David Suter
Issue Date:July 1998
pp. 24-31
The authors consider the problem of interpolating scattered data using spline methods, presenting a general framework for using the multipole method to accelerate spline evaluations. The method depends on a tree-data structure and two hierarchical approxim...
 
The Random Cluster Model for Robust Geometric Fitting
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Trung T. Pham,Tat-Jun Chin,Jin Yu,David Suter
Issue Date:August 2014
pp. 1658-1671
Random hypothesis generation is central to robust geometric model fitting in computer vision. The predominant technique is to randomly sample minimal subsets of the data, and hypothesize the geometric models from the selected subsets. While taking minimal ...
 
As-Projective-As-Possible Image Stitching with Moving DLT
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Julio Zaragoza,Tat-Jun Chin,Quoc-Huy Tran,Michael S. Brown,David Suter
Issue Date:July 2014
pp. 1-1
The success of commercial image stitching tools often leads to the impression that image stitching is a “solved problem”. The reality, however, is that many tools give unconvincing results when the input photos violate fairly restrictive imaging assumption...
 
As-Projective-As-Possible Image Stitching with Moving DLT
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Julio Zaragoza,Tat-Jun Chin,Michael S. Brown,David Suter
Issue Date:June 2013
pp. 2339-2346
We investigate projective estimation under model inadequacies, i.e., when the underpinning assumptions of the projective model are not fully satisfied by the data. We focus on the task of image stitching which is customarily solved by estimating a projecti...
 
Conditional Random Field for 3D Point Clouds with Adaptive Data Reduction
Found in: Cyberworlds, International Conference on
By Ee Hui Lim, David Suter
Issue Date:October 2007
pp. 404-408
We proposed using Conditional Random Fields with adaptive data reduction for the classification of 3D point clouds acquired from a Riegl Terrestrial laser scanner. The training and inference of the acquired large outdoor urban data can be time consuming. W...
 
Elastic Spline Models for Human Cardiac Motion Estimation
Found in: Motion of Non-Rigid and Articulated Objects, IEEE Computer Society Workshop on
By Fang Chen, David Suter
Issue Date:July 1997
pp. 0120
Elastic splines (including dynamic ``snakes'' and elastic contours), minimising an energy norm of the membrane and/or thin-plate types, have been used to model many surfaces in visual reconstruction and related biomedical applications. In this paper, we mo...
 
Fast rotation search for real-time interactive point cloud registration
Found in: Proceedings of the 18th meeting of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D '14)
By Álvaro Parra Bustos, David Suter, Michael S. Brown, Tat-Jun Chin
Issue Date:March 2014
pp. 55-62
Our goal is the registration of multiple 3D point clouds obtained from LIDAR scans of underground mines. Such a capability is crucial to the surveying and planning operations in mining. Often, the point clouds only partially overlap and initial alignment i...
     
Recognition of adult images, videos, and web page bags
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By David Suter, Haiqiang Zuo, Haiqiang Zuo, Ou Wu, Ou Wu, Weiming Hu, Weiming Hu, Yunfei Chen, Yunfei Chen, Zhongfei Zhang, Zhongfei Zhang
Issue Date:October 2011
pp. 1-24
In this article, we develop an integrated adult-content recognition system which can detect adult images, adult videos, and adult Web page bags, where a Web page bag consists of a Web page and a predefined number of Web pages linked to it through hyperlink...
     
Color correction for multi-camera system by using correspondences
Found in: ACM SIGGRAPH 2006 Research posters (SIGGRAPH '06)
By David Suter, Kenji Yamamoto, Masayuki Tanimoto, Tomohiro Yendo, Toshiaki Fujii
Issue Date:July 2006
pp. 73-es
Imposters are a powerful technique which has been widely used for many years in the graphics community. An imposter is a two dimensional image rendered onto a billboard which represents highly detailed geometry. Imposters can be created on the fly or pre-c...
     
Color correction for multi-camera system by using correspondences
Found in: Material presented at the ACM SIGGRAPH 2006 conference (SIGGRAPH '06)
By David Suter, Kenji Yamamoto, Masayuki Tanimoto, Tomohiro Yendo, Toshiaki Fujii
Issue Date:July 2006
pp. 73-es
Imposters are a powerful technique which has been widely used for many years in the graphics community. An imposter is a two dimensional image rendered onto a billboard which represents highly detailed geometry. Imposters can be created on the fly or pre-c...
     
 1