iccv 2009 论文列表12th IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2009, Kyoto, Japan, September 27 - October 4, 2009. |
A novel non-central catadioptric auto-calibration approach.
Generalized stereo for hybrid omnidirectional and perspective imaging.
Image reconstruction in the gigavision camera.
Krill-eye : Superposition compound eye for wide-angle imaging via GRIN lenses.
Experiments in place recognition using gist panoramas.
From Google Street View to 3D city models.
Building consistent local submaps with omnidirectional SLAM.
Face tracking by using omnidirectional sensor network.
Self-calibration of asynchronized camera networks.
'Featuring' Optical Rails: View-based robot guidance using orientation features on the sphere.
Direct approach to the self-calibration of omnidirectional cameras.
Projection through quadric mirrors made faster.
Compressed representation of feature vectors using a Bloomier filter and its application to specific object recognition.
Robust and efficient recognition of low-quality images by cascaded recognizers with massive local features.
Scaling object recognition: Benchmark of current state of the art techniques.
Better matching with fewer features: The selection of useful features in large database recognition problems.
Approximate nearest neighbor search on HDD.
Error-correcting semi-supervised learning with mode-filter on graphs.
Discriminative structured outputs prediction model and its efficient online learning algorithm.
Spectral camera clustering.
BUBL: An effective region labeling tool using a hexagonal lattice.
Applying incremental learning to parallel image segmentation.
Real-time motion control using pose space probability density estimation.
Shoulder gesture interface for operating electric wheelchair.
Tracking humans interacting with the environment using efficient hierarchical sampling and layered observation models.
Is gender recognition affected by age?
Object recognition in service robots: Conducting verbal interaction on color and spatial relationship.
The use of tongue protrusion gestures for video-based communication.
Learning to rank images from eye movements.
Automatic sign segmentation from continuous signing via multiple sequence alignment.
Automatic detection of facial actions from 3D data.
Feature selection of facial displays for detection of non verbal communication in natural conversation.
Incorporating facial features into a multi-channel gesture recognition system for the interpretation of Irish Sign Language sequences.
Diamond color grading based on machine vision.
Pixel-based correspondence and shape reconstruction for moving objects.
Reducing integrability artefacts for data fusion through colour space manipulation.
Single image focus editing.
A common framework for ambient illumination in the dichromatic reflectance model.
Lightness recovery for pictorial surfaces.
An invariant metric on the manifold of second order moments.
Temporal reflectance changes in vegetables.
Multispectral imaging for material analysis in an outdoor environment using Normalized Cuts.
Color from black-and-white surveillance cameras.
Perceptually motivated automatic color contrast enhancement.
Color harmony for image indexing.
Compact local color descriptor based on rank correlations.
Disparity map refinement and 3D surface smoothing via Directed Anisotropic Diffusion.
Fast computation of 3D spherical Fourier harmonic descriptors - a complete orthonormal basis for a rotational invariant representation of three-dimensional objects.
Sampled medial loci and boundary differential geometry.
Large-scale urban environment modeling from videos using image content segmentation and alignment.
Robust 3D street-view reconstruction using sky motion estimation.
Shade Face: Multiple image-based 3D face recognition.
Tracking human joint motion for turntable-based static model reconstruction.
Optimal consensus set for digital plane fitting.
Virtual 3D bone fracture reconstruction via inter-fragmentary surface alignment.
Region extraction in large-scale urban LIDAR data.
A compact representation for scanned 3D objects.
One-shot scanning using De Bruijn spaced grids.
Markerless reconstruction of dynamic facial expressions.
An efficient data-driven tissue deformation model.
A locally global approach to stereo correspondence.
Mobile phone-based 3D modeling framework for instant interaction.
Improving photometric stereo with laser sectioning.
Real-time free viewpoint video from uncalibrated cameras using plane-sweep algorithm.
On-line 3-D inspection of deformable parts using FEM trained radial basis functions.
Local PotentialWell Space Embedding.
Creating compact architectural models by geo-registering image collections.
Automation of 3D view acquisition for geometric tolerances verification.
Monocular structure from motion for near to long ranges.
Context-Consistent stereo matching.
Tackling the coplanarity problem in 3D camera calibration by means of fuzzy landmarks: a performance study in forensic craniofacial superimposition.
A probabilistic approach to camera pose and calibration from a small set of point and line correspondences.
Fast 3D surface reconstruction by unambiguous compound phase coding.
Complex 3D shape recovery using hybrid geometric shape features in a hierarchical shape segmentation approach.
Robust range image registration using local distribution of albedo.
Spatio-temporal image-based texture atlases for dynamic 3-D models.
Online segmentation of free-viewpoint video.
In-hand scanning with online loop closure.
Plenoptic depth estimation from multiple aliased views.
Robust multi-view stereo without matching.
Self-correction of 3D reconstruction from multi-view stereo images.
Hierarchical shape-based surface reconstruction for dense multi-view stereo.
Freeform shape clustering for customized design automation.
Alexander Zouhar Sajjad Baloch Sergei Azernikov Claus Bahlmann Gözde B. Ünal Tong Fang Siegfried Fuchs
A minimum cover approach for extracting the road network from airborne LIDAR data.
Posture invariant correspondence of triangular meshes in shape space.
Color matching and illumination estimation for urban scenes.
Elastic convolved ICP for the registration of deformable objects.
Shape from depth discontinuities under orthographic projection.
Multi-view image and ToF sensor fusion for dense 3D reconstruction.
Environment modelling using spherical stereo imaging.
Scalable multi-view stereo.
Real-time photo-realistic visualization of 3D environments for enhanced tele-operation of vehicles.
Shape-Colour Histograms for matching 3D video sequences.
3D-color video camera.
Automatic bootstrapping of a morphable face model using multiple components.
Structure-and-motion pipeline on a hierarchical cluster tree.
Consistency and confidence: A dual metric for verifying 3D object detections in multiple LiDAR scans.
Measuring 3D shape similarity by matching the medial scaffolds.
Iterative mesh deformation for dense surface tracking.
Fully automatic calibration of LIDAR and video streams from a vehicle.
A high speed iterative closest point tracker on an FPGA platform.
LiDAR inpainting from a single image.
Training many-parameter shape-from-shading models using a surface database.
Learning shape priors for single view reconstruction.
Online learning of robust object detectors during unstable tracking.
Beyond semi-supervised tracking: Tracking should be as simple as detection, but not simpler than recognition.
Combining online and offline learning for tracking a talking face in video.
On-line Random Forests.
Online learning of robust facial feature trackers.
Generalized Query by Transduction for online active learning.
Inter-active learning of randomized tree ensembles for object detection.
On robustness of on-line boosting - a competitive study.
Online coordinate boosting.
A family of online boosting algorithms.
Topic models for scene analysis and abnormality detection.
On-the-fly global activity prediction and anomaly detection.
Simultaneous video synchronization and rare event detection via Cross-Entropy Monte Carlo optimization.
Automatic configuration of spectral dimensionality reduction methods for 3D human pose estimation.
Cell-based object tracking method for 3D shape reconstruction using multi-viewpoint active cameras.
People detection and tracking using the Explorative Particle Filtering.
Accurate fusion of robot, camera and wireless sensors for surveillance applications.
What are they doing? : Collective activity classification using spatio-temporal relationship among people.
Using location and motion statistics for the localization of moving objects in multiple camera surveillance videos.
A portable geo-aware visual surveillance system for vehicles.
A simplified error model for height estimation using a single camera.
Multitarget tracking with a corner-based particle filter.
Hunting Nessie - Real-time abnormality detection from webcams.
Full body image feature representations for gender profiling.
Modelling pedestrian trajectory patterns with Gaussian processes.
Active background modeling: Actors on a stage.
Combining low-level segmentation with relational classification.
A particle swarm optimization approach for multi-objects tracking in crowded scene.
Accurate camera calibration using iterative refinement of control points.
Active Shape Model and linear predictors for face association refinement.
Human segmentation by fusing visible-light and thermal imaginary.
Multi-class multi-instance boosting for part-based human detection.
Object detection by joint features based on two-stage boosting.
Efficient tracking of many objects in structured environments.
Pyramidal Statistics of Oriented Filtering for robust pedestrian detection.
Spatio-temporal nonparametric background modeling and subtraction.
A Simple and efficient saliency detector for background subtraction.
Detection and tracking of objects with direct integration of perception and expectation.
Scale invariant 3D multi-person tracking using a base set of bundle adjusted visual landmarks.
Tracker trees for unusual event detection.
Multi-object tracking via species based particle swarm optimization.
Boosting Associated Pairing Comparison Features for pedestrian detection.
The TUM Kitchen Data Set of everyday manipulation activities for motion tracking and action recognition.
Trajectory based Primitive Events for learning and recognizing activity.
Continuous recognition of motion based gestures in sign language.
Summarised hierarchical Markov models for speed-invariant action matching.
Multiple views gait recognition using View Transformation Model based on optimized Gait Energy Image.
Monocular 3D human pose estimation using sparse motion features.
3D model-based marker-less human motion tracking in cluttered environment.
Modeling the product manifold of posture and motion.
A framework for Human tracking using Kalman filter and fast mean shift algorithms.
Tracking of humans and estimation of body/head orientation from top-view single camera for visual focus of attention analysis.
A regression-based approach to recover human pose from voxel data.
User-centric speaker report: Ranking-based effectiveness evaluation and feedback.
3D Body-part tracking of two persons using a hierarchical body model.
Retrieving ancient Maya glyphs with Shape Context.
Enhancing color texture quality of 3D models for digital preservation of indigenous ceramic artworks.
Automatically identifying join candidates in the Cairo Genizah.
A lightness recovery algorithm for the multispectral acquisition of frescoed environments.
Weave pattern modeling of silk-like fabrics from multi-illuminated HDR image analysis.
Unsupervised ink type recognition in ancient manuscripts.
Capturing village-level heritages with a hand-held camera-laser fusion sensor.
Image guided reconstruction of un-sampled data: a coherent filling for uncomplete Cultural Heritage models.
Image-based network rendering system for large sized meshes.
Method of 3D reconstruction using graph cuts, and its application to preserving intangible cultural heritage.
Prominent field for shape processing of archaeological artifacts.
3D line drawing for archaeological illustration.
Parallel implementation of pedestrian tracking using multiple cues on GPGPU.
Hardware architecture for high-accuracy real-time pedestrian detection with CoHOG features.
Realtime affine-photometric KLT feature tracker on GPU in CUDA framework.
An FPGA-based stream processor for embedded real-time vision with Convolutional Networks.
GPU-based non-parametric background subtraction for a practical surveillance system.
Parallel algorithms to a parallel hardware: Designing vision algorithms for a GPU.
Fast image segmentation and texture feature extraction for image retrieval.
Towards complex visual surveillance algorithms on smart cameras.
A self-calibration method for smart video cameras.
Flexible clustering in networks of smart cameras.
MCMC-based feature-guided particle filtering for tracking moving objects from a moving platform.
Efficient systolic architecture and power modeling for finite ridgelet transform.
Probabilistic model of error in fixed-point arithmetic Gaussian pyramid.
Efficient keypoint matching for robot vision using GPUs.
Geodesic tree-based dynamic programming for fast stereo reconstruction.
Real-time accurate stereo with bitwise fast voting on CUDA.
A very fast census-based stereo matching implementation on a graphics processing unit.
An embedded AER dynamic vision sensor for low-latency pole balancing.
RACKET: Real-time autonomous computation of kinematic elements in tennis.
Kernel Spectral Curvature Clustering (KSCC).
Motion segmentation by SCC on the hopkins 155 database.
Provably convergent on-line structure and motion estimation for perspective systems.
A vision-based approach for high accuracy assessment of satellite attitude.
An iterative scheme for motion-based scene segmentation.
Motion segmentation with occlusions on the superpixel graph.
Combining spatial and temporal priors for articulated human tracking with online learning.
A stochastic dynamical system for optical flow estimation.
2.5D Elastic Graph Matching algorithms.
Scale and orientation invariant 3D interest point extraction using HK curvatures.
Intrinsic shape signatures: A shape descriptor for 3D object recognition.
Image composition for object pop-out.
3D pose estimation for planes.
Semantic classification by covariance descriptors within a randomized forest.
Road scene labeling using SfM module and 3D bag of textons.
Shading cues for object class detection.
Active view selection for object and pose recognition.
(Multiscale) Local Phase Quantisation histogram discriminant analysis with score normalisation for robust face recognition.
Semantic segmentation of street scenes by superpixel co-occurrence and 3D geometry.
Feature-Cut: Video object segmentation through local feature correspondences.
Transfer pedestrian detector towards view-adaptiveness and efficiency.
Quantitative comparison of metrics for change detection in video patrolling applications.
Acquiring 3D motion trajectories of large numbers of swarming animals.
Workflow monitoring based on 3D motion features.
Automatic identification of fusion events in TIRF microscopy image sequences.
Katarina Mele Adelle Coster James G. Burchfield Jamie Lopez David E. James William E. Hughes Pascal Vallotton
Video-based raindrop detection for improved image registration.
ICA mixture hidden conditional random field model for sports event classification.
Event detection and semantic identification using Bayesian belief network.
Efficient human action recognition by cascaded linear classifcation.
Boosted Exemplar Learning for human action recognition.
Action recognition using Randomised Ferns.
Human action detection by boosting efficient motion features.
Trajectons: Action recognition through the motion analysis of tracked features.
Effective Codebooks for human action categorization.
Action exemplar based real-time action detection.
Evaluation of threshold model HMMS and Conditional Random Fields for recognition of spatiotemporal gestures in sign language.
Human action recognition from a single clip per action.
Supervised Neighborhood Topology Learning for Human Action Recognition.
Randomized algorithm of spectral clustering and image/video segmentation using a minority of pixels.
An improved local descriptor and threshold learning for unsupervised dynamic texture segmentation.
H-APF: Using hierarchical representation of human body for 3-D articulated tracking and action classification.
Learning mixed-state Markov models for statistical motion texture tracking.
Sparse learning approach to the problem of robust estimation of camera locations.
On-line learning of the transition model for Recursive Bayesian Estimation.
Fitting parametric road models to spatio-temporal derivatives.
Two-layer generative models for estimating unknown gait kinematics.
Combining discriminative appearance and segmentation cues for articulated human pose estimation.
A phase field higher-order active contour model of directed networks.
Joint estimation of deformable motion and photometric parameters in single view video.
Bending invariant meshes and application to groupwise correspondences.
Effective and efficient interpolation for mutual information based multimodality elastic image registration.
Online Active Feature Model for lip tracking.
Integrating contour and skeleton for shape classification.
Uncalibrated non-rigid factorisation with automatic shape basis selection.
Learning varying dimension radial basis functions for deformable image alignment.
Unsupervised learning of human body parts from video footage.
Learning shape metrics based on deformations and transport.
Shape Google: a computer vision approach to isometry invariant shape retrieval.
Non-rigid registration between color channels based on joint-histogram entropy in subspace.
Fast nonrigid mesh registration with a data-driven deformation prior.
Markov Chain Monte Carlo shape sampling using level sets.
Probabilistic constrained adaptive local displacement experts.
Detailed body shapes from flash photographs.
On reconstruction of non-rigid shapes with intrinsic regularization.
Efficient retrieval of deformable shape classes using local self-similarities.
Spectral Gromov-Wasserstein distances for shape matching.
Curve fitting by Spherical Least Squares on two-dimensional sphere.
Optimization on the manifold of multiple homographies.
Median K-Flats for hybrid linear modeling with many outliers.
Head pose estimation using multilinear subspace analysis for robot human awareness.
Synthesis of multiple pose facial images using tensor-based subspace learning method.
Multilinear Isometric Embedding for visual pattern analysis.
Learning good features for Active Shape Models.
Optimal feature selection for subspace image matching.
3D-MAM: 3D morphable appearance model for efficient fine head pose estimation from still images.
Spectral face clustering.
Visual category recognition using Spectral Regression and Kernel Discriminant Analysis.
Multiple pattern classification by sparse subspace decomposition.
Subset kernel PCA for pattern recognition.
Non-linear generative embeddings for kernels on latent variable models.
Stepwise Correlation metric based Discriminant Analysis and multi-probe images fusion for face recognition.
Robust faces manifold modeling: Most expressive Vs. most Sparse criterion.
Investigating the spatial support of signal and noise in face recognition.
Identity and Variation Spaces: Revisiting the Fisher Linear Discriminant.
A strategy of classification via sparse dictionary learned by non-negative K-SVD.
A general framework for Approximate Nearest Subspace search.
Large margin classifiers based on convex class models.
Mahalanobis distance Minimization Mapping: M3.
Learning invariances with Stationary Subspace Analysis.
Nonnegative Matrix Factorization with Gibbs Random Field modeling.
A similarity measure for 3D rigid registration of point clouds using image-based descriptors with low overlap.
Scale-weighted dense bag of visual features for 3D model retrieval from a partial view 3D model.
Valence Normalized Spatial Median for skeletonization and matching.
Detecting and segmenting objects for mobile manipulation.
Min-cut based segmentation of point clouds.
Pedestrian detection with depth-guided structure labeling.
Geolocalization using skylines from omni-images.
3D human pose search using oriented cylinders.
Discriminative 3D human pose estimation from monocular images via topological preserving hierarchical affinity clustering.
3D action matching with key-pose detection.