Bayesian Pixel Classification for Human Tracking
WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Bayesian Modeling of Dynamic Scenes for Object Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
On-Road Vehicle Detection: A Review
IEEE Transactions on Pattern Analysis and Machine Intelligence
A General Framework for Combining Visual Trackers --- The "Black Boxes" Approach
International Journal of Computer Vision
Robust Tracking Using Foreground-Background Texture Discrimination
International Journal of Computer Vision
ACM Computing Surveys (CSUR)
Tracking People by Learning Their Appearance
IEEE Transactions on Pattern Analysis and Machine Intelligence
Spatio-Temporal Context for Robust Multitarget Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
Nonparametric background generation
Journal of Visual Communication and Image Representation
Robust Object Tracking Via Online Dynamic Spatial Bias Appearance Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking with Dynamic Hidden-State Shape Models
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Image description with features that summarize
Computer Vision and Image Understanding
Graph-based transductive learning for robust visual tracking
Pattern Recognition
Tracking nonstationary visual appearances by data-driven adaptation
IEEE Transactions on Image Processing
Automatic Detection of Object of Interest and Tracking in Active Video
PCM '09 Proceedings of the 10th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Image trimming via saliency region detection and iterative feature matching
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Collaboration of spatial and feature attention for visual tracking
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
A noise-insensitive object tracking algorithm
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Increasing classification robustness with adaptive features
ICVS'08 Proceedings of the 6th international conference on Computer vision systems
LDA based color information fusion for visual objects tracking
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Online visual tracking with histograms and articulating blocks
Computer Vision and Image Understanding
Assessment of the influence of adaptive components in trainable surface inspection systems
Machine Vision and Applications - Integrated Imaging and Vision Techniques for Industrial Inspection
Discriminative spatial attention for robust tracking
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Human tracking using convolutional neural networks
IEEE Transactions on Neural Networks
A probabilistic framework for combining tracking algorithms
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Discriminative tracking by metric learning
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Visual object tracking via sparse reconstruction
ICIMCS '10 Proceedings of the Second International Conference on Internet Multimedia Computing and Service
Background subtraction for automated multisensor surveillance: a comprehensive review
EURASIP Journal on Advances in Signal Processing - Special issue on advanced image processing for defense and security applications
Neural network based online feature selection for vehicle tracking
ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Automatic Detection of Object of Interest and Tracking in Active Video
Journal of Signal Processing Systems
Object tracking using discriminative feature selection
ACIVS'06 Proceedings of the 8th international conference on Advanced Concepts For Intelligent Vision Systems
Attractor-Guided particle filtering for lip contour tracking
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Online selection of discriminative features using bayes error rate for visual tracking
PCM'06 Proceedings of the 7th Pacific Rim conference on Advances in Multimedia Information Processing
Adaptive sparse vector tracking via online bayesian learning
IWICPAS'06 Proceedings of the 2006 Advances in Machine Vision, Image Processing, and Pattern Analysis international conference on Intelligent Computing in Pattern Analysis/Synthesis
Visual saliency based object tracking
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Fast Human Pose Detection Using Randomized Hierarchical Cascades of Rejectors
International Journal of Computer Vision
Fast and adaptive deep fusion learning for detecting visual objects
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Robust Visual Tracking via Structured Multi-Task Sparse Learning
International Journal of Computer Vision
Robust visual tracking with discriminative sparse learning
Pattern Recognition
Dynamic objectness for adaptive tracking
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Visual tracking in continuous appearance space via sparse coding
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Tracking in dense crowds using prominence and neighborhood motion concurrence
Image and Vision Computing
| Hi-index | 0.00 |
This paper presents a method for evaluating multiple feature spaceswhile tracking, and for adjusting the set of features used toimprove tracking performance. Our hypothesisis that the featuresthat best discriminate between object and background are also bestfor tracking the object. We develop an on-line feature selectionmechanism based on the two-class variance ratio measure, applied tolog likelihood distributions computed with respect to a givenfeature from samples of object and background pixels. This featureselection mechanism is embedded in a tracking system thatadaptively selects the top-ranked discriminative features fortracking. Examples are presented to illustrate how the methodadapts to changing appearances of both tracked object and scenebackground.