Monte Carlo methods. Vol. 1: basics
Monte Carlo methods. Vol. 1: basics
Learning control strategies for object recognition
Symbolic visual learning
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognition without Correspondence using MultidimensionalReceptive Field Histograms
International Journal of Computer Vision
Example-Based Object Detection in Images by Components
IEEE Transactions on Pattern Analysis and Machine Intelligence
Semantic Annotation of Sports Videos
IEEE MultiMedia
Perceptual Components for Context Aware Computing
UbiComp '02 Proceedings of the 4th international conference on Ubiquitous Computing
Combining greyvalue invariants with local constraints for object recognition
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Learning Temporal Context in Active Object Recognition Using Bayesian Analysis
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Brand identification using Gaussian derivative histograms
ICVS'03 Proceedings of the 3rd international conference on Computer vision systems
Context based object detection from video
ICVS'03 Proceedings of the 3rd international conference on Computer vision systems
A probabilistic framework for semantic video indexing, filtering,and retrieval
IEEE Transactions on Multimedia
| Hi-index | 0.00 |
This work discriminates external and internal visual context according to a recently determined terminology in computer vision. It is conceptually based on psychological findings in human perception that stress the utility of visual context in object detection processes. The paper outlines a machine vision detection system that analyzes external context and thereby gains prospective information from rapid scene analysis in order to focus attention on promising object locations. A probabilistic framework is defined to predict the occurrence of object detection events in video in order to significantly reduce the computational complexity involved in extensive object search. Internal context is processed using an innovative method to identify the object's topology from local object features. The rationale behind this methodology is the development of a generic cognitive detection system that aims at more robust, rapid and accurate event detection from streaming video. Performance implications are analyzed with reference to the application of logo detection in sport broadcasts and provide evidence for the crucial improvements achieved from the usage of visual context information.