Elements of information theory
Elements of information theory
Combining labeled and unlabeled data with co-training
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Learning Patterns of Activity Using Real-Time Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Tracking and Object Classification for Automated Surveillance
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Pedestrian Detection Using Wavelet Templates
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Moving Target Classification and Tracking from Real-time Video
WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Fast Vehicle Detection with Probabilistic Feature Grouping and its Application to Vehicle Tracking
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Unsupervised Improvement of Visual Detectors using Co-Training
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Minimally-Supervised Classification using Multiple Observation Sets
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Detecting Pedestrians Using Patterns of Motion and Appearance
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Pre-Attentive and Attentive Detection of Humans in Wide-Field Scenes
International Journal of Computer Vision
Robotic eye-to-hand coordination: Implementing visual perception to object manipulation
International Journal of Hybrid Intelligent Systems - Recent developments in Hybrid Intelligent Systems
Patch-based experiments with object classification in video surveillance
ACIVS'07 Proceedings of the 9th international conference on Advanced concepts for intelligent vision systems
Genetic algorithms for automatic classification of moving objects
Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
Automatic learning of background semantics in generic surveilled scenes
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Geometric constraints for human detection in aerial imagery
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Multiclass object classification for real-time video surveillance systems
Pattern Recognition Letters
Genetic algorithms for automatic object movement classification
ICHIT'11 Proceedings of the 5th international conference on Convergence and hybrid information technology
Learning semantic scene models by trajectory analysis
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Shadow Casting Out Of Plane (SCOOP) Candidates for Human and Vehicle Detection in Aerial Imagery
International Journal of Computer Vision
| Hi-index | 0.00 |
Object classification in far-field video sequences is a challenging problem because of low resolution imagery and projective image distortion. Most existing far-field classification systems are trained to work well in a constrained set of scenes, but can fail dramatically when applied to new scenes, or even different views of the same scene. We identify discriminative object features for classifying vehicles and pedestrians and develop a scene-invariant classification system that is trained on a small number of labelled examples from a few scenes, but transfers well to a wide range of new scenes. Simultaneously, we demonstrate that use of scene-specific context features (such as image position and direction of motion of objects) can greatly improve classification in any given scene. To combine these ideas, we propose a new algorithm for adapting a scene-invariant classifier to scene-specific features by retraining with the help of unlabelled data in a novel scene. Experimental results demonstrate the effectiveness of our context features and scene-transfer/adaptation algorithm for multiple urban and highway scenes.