Robust Techniques for Visual Surveillance
Explore this paper's citation graph
Summary
The work described here aims at improving the performance of three building blocks of visual surveillance systems: foreground detection, object tracking and event detection, and addressing the problem of visual event recognition in surveillance where noise and missing observations are serious problems.
- Published
- 2008-01-01
- Cited by
- 0
- References
- 87
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:38290631
References
- PYRAMID METHODS IN IMAGE PROCESSING.
- Recursive Random Fields
- Memory-Efficient Inference in Relational Domains
- Activity Recognition from Video Sequences using Declarative Models
- Silhouette and stereo fusion for 3D object modeling
- A Probabilistic Exclusion Principle for Tracking Multiple Objects
- Recognizing human action in time-sequential images using hidden Markov model
- Multi-feature hierarchical template matching using distance transforms
- Markov logic networks
- A Comparison of Affine Region Detectors
- Simulated tempering: a new Monte Carlo scheme
- Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions
- The template update problem
- Methods for Volumetric Reconstruction of Visual Scenes
- Adaptive 3-D Object Recognition from Multiple Views
- Sequential Monte Carlo Methods in Practice
- On-line selection of discriminative tracking features
- Rapid octree construction from image sequences
- Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
- A Surface Reconstruction Method Using Global Graph Cut Optimization
Cited by
No citing papers recorded for this paper.
Related papers
No related papers recorded.