Waterfront surveillance and trackability
Machine Vision and Applications
Robust foreground segmentation based on two effective background models
MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
Learning complex background by multi-scale discriminative model
Pattern Recognition Letters
Spatial-temporal nonparametric background subtraction in dynamic scenes
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Real-time object detection and background maintenance for uncontrolled environments
SPPRA '08 Proceedings of the Fifth IASTED International Conference on Signal Processing, Pattern Recognition and Applications
Light-weight salient foreground detection for embedded smart cameras
Computer Vision and Image Understanding
Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking
International Journal of Computer Vision
Automatic body segmentation with graph cut and self-adaptive initialization level set (SAILS)
Journal of Visual Communication and Image Representation
Recovery and Reasoning About Occlusions in 3D Using Few Cameras with Applications to 3D Tracking
International Journal of Computer Vision
Background subtraction framework based on local spatial distributions
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part I
Modeling and segmentation of floating foreground and background in videos
Pattern Recognition
Smooth foreground-background segmentation for video processing
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
An edge-based approach to motion detection
ICCS'06 Proceedings of the 6th international conference on Computational Science - Volume Part I
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Quantitative performance analysis of object detection algorithms on underwater video footage
Proceedings of the 1st ACM international workshop on Multimedia analysis for ecological data
Background subtraction using low rank and group sparsity constraints
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
| Hi-index | 0.00 |
Detecting moving objects using stationary cameras is an important precursor to many activity recognition, object recognition and tracking algorithms. In this paper, three innovations are presented over existing approaches. Firstly, the model of the intensities of image pixels as independently distributed random variables is challenged and it is asserted that useful correlation exists in the intensities of spatially proximal pixels. This correlation is exploited to sustain high levels of detection accuracy in the presence of nominal camera motion and dynamic textures. By using a non-parametric density estimation method over a joint domain-range representation of image pixels, multi-modal spatial uncertainties and complex dependencies between the domain (location) and range (color) are directly modeled. Secondly, temporal persistence is proposed as a detection criteria. Unlike previous approaches to object detection which detect objects by building adaptive models of the only background, the foreground is also modeled to augment the detection of objects (without explicit tracking) since objects detected in a preceding frame contain substantial evidence for detection in a current frame. Third, the background and foreground models are used competitively in a MAP-MRF decision framework, stressing spatial context as a condition of pixel-wise labeling and the posterior function is maximized efficiently using graph cuts. Experimental validation of the proposed method is presented on a diverse set of dynamic scenes.