A Texture-Based Method for Modeling the Background and Detecting Moving Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Video object tracking using adaptive Kalman filter
Journal of Visual Communication and Image Representation
Efficient hierarchical method for background subtraction
Pattern Recognition
Background Subtraction Based on Local Orientation Histogram
APCHI '08 Proceedings of the 8th Asia-Pacific conference on Computer-Human Interaction
Vision Based Pose Recognition in Video Game
Edutainment '08 Proceedings of the 3rd international conference on Technologies for E-Learning and Digital Entertainment
Difference of Gaussian Edge-Texture Based Background Modeling for Dynamic Traffic Conditions
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing
Multl-resolution background subtraction for dynamic scenes
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Local histogram of figure/ground segmentations for dynamic background subtraction
EURASIP Journal on Advances in Signal Processing
TED: A texture-edge descriptor for pedestrian detection in video sequences
Pattern Recognition
Fusing color and texture features for background model
FSKD'06 Proceedings of the Third international conference on Fuzzy Systems and Knowledge Discovery
Background subtraction based on phase feature and distance transform
Pattern Recognition Letters
Robust detection of moving objects in video sequences through rough set theory framework
Image and Vision Computing
Real-time background modeling based on a multi-level texture description
Information Sciences: an International Journal
Hi-index | 0.00 |
Two methods of detecting and tracking objects in colorvideo are presented. Color and edge histograms are exploredas ways to model the background and foreground ofa scene. The two types of methods are evaluated to determinetheir speed, accuracy and robustness. Histogram comparisontechniques are used to compute similarity valuesthat aid in identifying regions of interest. Foreground objectsare detected and tracked by dividing each video frameinto smaller regions (cells) and comparing the histogram ofeach cell to the background model. Results are presentedfor video sequences of human activity.