A Theory for Memory-Based Learning
Machine Learning - Special issue on computational learning theory, COLT'92
Learning Patterns of Activity Using Real-Time Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Effective Gaussian Mixture Learning for Video Background Subtraction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer Animation and Virtual Worlds
ACM Computing Surveys (CSUR)
Formal Description of the Cognitive Process of Memorization
Transactions on Computational Science V
Modelling Human Memory in Robotic Companions for Personalisation and Long-term Adaptation in HRI
Proceedings of the 2010 conference on Biologically Inspired Cognitive Architectures 2010: Proceedings of the First Annual Meeting of the BICA Society
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking
IEEE Transactions on Signal Processing
A flexible edge matching technique for object detection in dynamic environment
Applied Intelligence
Cognitive informatics models of the brain
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
On the cognitive process of human problem solving
Cognitive Systems Research
A target-based color space for sea target detection
Applied Intelligence
Visual tracking and recognition using appearance-adaptive models in particle filters
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
Inspired by the way humans perceive the environment, in this paper, we propose a memory-based cognitive model for visual information processing which can imitate some cognitive functions of the human brain such as remembering, recall, forgetting, learning, classification, and recognition, etc. The proposed model includes five components: information granule, memory spaces, cognitive behaviors, rules for manipulating information among memory spaces, and decision-making processes. Three memory spaces are defined for separately storing the current, temporal and permanent information acquired, i.e. ultra short-term memory space (USTMS), short-term memory space (STMS) and long-term memory space (LTMS). The proposed memory-based model can remember or forget what the scene has ever been which helps the model adapt to the variation of the scene more quickly. We apply the model to address two hot issues in computer vision: background modeling and object tracking. A聽memory-based Gaussian mixture model (MGMM) for object segmentation and a memory-based template updating (MTU) model for object tracking with particle filter (PF) are exhibited respectively. Experimental results show that the proposed model can deal with scenes with sudden background and foreground changes more robustly when segmenting and tracking moving objects under complex background.