Recognizing 2-tone images in grey-level parametric eigenspaces
Pattern Recognition Letters
Indexing for local appearance-based recognition of planar objects
Pattern Recognition Letters
A Robust PCA Algorithm for Building Representations from Panoramic Images
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Recognizing Objects by Their Appearance Using Eigenimages
SOFSEM '00 Proceedings of the 27th Conference on Current Trends in Theory and Practice of Informatics
Robust Recognition of Scaled Eigenimages through a Hierarchical Approach
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Contour-based partial object recognition using symmetry in image databases
Proceedings of the 2005 ACM symposium on Applied computing
Weighted and robust learning of subspace representations
Pattern Recognition
Incremental and robust learning of subspace representations
Image and Vision Computing
SCIA '09 Proceedings of the 16th Scandinavian Conference on Image Analysis
On-Line, incremental learning of a robust active shape model
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
A view-based 3D object shape representation technique
ICIAR'07 Proceedings of the 4th international conference on Image Analysis and Recognition
| Hi-index | 0.00 |
We describe a hierarchical appearance-based method for learning, recognizing, and predicting arbitrary spatiotemporal sequences of images. The method, which implements a robust hierarchical form of the Kalman filter derived from the Minimum Description Length (MDL) principle, includes as a special case several well-known object encoding techniques including eigenspace methods for static recognition. Successive levels of the hierarchical filter implement dynamic models operating over successively larger spatial and temporal scales. Each hierarchical level predicts the recognition state at a lower level and modifies its own recognition state using the residual error between the prediction and the actual lower-level state. Simultaneously, on a longer time scale, the filter learns an internal model of input dynamics by adapting its generative and state transition matrices at each level to minimize prediction errors. The resulting prediction/learning scheme thereby implements an on-line form of the well-known Expectation-Maximization (EM) algorithm from statistics. We present experimental results demonstrating the method's efficacy in mediating robust spatiotemporal recognition in a variety of scenarios containing varying degrees of occlusions and clutter.