Name
Abstract | ||
|---|---|---|
An original approach to the motion analysis, based on the novelty filter, is proposed. T h e novelty filter stresses the novelties occurring in a pattern representing an image of the scene under consideration with respect to patterns representing previous images of the same scene, so that visual information about the motion of the objects is obtained. The novelty filter may b e implemented by a neural network architecture, taking advantage of the capabilities o f massive parallelism, adaptive learning and noise robustness. The novelty filter may learn the entire trajectory of an object, through an incremental learning of a sequence of images capturing the scene, thus emphasizing if the position of the object in an image belongs to t h e learned trajectory. If the position of the object does not belong to the trajectory, the network gives information on the shift from the trajectory. |
Year | DOI | Venue |
|---|---|---|
1991 | 10.1016/0167-8655(91)90047-P | Pattern Recognition Letters |
Keywords | Field | DocType |
motion analysis,novelty filter.,novelty filter,neural network,adaptive learning | Computer vision,Pattern recognition,Computer science,Filter (signal processing),Image processing,Robustness (computer science),Artificial intelligence,Novelty,Motion analysis,Artificial neural network,Adaptive learning,Trajectory | Journal |
Volume | Issue | ISSN |
12 | 3 | Pattern Recognition Letters |
Citations | PageRank | References |
1 | 0.41 | 2 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| E. Ardizzone | 1 | 158 | 22.06 |
| A. Chella | 2 | 216 | 15.99 |
| S. Gaglio | 3 | 246 | 21.47 |
| F. Sorbello | 4 | 112 | 13.73 |