Abstract | ||
---|---|---|
Perception of visual motion is thought to consist of two stages: generation of candidates and their interaction to determine true motion. In this paper, a three-layered neural network is applied to detect local visual motion. The network, after learning, could categorize nine types of motion and obtained a motion detection algorithm that included the two states of perception. The internal representations for the first stage agree with the functions of on-center and off-center cells, and those for the second stage agree with the functions of lateral inhibition. We also tried to detect arbitrary motions by combining multi-resolution representation of images with the neural network. |
Year | DOI | Venue |
---|---|---|
1994 | 10.1002/scj.4690251103 | SYSTEMS AND COMPUTERS IN JAPAN |
Keywords | Field | DocType |
MOTION DETECTION,NEURAL NETWORK,SUCCESSIVE IMAGE ANALYSIS | Structure from motion,Computer vision,Categorization,Motion detection,Computer science,Lateral inhibition,Artificial intelligence,Motion estimation,Artificial neural network,Perception,Visual perception | Journal |
Volume | Issue | ISSN |
25 | 11 | 0882-1666 |
Citations | PageRank | References |
1 | 0.43 | 1 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Eiji Atsumi | 1 | 1 | 0.43 |
Mikio Takagi | 2 | 221 | 198.87 |
Kazuhiko Yokosawa | 3 | 10 | 10.87 |