Complexity Reduction of Neural Network Model for Local Motion Detection in Motion Stereo Vision
Spatial perception, in which objects’ motion and positional relationship are recognized, is necessary for applications such as a walking robot and an autonomous car. One of the demanding features of spatial perception in real world applications is robustness. Neural network-based approaches, in which perception results are obtained by voting among a large number of neuronal activities, seem to be promising. We focused on a neural network model for motion stereo vision proposed by Kawakami et al. In this model, local motion in each small region of the visual field, which comprises optical flow, is detected by hierarchical neural network. Implementation of this model into a VLSI is required for real-time operation with low power consumption. In this study, we reduced the computational complexity of this model and showed cell responses of the reduced model by numerical simulation.
KeywordsMotion stereo vision Local motion detection Hough transform VLSI
This work was partly supported by JSPS KAKENHI Grant Number 15K18044. We would like to thank Editage (www.editage.jp) for English language editting.
- 2.Gibson, J.J.: The Perception of the Visual World. Houghton Mifflin, Boston (1950)Google Scholar
- 7.Hough, P.V.C.: Method and means for recognizing complex patterns. U.S. Patent 3069654 (1962)Google Scholar
- 8.Reichart, W.: Autocorrelation. A Principle for the Evaluation of Sensory Information by the Central Nervous System. Sensory Communication, pp. 303–317. Wiley, New York (1961)Google Scholar
- 9.Kawakami, S., Morita, T., Okamoto, H., Hasegawa, F., Yasukawa, Y., Inamoto, Y.: A model for intracortical connections of hypercolumn. V. One dimensional filterings and Gabor functions. IEICE Technical report, NC 92, pp. 9–16 (1992)Google Scholar
- 10.Kawakami, S., Okamoto, H.: A neuronal circuit model for multiplication-like function performed by a combination of three synapse types. IEICE Technical report, NC 95, pp. 47–54 (1995)Google Scholar