CNNによる面積階調ダイナミクス 両眼視差の為のブロックマッチング

Translated title of the contribution: Area Gradation Dynamics by Cellular Neural Networks. Block Matching for Stereo Vision.

服部泰造, Kenya JINNO, 田中衛

Research output: Contribution to journalMisc

Abstract

The CNN (cellular neural network) that consists of locally connected neurons realizes the silicon retina. This paper describes CNN state equations to perform dynamic depth extraction for binocular stereo vision. The transmitter compress stereo images by constructure and area gradation quantization. Then the receiver reconstruct stereo images, and extracting parallax. The correspondence problem between left and right images is solved by block matching process of depth extraction system.
Translated title of the contributionArea Gradation Dynamics by Cellular Neural Networks. Block Matching for Stereo Vision.
Original languageJapanese
Pages (from-to)41 - 48
Journal電子情報通信学会技術研究報告
Volume96
Issue number94(NLP96 34-45)
StatePublished - 14 Jun 1996

Fingerprint

Dive into the research topics of 'Area Gradation Dynamics by Cellular Neural Networks. Block Matching for Stereo Vision.'. Together they form a unique fingerprint.

Cite this