Stereo Matching Using Synchronous Hopfield Neural Network

運用同步式霍普菲爾類神經網路求解雙影像對應問題

孫德修(Te-Hsiu Sun)

《工業工程學刊》 26卷4期 (2009/07) Pp. 276-288

https://doi.org/10.29977/JCIIE.200907.0005

摘要

深度資訊之取得為電腦視覺研究領域中之最要議題，而雙影像爲3D資訊取得技術之重要技術之一。本研究以同步式霍普菲爾類神經網路解決掃瞄式雙影性對應問題，首先，特性點以索伯運算子(Sobel operator)及自訂之臨界值於雙影像中分別取得，再將此資訊表示爲一雙影像對應最佳化問題之能量函數，此函數包含相異性、連續性、視差特性及單一性等條件，再以同步式霍普菲爾類神經網路求取此函數之最小植，最後再以一錯誤對應移除準則將錯誤之對應點移除。本研究以一般通用之雙影像作實驗驗證，實驗顯示本研究所提出方法可有效地解決該問題，並可應用於多種領域中。

關鍵字

雙影像對應 ； 雙影像系統 ； 同步式霍普菲爾類神經網路 ； 機器視覺

並列摘要

Deriving depth information has been an important issue in computer vision. In this area, stereo vision is an important technique for 3D information acquisition. This paper presents a scanline-based stereo matching technique using synchronous Hopfield neural networks (SHNN). Feature points are extracted and selected using the Sobel operator and a user-defined threshold for a pair of scanned images. Then, the scanline-based stereo matching problem is formulated as an optimization task where an energy function, including dissimilarity, continuity, disparity and uniqueness mapping properties, is minimized. Finally, the incorrect matches are eliminated by applying a false target removing rule. The proposed method is verified with an experiment using several commonly used stereo images. The experimental results show that the proposed method solves effectively the stereo matching problem and is applicable to various areas.

並列關鍵字

stereo matching ； correspondence problem ； synchronous Hopfield neural network ； computer vision

參考文獻

Ackermann, F.(1984).Digital image correlation-performance and potential application in photogrammetry.Photgrammetric Record.11,429-439.

Calitz, M. F.,H. Ruether(1985).Least absolute deviation (LAD) image matching.ISPRS Journal of Photogrammetry and Remote Sensing.52,160-168.

Cavalieri, S.,A. D. Stefano,O. Mirabella(1994).Optimal path determination in a graph by Hopfield neural network.Neural Networks.7,387-404.

Craievich, D.,B. Barnett,A. C. Bovik(1999).A stereo visual pattern image coding system.Image and Vision Computing.18,21-37.

Do, K. H.,Y. S. Kim,T. U. Uam,Y. H. Ha(1998).Iterative relaxational stereo matching based on adaptive support between disparities.Pattern Recognition.31,1049-1059.