뉴로-퍼지 알고리즘을 이용한 원격탐사 화상의 지표면 패턴 분류시스템 구현

An Implementation of Neuro-Fuzzy Based Land Convert Pattern Classification System for Remote Sensing Image

  • 이상구 (한남대학교 컴퓨터전자통신공학부)
  • 발행 : 1999.10.01

초록

본 논문에서는 뉴로-퍼지 알고리즘을 이용한 원격탐사 화상의 지표면 패턴분류기를 제안한다. 제안된 패턴 분류기는 일반적인 퍼지 인식기를 가지고 있는 3층 전방향 신경회로망 구조로 되어 있고 가중치들은 퍼지집합으로 구성된다. 이러한 퍼지-뉴로 패턴분류 시스템을 Visual C++ 환경을 구현한다. 성능평가를 위해 기존의 역전파 학습기능을 가진 신경회로망과 Maximum-likelihood 알고리즘을 이용해처리한 결과와비교분석한다. 대표적인 지표면 특징을 나타내는 8개의 클래스에 대해 훈련집합을 선정하고 각각의 분류 알고리즘에 같은 훈련집합을 사용하여 학습시킨 후 실험화상을 적용하여 지표면 특징을 8개의 클래스로 분류하였다. 실험결과 제안된 뉴로-퍼지 분류기는 여러개의 클래스로 혼합된 패턴에 대해서 기존의 분류기들에 비해 보다 더 좋은 성능을 보인다.

In this paper, we propose a land cover pattern classifier for remote sensing image by using neuro-fuzzy algorithm. The proposed pattem classifier has a 3-layer feed-forward architecture that is derived from generic fuzzy perceptrons, and the weights are con~posed of h u y sets. We also implement a neuro-fuzzy pattern classification system in the Visual C++ environment. To measure the performance of this, we compare it with the conventional neural networks with back-propagation learning and the Maximum-likelihood algorithms. We classified the remote sensing image into the eight classes covered the majority of land cover feature, selected the same training sites. Experimental results show that the proposed classifier performs well especially in the mixed composition area having many classes rather than the conventional systems.

키워드

참고문헌

  1. Manual of Remote Sensing American Society of Photogrammetry
  2. Int. J. Remote Sensing v.17 no.9 Integration of multi-seasonal remotely-sensed images for improved landuse classification of a hilly watershed using geographical information systems J. Adinarayana;N. Rama krishna
  3. Int. J. Remote Sensing v.17 no.7 Approaches for the production and evaluation of fuzzy land over classifications from remotely-sensed data G.M. Foody
  4. Photogrammetric Engineering & Remote Sensing v.58 no.2 inclusion of Prior Probabilities Derived from a Nonparametric Process into the Maximum-Likelihood Classifier F. Maselli;C. Conese;Ljiljana;R. Resti
  5. in Proc. of the IASTED Int. Conf. Artificial Intelligence and Soft Computing Land Surface Classification of Landsat 5 TM Data Using SOFM and GA Sang Gu Lee;Jong Gyu Han
  6. IEEE Trans. Geosci. and Remote Sensing v.33 A Detailed Comparison of Backpropagation Neural Network and Maximum-Likelihood Classifier for Urban Land Use Classification J.D. Paola;R.A. Schowengerdt
  7. IEEE Trans. Geosci. and Remote Sensing v.34 no.2 Remote Sensing of Forest Change Using Artificial Neural Networks S. Gopal;C. Woodcock
  8. Photogrammetric Engineering & Remote Sensing v.63 no.11 An Evaluation of the Potential for Fuzzy Classification of Mutispectral Data Using Artificial Neural network T.A. Warner;M. Shank
  9. Neural Networks for Statistical Modeling M. Smith
  10. Neural Fuzzy Systems Chin Teng Lin;C.S. George Lee
  11. Journal of the Korean Society of Remote Sensing v.13 no.3 Fuzzy Logic Based Satellite Image Classification Using Automatically Generated Fuzzy Membership Functions and Rules from Training Set Wonkyu Park;Heung Kyu Lee
  12. FUZZ-IEEE'99 v.2 A Neuro-Fuzzy Classifier for Land Cover Classification Sang Gu Lee;Jong Gyu Han(et al.)