Numeric and symbolic data fusion: A soft computing approach to remote sensing images analysis

被引:23
作者
Desachy, J
Roux, L
Zahzah, EH
机构
[1] UNIV TOULOUSE 3, IRIT, F-31062 TOULOUSE, FRANCE
[2] UNIV LA ROCHELLE, L3I, F-17000 LA ROCHELLE, FRANCE
关键词
satellite image classification; information fusion; neural networks; evidence and possibility theory;
D O I
10.1016/S0167-8655(96)00093-1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
An expert system approach for image classification according to expert knowledge about best sites for vegetation classes is described. Uncertainty management is solved by a certainty factor approach. The numerical and symbolic data fusion is viewed as an updating process. The fusion approach is then described. A neural classifier applied to image data is the first source. A set of fuzzy neural networks representing expert knowledge constitutes the second source. A conjunctive combination based on evidence theory is applied. Finally, a possibility theory-based pooling aggregation rule is presented. These three approaches are applied to a vegetation classification problem.
引用
收藏
页码:1361 / 1378
页数:18
相关论文
共 20 条
  • [1] [Anonymous], 1986, International Journal of Intelligent Systems, DOI [DOI 10.1002/INTA550010302, DOI 10.1002/INT.4550010302]
  • [2] [Anonymous], 1988, POSSIBILITY THEORY A
  • [3] Information combination operators for data fusion: A comparative review with classification
    Bloch, I
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS, 1996, 26 (01): : 52 - 67
  • [4] DESACHY J, 1980, NATO ASI SERIES
  • [5] DESACHY J, 1989, P IEEE INT C IM PROC, V1, P127
  • [6] DESACHY J, 1987, P ISPRS, P418
  • [7] POSSIBILITY THEORY AND DATA FUSION IN POORLY INFORMED ENVIRONMENTS
    DUBOIS, D
    PRADE, H
    [J]. CONTROL ENGINEERING PRACTICE, 1994, 2 (05) : 811 - 823
  • [8] Dubois D., 1992, DATA FUSION ROBOTICS, P481
  • [9] Farreny H., 1985, SYSTEMES EXPERTS PRI
  • [10] CONNECTIONIST EXPERT SYSTEMS
    GALLANT, SI
    [J]. COMMUNICATIONS OF THE ACM, 1988, 31 (02) : 152 - 169