Color and texture fusion: application to aerial image segmentation and GIS updating

被引:48
作者
Dubuisson-Jolly, MP [1 ]
Gupta, A [1 ]
机构
[1] Siemens Corp Res, Imaging & Visualizat Dept, Princeton, NJ 08540 USA
关键词
color segmentation; texture segmentation; fusion; geographical information systems;
D O I
10.1016/S0262-8856(99)00050-5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper describes a new algorithm for combining color and texture information for the segmentation of color images. The algorithm uses maximum likelihood classification combined with a certainty based fusion criterion. The algorithm was validated using mosaics of real color textures. It was also tested on real outdoor color scenes and aerial images. This algorithm is part of a more complex system, which is currently bring designed to assist an operator in updating an old map of an area using aerial images. (C) 2000 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:823 / 832
页数:10
相关论文
共 12 条
[1]   ON THE CLASSIFICATION OF IMAGE REGIONS BY COLOR, TEXTURE AND SHAPE [J].
CAELLI, T ;
REYE, D .
PATTERN RECOGNITION, 1993, 26 (04) :461-470
[2]  
HAAG W, 1995, P IGARSS FIR IT, P901
[3]   TEXTURE CLASSIFICATION AND SEGMENTATION USING MULTIRESOLUTION SIMULTANEOUS AUTOREGRESSIVE MODELS [J].
MAO, JC ;
JAIN, AK .
PATTERN RECOGNITION, 1992, 25 (02) :173-188
[4]  
MURNI A, 1995, P ACCV SING, V3, P92
[5]   MARKOV RANDOM-FIELD MODELS FOR UNSUPERVISED SEGMENTATION OF TEXTURED COLOR IMAGES [J].
PANJWANI, DK ;
HEALEY, G .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1995, 17 (10) :939-954
[6]  
Picard R. W., 1993, Proceedings. 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.93CH3309-2), P638, DOI 10.1109/CVPR.1993.341050
[7]   VISION TEXTURE FOR ANNOTATION [J].
PICARD, RW ;
MINKA, TP .
MULTIMEDIA SYSTEMS, 1995, 3 (01) :3-14
[8]  
REED TR, 1993, CVGIP-IMAG UNDERSTAN, V57, P359, DOI 10.1006/ciun.1993.1024
[9]  
RICHARDS JA, 1993, REMOTE SENSING DIGIT, V2
[10]  
SHE AC, 1994, P IEEE INT C IM PROC, V3, P1026