Influence of Image Fusion Approaches on Classification Accuracy – A Case Study

作者: René R. Colditz , Thilo Wehrmann , Martin Bachmann , Klaus Steinnocher , Michael Schmidt

DOI: 10.1080/01431160600649254

关键词:

摘要: While many studies in the field of image fusion remotely sensed data aim towards deriving new algorithms for visual enhancement, there is little research on influence other applications. One major application earth science land cover mapping. The concept sensors with multiple spatial resolutions provides a potential fusion. It minimises errors geometric alignment and atmospheric or temporal changes. This study focuses spectral classification their accuracy. A Landsat 7 ETM+ was used, where six multispectral bands (30 m) were fused corresponding 15 m panchromatic channel. methods comprise rather common techniques like Brovey, hue‐saturation‐value transform, principal component analysis, more complex approaches, including adaptive fusion, multisensor multiresolution technique, wavelet transformation. Image performed supervised met...

参考文章(48)
Jim. Vrabel, Multispectral imagery band sharpening study Photogrammetric Engineering and Remote Sensing. ,vol. 62, pp. 1075- 1083 ,(1996)
J.L. van Genderen, C. Pohl, Image fusion : issues, techniques and applications ,(1994)
M. Baatz, Multiresolution Segmentation-an optimization approach for high quality multi-scale image segmentation Angewandte Geographische Informations verarbeitung. ,(2000)
Jian Guo Liu, Evaluation of Landsat-7 ETM+ Panchromatic Band for Image Fusion with Multispectral Bands Natural resources research. ,vol. 9, pp. 269- 276 ,(2000) , 10.1023/A:1011553209310
Donald O. Ohlen, Jesslyn F. Brown, Thomas R. Loveland, Zhiliang Zhu, Limin Yang, Bradley C. Reed, An analysis of the IGBP global land-cover characterization process Photogrammetric Engineering and Remote Sensing. ,vol. 65, pp. 1021- 1032 ,(1999)
L. Wald, Groupe Télédétection, Definitions and terms of reference in data fusion Joint EARSeL/ISPRS Workshop "fusion of sensor data, knowledge sources and algorithms for extraction and classification of topographic objects". ,vol. 32, pp. 2- 6 ,(1999)
J Hill, C Diemer, O Stöver, Th Udelhoven, A LOCAL CORRELATION APPROACH FOR THE FUSION OF REMO TE SENSING DATA WITH DIFFERENT SPATIAL RESOLUTIONS IN FORESTRY APPLICATIONS Journal of International Archives of photogrammetry and Remote Sensing. ,vol. 32, pp. 14- 22 ,(1999)
J. Herrero-Isern, R. García, T. Benes, M. González-Audícana, Fusion of multispectral and panchromatic images using new methods based on wavelet transforms - evaluation of crop classification accuracy. Geoinformation for European-wide integration. Proceedings of the 22nd Symposium of the European Association of Remote Sensing Laboratories, Prague, Czech Republic, 4-6 June 2002.. pp. 265- 272 ,(2003)