The impact of relative radiometric calibration on the accuracy of kNN-predictions of forest attributes

The k-nearest-neighbour (kNN) algorithm is widely applied for the estimation of forest attributes using remote sensing data. It requires a large amount of reference data to achieve satisfactory results. Usually, the number of available reference plots for the kNN-prediction is limited by the size of the area covered by a terrestrial reference inventory and remotely sensed imagery collected from one overflight. The applicability of kNN could be enhanced if adjacent images of different acquisition dates could be used in the same estimation procedure. Relative radiometric calibration is a prerequisite for this. This study focuses on two empirical calibration methods. They are tested on adjacent LANDSAT TM scenes in Austria. The first, quite conventional one is based on radiometric control points in the overlap area of two images and on the determination of transformation parameters by linear regression. The other, recently developed method exploits the kNN-cross-validation procedure. Performance and applicability of both methods as well as the impact of phenology are discussed.

[1]  E. Tomppo,et al.  Selecting estimation parameters for the Finnish multisource National Forest Inventory , 2001 .

[2]  Erkki Tomppo,et al.  Using coarse scale forest variables as ancillary information and weighting of variables in k-NN estimation: a genetic algorithm approach , 2004 .

[3]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[4]  Walter G. Kropatsch,et al.  Digital image analysis: selected techniques and applications , 2001 .

[5]  J. Cihlar,et al.  Radiometric normalization of multitemporal high-resolution satellite images with quality control for land cover change detection , 2002 .

[6]  Werner Schneider,et al.  Image Understanding Methods for Remote Sensing , 2001, Digital Image Analysis.

[7]  Didier Tanré,et al.  Second Simulation of the Satellite Signal in the Solar Spectrum, 6S: an overview , 1997, IEEE Trans. Geosci. Remote. Sens..

[8]  Susan A. Murphy,et al.  Monographs on statistics and applied probability , 1990 .

[9]  Ronald E. McRoberts,et al.  Stratified estimation of forest area using satellite imagery, inventory data, and the k-Nearest Neighbors technique , 2002 .

[10]  S. Goetz,et al.  Radiometric rectification - Toward a common radiometric response among multidate, multisensor images , 1991 .

[11]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[12]  John A. Richards,et al.  Remote Sensing Digital Image Analysis , 1986 .

[13]  M. Nilsson,et al.  Regional forest biomass and wood volume estimation using satellite data and ancillary data , 1999 .

[14]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[15]  M. Over,et al.  Relative radiometric normalisation of multitemporal Landsat data-a comparison of different approaches , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[16]  William J. Volchok,et al.  Radiometric scene normalization using pseudoinvariant features , 1988 .

[17]  Robert Tibshirani,et al.  An Introduction to the Bootstrap , 1994 .

[18]  M. Bauer,et al.  Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method , 2001 .

[19]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[20]  Belur V. Dasarathy,et al.  Nearest neighbor (NN) norms: NN pattern classification techniques , 1991 .

[21]  Christopher D. Elvidge,et al.  Relative radiometric normalization of Landsat Multispectral Scanner data using an automatic scattergram-controlled regression , 1998 .