Sub‐pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super‐resolution pixel‐swapping

Mapping rural land cover features, such as trees and hedgerows, for ecological applications is a desirable component of the creation of cartographic maps by the Ordnance Survey. Based on the phenomenon of spatial dependence, sub‐pixel mapping can provide increased mapping accuracy of such features. A simple pixel‐swapping algorithm for sub‐pixel mapping was applied to soft classified fine spatial resolution remotely sensed imagery. Initially, QuickbirdTM satellite sensor imagery with a spatial resolution of 2.6 m was acquired of the Christchurch area of Dorset, UK, and three field sites chosen. The imagery was soft classified using a supervised fuzzy c‐means algorithm and then super‐resolved into sub‐pixels using a zoom factor of five. Sub‐pixels within pixels were then iteratively swapped until the spatial correlation between sub‐pixels for the entire image was maximized. Mathematical morphology was used to suppress error in the super‐resolved output, increasing overall accuracy. Field data, including detailed information on the features apparent in the field sites, were used to assess the accuracy of the resultant image. Overall RMSE was between 20 and 30%, resulting in the sub‐pixel mapping method producing reasonably accurate results overall of between 50 and 75%. Visual inspection of the super‐resolved output shows that the prediction of the position and dimensions of hedgerows was comparable with the original imagery.

[1]  V. F. Leavers,et al.  Which Hough transform , 1993 .

[2]  Nathan J. Heinert,et al.  Extending satellite remote sensing to local scales: land and water resource monitoring using high-resolution imagery , 2003 .

[3]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[4]  C. Woodcock,et al.  The factor of scale in remote sensing , 1987 .

[5]  L. Bastin.  Comparison of fuzzy c-means classification, linear mixture modelling and MLC probabilities as tools for unmixing coarse pixels , 1997 .

[6]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

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

[8]  P. Atkinson,et al.  Introduction Neural networks in remote sensing , 1997 .

[9]  Jacques Baudry,et al.  An overview of the landscape ecology of hedgerows. , 2001 .

[10]  Lindi J. Quackenbush.  A Review of Techniques for Extracting Linear Features from Imagery , 2004 .

[11]  Robert A. Schowengerdt.  CHAPTER 9 – Thematic Classification , 2007 .

[12]  J. Chilès,et al.  Geostatistics: Modeling Spatial Uncertainty , 1999 .

[13]  Peter M. Atkinson.  Super-resolution target mapping from soft classified remotely sensed imagery , 2001 .

[14]  P. Atkinson.  Sub-pixel Target Mapping from Soft-classified, Remotely Sensed Imagery , 2005 .

[15]  Giles M. Foody,et al.  Approaches for the production and evaluation of fuzzy land cover classifications from remotely-sensed data , 1996 .

[16]  Alan R. Gillespie,et al.  Vegetation in deserts. I - A regional measure of abundance from multispectral images. II - Environmental influences on regional abundance , 1990 .

[17]  Michael Batty,et al.  The discrete dynamics of small-scale spatial events: agent-based models of mobility in carnivals and street parades , 2003, Int. J. Geogr. Inf. Sci..

[18]  Peter M. Atkinson,et al.  Fine Spatial Resolution Simulated Satellite Sensor Imagery for Land Cover Mapping in the United Kingdom , 1999 .

[19]  Weiguo Liu,et al.  Comparison of non-linear mixture models: sub-pixel classification , 2005 .

[20]  Emes Dynamiques.  Ecole Nationale Superieure des Mines de Paris , 1993 .

[21]  Paul J. Curran,et al.  Remote sensing: Using the spatial domain , 2001, Environmental and Ecological Statistics.

[22]  Giles M. Foody,et al.  Hard and soft classifications by a neural network with a non-exhaustively defined set of classes , 2002 .

[23]  P. Fisher.  The pixel: A snare and a delusion , 1997 .

[24]  Luis Samaniego,et al.  Fuzzy rule-based classification of remotely sensed imagery , 2002, IEEE Trans. Geosci. Remote. Sens..

[25]  Robert De Wulf,et al.  Land cover mapping at sub-pixel scales using linear optimization techniques , 2002 .

[26]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[27]  Giles M. Foody,et al.  Estimation of sub-pixel land cover composition in the presence of untrained classes , 2000 .

[28]  E Brown de Colstoun,et al.  National Park vegetation mapping using multitemporal Landsat 7 data and a decision tree classifier , 2003 .

[29]  C. Burnett,et al.  A multi-scale segmentation/object relationship modelling methodology for landscape analysis , 2003 .

[30]  Alan H. Strahler,et al.  Global land cover mapping from MODIS: algorithms and early results , 2002 .

[31]  Robert A. Schowengerdt,et al.  Remote sensing, models, and methods for image processing , 1997 .

[32]  Hugh G. Lewis,et al.  Increasing the spatial resolution of agricultural land cover maps using a Hopfield neural network , 2003, Int. J. Geogr. Inf. Sci..

[33]  Céline Boutin,et al.  Hedgerows in the farming landscapes of Canada. , 2001 .

[34]  U. Benz,et al.  Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information , 2004 .

[35]  P. Mather,et al.  Classification Methods for Remotely Sensed Data , 2001 .

[36]  Q. Zhan,et al.  Pixel unmixing at the sub-pixel scale based on land cover class probabilities : application to urban areas , 2001 .

[37]  Alan H. Strahler,et al.  On the nature of models in remote sensing , 1986 .

[38]  A. Cracknell.  Review article Synergy in remote sensing-what's in a pixel? , 1998 .

[39]  Jian-guo Wu.  Hierarchy and scaling: Extrapolating informa-tion along a scaling ladder , 1999 .

[40]  J. Settle,et al.  Linear mixing and the estimation of ground cover proportions , 1993 .