Mapping land cover from detailed aerial photography data using textural and neural network analysis

Automated mapping of land cover using black and white aerial photographs, as an alternative method to traditional photo‐interpretation, requires using methods other than spectral analysis classification. To this end, textural measurements have been shown to be useful indicators of land cover. In this work, a neural network model is proposed and tested to map historical land use/land cover (LUC) from very detailed panchromatic aerial photographs (5 m resolution) using textural measurements. The method is used to identify different land use and management types (e.g. traditional versus mechanized vineyard systems). These have been tested with known ground reference data. The results show the potential of the methodology to obtain automatic, historic, and very detailed cartography information from a complex landscape such as the mountainous and Mediterranean region to which it is applied here, and the advantages that this method has over traditional methods.

[1]  R. Hord,et al.  LAND-USE MAP ACCURACY CRITERIA , 1976 .

[2]  Luis A. Ruiz,et al.  Combining multispectral images and selected textural features from high-resolution images to improve discrimination of forest canopies , 1998, Remote Sensing.

[3]  Arko Lucieer,et al.  Interactive and visual fuzzy classification of remotely sensed imagery for exploration of uncertainty , 2004, Int. J. Geogr. Inf. Sci..

[4]  Arivazhagan Selvaraj,et al.  Texture classification using wavelet transform , 2003, Pattern Recognit. Lett..

[5]  Matt Aitkenhead,et al.  A novel method for training neural networks for time-series prediction in environmental systems , 2003 .

[6]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[7]  V. Caselles,et al.  Cartografiado de la Vid con datos Landsat-TM. Aplicación a una Zona de Tomelloso (Ciudad Real) , 2001 .

[8]  Invariant Features for Texture Image Retrieval using Steerable Pyramid , 2000 .

[9]  A. Gibon,et al.  Agricultural abandonment in mountain areas of Europe: Environmental consequences and policy response , 2000 .

[10]  W. Fjellstad,et al.  Patterns of change in two contrasting Norwegian agricultural landscapes , 1999 .

[11]  S. Kirkby,et al.  Agricultural terrace abandonment in the alpujarra, andalucia, spain , 1994 .

[12]  B. S. Manjunath,et al.  A Texture Thesaurus for Browsing Large Aerial Photographs , 1998, J. Am. Soc. Inf. Sci..

[13]  M. Ihse,et al.  Swedish agricultural landscapes : patterns and changes during the last 50 years, studied by aerial photos , 1995 .

[14]  Eric F. Lambin,et al.  Modelling and monitoring land-cover change processes in tropical regions , 1997 .

[15]  William T. Freeman,et al.  Presented at: 2nd Annual IEEE International Conference on Image , 1995 .

[16]  R. G. Pontius,et al.  Modeling land-use change in the Ipswich watershed, Massachusetts, USA , 2001 .

[17]  Xavier Pons,et al.  Agricultural Abandonment in the North Eastern Iberian Peninsula: The Use of Basic Landscape Metrics to Support Planning , 2005 .

[18]  Arko Lucieer,et al.  Texture based segmentation of high - resolution remotely sensed imagery for identification of fuzzy objects , 2003 .

[19]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[20]  Moncef Gabbouj,et al.  Rock Texture Retrieval Using Gray Level Co-occurrence Matrix , 2002 .

[21]  Jinfei Wang,et al.  Deriving terrain and textural information from stereo RADARSAT data for mountainous land cover mapping , 2005 .

[22]  R. Congalton,et al.  Accuracy assessment: a user's perspective , 1986 .

[23]  Peter M. Atkinson,et al.  The integration of spectral and textural information using neural networks for land cover mapping in the Mediterranean , 2000 .

[24]  G..  A Comparison of Sampling Schemes Used in Generating Error Matrices for Assessing the Accuracy of Maps Generated from Remotely Sensed Data , 2008 .

[25]  Stephen V. Stehman,et al.  A Strategy for Estimating the Rates of Recent United States Land-Cover Changes , 2002 .

[26]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[27]  J. Bouma,et al.  A spatial explicit allocation procedure for modelling the pattern of land use change based upon actual land use , 1999 .

[28]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[29]  A. Hay.  Sampling designs to test land-use map accuracy , 1979 .

[30]  José A. Martínez-Casasnovas,et al.  Land terracing for new vineyard plantations in the north-eastern Spanish Mediterranean region: Landscape effects of the EU Council Regulation policy for vineyards’ restructuring , 2006 .

[31]  A. Skidmore,et al.  Selection of imagery data and classifiers for mapping Brazilian semideciduous Atlantic forests , 2004 .

[32]  Paul M. Mather,et al.  The use of backpropagating artificial neural networks in land cover classification , 2003 .

[33]  Michael Batty,et al.  GIS and remote sensing as tools for the simulation of urban land‐use change , 2005 .

[34]  Jean-François Mas,et al.  Mapping land use/cover in a tropical coastal area using satellite sensor data, GIS and artificial neural networks , 2004 .

[35]  X. Li,et al.  Land-use change analysis in Yulin prefecture, northwestern China using remote sensing and GIS , 2004 .

[36]  G. H. Rosenfield,et al.  A coefficient of agreement as a measure of thematic classification accuracy. , 1986 .

[37]  Sakari Tuominen,et al.  Performance of different spectral and textural aerial photograph features in multi-source forest inventory , 2005 .

[38]  Análisis de imágenes mediante texturas: aplicación a la clasificación de unidades de vegetación , 2000 .

[39]  Alfred Stein,et al.  Multivariate texture‐based segmentation of remotely sensed imagery for extraction of objects and their uncertainty , 2005 .

[40]  Anne Puissant,et al.  The utility of texture analysis to improve per‐pixel classification for high to very high spatial resolution imagery , 2005 .

[41]  G. M. Foody,et al.  Relating the land-cover composition of mixed pixels to artificial neural network classification outpout , 1996 .

[42]  G. Fry,et al.  The ecological and amenity functions of woodland edges in the agricultural landscape; a basis for design and management , 1997 .

[43]  P. S. K. Shah.  Image Classification Based on Textural Features using Artificial Neural Network ( ANN ) , 2022 .

[44]  G. Bocco,et al.  Predicting land-cover and land-use change in the urban fringe A case in Morelia city, Mexico , 2001 .

[45]  B. S. Manjunath,et al.  A texture thesaurus for browsing large aerial photographs , 1998 .

[46]  E. Salinero.  Teledetección ambiental: la observación de la Tierra desde el espacio , 2002 .

[47]  Robert M. Haralick,et al.  Textural features for image database retrieval , 1998, Proceedings. IEEE Workshop on Content-Based Access of Image and Video Libraries (Cat. No.98EX173).

[48]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..