Identification of hazelnut fields using spectral and Gabor textural features Selçuk Reis a , Kadim Tas ßdemir b,⇑ a Department of Geomatics, Faculty of Engineering, Aksaray University, 68100 Aksaray, Turkey b Monitoring Agricultural Resources Unit, Institute for Environment and Sustainability, European Commission Joint Research Centre, Via E. Fermi 2749, 21027 Ispra (VA), Italy article info Article history: Received 28 September 2010 Received in revised form 27 April 2011 Accepted 27 April 2011 Available online 24 May 2011 Keywords: Orchard detection Hazel orchards Texture analysis Multi-scale Gabor features Self-organizing maps Maximum likelihood classifier abstract Land cover identification and monitoring agricultural resources using remote sensing imagery are of great significance for agricultural management and subsidies. Particularly, permanent crops are impor- tant in terms of economy (mainly rural development) and environmental protection. Permanent crops (including nut orchards) are extracted with very high resolution remote sensing imagery using visual interpretation or automated systems based on mainly textural features which reflect the regular planta- tion pattern of their orchards, since the spectral values of the nut orchards are usually close to the spec- tral values of other woody vegetation due to various reasons such as spectral mixing, slope, and shade. However, when the nut orchards are planted irregularly and densely at fields with high slope, textural delineation of these orchards from other woody vegetation becomes less relevant, posing a challenge for accurate automatic detection of these orchards. This study aims to overcome this challenge using a classification system based on multi-scale textural features together with spectral values. For this pur- pose, Black Sea region of Turkey, the region with the biggest hazelnut production in the world and the region which suffers most from this issue, is selected and two Quickbird archive images (June 2005 and September 2008) of the region are acquired. To differentiate hazel orchards from other woodlands, in addition to the pansharpened multispectral (4-band) bands of 2005 and 2008 imagery, multi-scale Gabor features are calculated from the panchromatic band of 2008 imagery at four scales and six orien- tations. One supervised classification method (maximum likelihood classifier, MLC) and one unsuper- vised method (self-organizing map, SOM) are used for classification based on spectral values, Gabor features and their combination. Both MLC and SOM achieve the highest performance (overall classifica- tion accuracies of 95% and 92%, and Kappa values of 0.93 and 0.88, respectively) when multi temporal spectral values and Gabor features are merged. High F b values (a combined measure of producer and user accuracy) for detection of hazel orchards (0.97 for MLC and 0.94 for SOM) indicate the high quality of the classification results. When the classification is based on multi spectral values of 2008 imagery and Gabor features, similar F b values (0.95 for MLC and 0.93 for SOM) are obtained, favoring the use of one imagery for cost/benefit efficiency. One main outcome is that despite its unsupervised nature, SOM achieves a classification performance very close to the performance of MLC, for detection of hazel orchards. Ó 2011 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved. 1. Introduction Permanent crops are very important commercially for agricul- tural sector of a number of countries as well as for rural develop- ment and environmental protection. As a result, many countries have regulations and monitoring systems to manage and control the agricultural activities related to these crops. This is in particu- lar the case of the European Union whose common agriculture pol- icy (CAP) was established to support farmers income, provide quality food at a reasonable price and in sufficient quantity while preserving the environment and rural heritage. In the history of the CAP, permanent crops have always had specific management rules. This has been the case for vineyards (to fight against over- production), olive groves (till 2009) and nut orchards. Presently nut orchards are only eligible to a specific payment provided they meet some criteria on minimum density and area of the orchard, which in turn requires determination of the lands covered by these orchards. This is usually done through visual interpretation of the remote sensing imagery, in absence of automatic method for map- ping nut orchards. Hazelnut is one of the most produced nut crops in the world, with a production of 1,051,652 tons produced mainly by Turkey (800,791 tons, 76% of world’s production) followed by Italy (111,841 tons) and the USA (33,000 tons) (FAO, 2008). Plantation area of hazel orchards are approximately 810,000 ha in the world with approximately 632,000 ha area in Turkey (Fiskobirlik, 2007). 0924-2716/$ - see front matter Ó 2011 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved. doi:10.1016/j.isprsjprs.2011.04.006 ⇑ Corresponding author. E-mail address: kadim.tasdemir@jrc.ec.europa.eu (K. Tas ßdemir). ISPRS Journal of Photogrammetry and Remote Sensing 66 (2011) 652–661 Contents lists available at ScienceDirect ISPRS Journal of Photogrammetry and Remote Sensing journal homepage: www.elsevier.com/locate/isprsjprs