Dilek Koc-San

Building extraction from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification, Hough transformation and perceptual grouping

Abstract This paper presents an integrated approach for the automatic extraction of rectangular- and circular-shape buildings from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification, Hough transformation and perceptual grouping. The building patches are detected from the image using the binary SVM classification. The generated normalized digital surface model (nDSM) and the normalized difference vegetation index (NDVI) are incorporated in the classification process as additional bands. After detecting the building patches, the building boundaries are extracted through sequential processing of edge detection, Hough transformation and perceptual grouping. Those areas that are classified as building are masked and further processing operations are performed on the masked areas only. The edges of the buildings are detected through an edge detection algorithm that generates a binary edge image of the building patches. These edges are then converted into vector form through Hough transform and the buildings are constructed by means of perceptual grouping. To validate the developed method, experiments were conducted on pan-sharpened and panchromatic Ikonos imagery, covering the selected test areas in Batikent district of Ankara, Turkey. For the test areas that contain industrial buildings, the average building detection percentage (BDP) and quality percentage (QP) values were computed to be 93.45% and 79.51%, respectively. For the test areas that contain residential rectangular-shape buildings, the average BDP and QP values were computed to be 95.34% and 79.05%, respectively. For the test areas that contain residential circular-shape buildings, the average BDP and QP values were found to be 78.74% and 66.81%, respectively.

Support vector machines classification for finding building patches from IKONOS imagery: the effect of additional bands

Abstract This study aims to find building patches from pan-sharpened IKONOS imagery using two-class support vector machines (SVM) classification. In addition to original bands of the image, the normalized digital surface model, normalized difference vegetation index, and several texture measures (mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment, and correlation) are also used in the classification. The study illustrates the performance of the binary SVM classification in building detection from IKONOS imagery. Moreover, the effect of additional bands in building detection is examined. The approach was tested in three test sites that are located in the Batikent district of Ankara, Turkey. The SVM classification provided quite accurate results with the building detection percentage (BDP) values in the range 81.27–96.26% and the quality percentage (QP) values in the range 41.01–74.83%. It was found that the usage of additional bands in SVM classification had a significant effect in building detection accuracy. When compared to results obtained using solely the original bands, the additional bands increased the accuracy up to 10.44% and 8.45% for BDP and QP, respectively.

A model-based approach for automatic building database updating from high-resolution space imagery

This article presents an approach for automatic building database updating from high-resolution space imagery based on the support vector machine (SVM) classification and building models. The developed approach relies on an idea that the buildings are similar in shape within an urban block or a neighbourhood unit. First, the building patches are detected through classification of the pan-sharpened high-resolution space imagery along with the normalized digital surface model (nDSM) and the normalized difference vegetation index (NDVI) using the binary SVM classifier. Then, the buildings that exist in the vector database but not seen in the image are detected through the analyses of the detected building patches. The buildings, which were constructed after the compilation date of the existing vector database, are extracted through the proposed model-based approach that utilizes the existing building database as a building model library. The approach was implemented in selected urban areas of the Batikent district of Ankara, the capital city of Turkey, using the IKONOS images and the existing building database. The results validated the success of the developed approach, with the building extraction accuracy computed to be higher than 80%.

Unsupervised extraction of greenhouses using approximate spectral clustering ensemble

Monitoring and mapping greenhouses are important for yield estimation, sustainable crop production, residue management and environmental impact. Conventional approaches based on in situ surveys, which are costly and time consuming, are being replaced by supervised classification of commonly used features extracted from very-high spatial resolution images. Alternatively, we extract (both plastic and glass) greenhouses from Worldview-2 images in an unsupervised manner by approximate spectral clustering ensemble using hybrid geodesic similarity criterion. Our proposed approach is promising for automated detection of greenhouse areas with limited user information and outperforms earlier unsupervised extraction methods for greenhouses.

Unsupervised extraction of greenhouses using WorldView-2 images

Greenhouses provide controlled areas to produce high-quality and wide variety of agricultural products. However, their monitoring and mapping are essential in many aspects such as yield estimation, sustainable crop production, residue management and environmental impact. Increased coverage area in recent years poses another necessity for advanced methods in addition to the (costly and time consuming) conventional techniques. Supervised classification methods have been currently used for greenhouse mapping based on well-known features (extracted from very-high spatial resolution images) and classifiers. Our contribution is to extract greenhouses in an unsupervised manner: we utilize spectral features and Gabor textural featuresextracted from WorldView-2 images, and then we cluster the combined features by an approximate spectral clustering method based on a local density based similarity. Our experimental results are very promising for effective and automated detection of greenhouse areas with very limited user information.

Greenhouse Detection Using Aerial Orthophoto and Digital Surface Model

Detection of greenhouse areas from remote sensing imagery is important for rural planning, yield estimation and sustainable development. This study is focused on plastic and glass greenhouse detection and discrimination using true color orthophoto and Digital Surface Model (DSM). Initially, the greenhouse areas were detected from true color aerial photograph and the additional normalised Digital Surface Model (nDSM) band using Support Vector Machines (SVM) classification technique. Then, an approach was developed for discriminating plastic and glass greenhouses by utilising the nDSM. The developed approach was implemented in a selected study area from Kumluca district of Antalya, Turkey that includes intensive plastic and glass greenhouses. The obtained results show the effectiveness of the SVM classifier for greenhouse detection with overall accuracy value of 96.15%. In addition, the plastic and glass greenhouses were discriminated efficiently using the developed approach that use nDSM.

Automatic citrus tree extraction from UAV images and digital surface models using circular Hough transform

Abstract Tree counts and sizes are important information to apply to crop yield estimation and agricultural planning. Therefore, obtaining automatic extraction of trees, their locations, diameters, and counts from remotely sensed data is a challenging task. In this study, a novel approach is proposed for the automatic extraction of citrus trees using unmanned aerial vehicle (UAV) multispectral images (MSIs) and digital surface models (DSMs). The tree boundaries were extracted by using sequential thresholding, Canny edge detection and circular Hough transform algorithms. The performance of the developed approach was assessed on three test areas that include different characteristics with regard to tree counts, diameters, densities and background covers. The proposed tree extraction procedure was applied to DSM that were generated from UAV images (Data Set 1), UAV MSIs (Data Set 2) and both of them together (Data Set 3). The accuracies of the obtained results were assessed using three different techniques that evaluate the tree extraction results according to the counts, areas and locations. The obtained results indicate the success of the developed approach with delineation accuracies that exceeded 80% for each test area using each data set. The most accurate results were obtained when Data Set 1 was used. Although Data Set 2 provides the lowest accuracies when compared with other data sets, the delineation accuracies are still high and can be used especially for counting trees and detecting tree locations.

Site selection for avocado cultivation using GIS and multi-criteria decision analyses: Case study of Antalya, Turkey

Abstract Site selection for agricultural products is an important research area because determining accurate areas is essential for the successful growth of the products and for sustainable agriculture. The purpose of this study is to select suitable sites for avocado cultivation using geographical information system (GIS)-based multi-criteria decision Analysis (MCDA). Seven important factors for the growth of avocado trees were determined: forest border, slope, permeability, soil depth, land use capability, protected areas/forbidden zones, and average and minimum temperature. In the study, the overlay and analytical hierarchy process (AHP) analyses were used and integrated for efficient evaluation of the determined factors. The proposed approach was implemented in the Antalya province of Turkey, which has great potential for avocado production due to its climatic and environmental conditions. As a result, 602.12 km2 and 653.14 km2 areas were determined to be the most suitable and moderately suitable for avocado cultivation, respectively. Using two MCDA analyses and determining the intersection areas in the site-selection studies would be robust. By using this methodology, suitable lands for avocado cultivation were determined effectively and accurately.