استخراج نقشه کاربری اراضی با استفاده از مقایسه الگوریتم های مختلف طبقه بندی پیکسل پایه و شئ گرا؛ مطالعه موردی: شهر زنجان

این پژوهش با هدف استخراج نقشه کاربری اراضی شهری، با استفاده از مقایسه الگوریتم‌های مختلف طبقه‌بندی پیکسل‌پایه و شئ‌گرا می‌باشد. در این راستا الگوریتم‎‌های طبقه‌بندی پیکسل‌پایه ماشین بردار پشتیبان، حداکثر احتمال، شبکه عصبی مصنوعی، حداقل فاصله از میانگین، سطوح موازی و فاصله ماهالانوی مورد استفاده قرار گرفتند. در ادامه به مقایسه روش‌های مذکور با طبقه‌بندی شئ‌گرا جهت تهیه نقشه‌ کاربری اراضی شهر زنجان با استفاده از تصویرماهواره‌ایsentinel2 با قدرت تفکیک مکانی  10 متر پرداخته شد. به منظور انجام پردازش تصویر مورد استفاده از نرم‌افزار‌های envi 5.3، snap،ecognition و arcgisاستفاده شده است. ‌برای‌ مقایسه ‌عملی‌ نتایج،‌ د‌ر ‌هر ‌د‌و ‌روش‌ از ‌د‌اد‌ه‌های‌ آموزشی‌ یکسان‌ برای‌ طبقه‌بندی‌ استفاد‌ه‌ گرد‌ید‌؛‌ سپس ‌مهم‌ترین ‌روش‌های ‌ارزیابی ‌صحت‌ شامل‌ د‌قت‌کلی‌و‌ ضریب‌ کاپای‌ طبقه‌بندی‌ استخراج‌ شد. نتایج بدست آمده، نشان می‌دهد که از بین روش‌های طبقه‌بندی پیکسل‌پایه مورد استفاده در این مطالعه، روش‌های طبقه‌بندی حداکثر احتمال و روش حداقل فاصله تا میانگین با ضریب کاپای به ترتیب 0.95درصد و 0.85 درصد از دقت قابل قبولی برخوردار هستند. هم‌چنین مقایسه نتایج حاصل از طبقه‌بندی پیکسل‌پایه و شئ‌گرا  نشان داد که روش شئ‌گرا با اعمال پارامترهای موثر در طبقه‌بندی و توسعه قوانین جهت اطلاح طبقه‌بندی اولیه شئ‌گرا با ضریب کاپای 0.95 درصد از نظر دقت در استخراج  نقشه کاربری اراضی از روش‎‌های پیکسل‌پایه از اولویت برخوردار است.

Extracting Land Use Map based on a comparison between PixelBased and ObjectOriented Classification Methods Case Study: Zanjan City

Extended Abstract Introduction Currently, two general methods are used for classification of digital satellite images: pixelbased and objectoriented processing. Unlike pixelbased Methods, objectoriented techniques employ different geometric, spatial, spectral, and formbased algorithms, and selecting the most efficient algorithm in this process requires a lot of experience in image processing. In addition, multiple algorithms usually offer different results and this in many cases makes the selection of efficient algorithms difficult. In general, pixelbased classification includes supervised and unsupervised methods. Examples of these methods include maximum likelihood, neural network and support vector machine. Maximum likelihood method is one of the most effective methods used for image classification. Objectoriented methods take advantage of knowledgebased algorithms, and thus overcome problems pixelbased method faces because of not using geometric and textual information. In order to achieve high classification accuracy, two methods of pixelbased and objectoriented classification are compared in this research. On the one hand, integrated planning and management of urban areas, and on the other hand, collecting reliable information regarding land use makes this kinds of studies indispensable. Materials&Methods Present study seeks to extract urban land use map. Thus, necessary data was received from Sentinel2. Moreover, ENVI 5.3, eCognation 9, SNAP, ArcGIS 10.3, Google Earth, and landuse data were also used to process images and analyze data. In SNAP, atmospheric correction process was performed on images collected from the study area using SEN2COR plugin. Samples collected from each class of Sentinel2 satellite image were mapped on the image area. Pixel classification algorithms, support vector machines, maximum likelihood, artificial neural network, Minimum Distance to Mean (MDM), parallelepiped and Mahalanobis distance were used. Finally, land use classes (residential, gardens and green spaces, wastelands and passageways) in the study area were mapped using different classification algorithms. For objectoriented classification using nearest neighbor algorithm, the satellite image was first segmented in eCognation software using the Multiresolution Segmentation Algorithm. Parameters such as scale, shape and compactness were also studied in the image segmentation stage. Through trial and error, an appropriate value was selected for parameters used in segmentation. For practical comparison of the results, the same educational data was used in both objectoriented and pixelbased classification methods. Then, the most important methods for assessing accuracy including overall precision and kappa coefficient were extracted. Results & Discussion As one of the most important methods used for extracting information from remotely sensed images, classification allows users to produce various types of information such as coverage maps, and landuse maps. Classification of satellite data includes segregation of similar spectral sets and classification of sets with the same spectral behavior. Regarding the resolution of images used (10 m) in this study, only 4 landuse classes possessed the required resolution capability for pixelbased classification of Sentinel2 satellite images. These classes include builtup (residential) area, waste land, urban green space and street network. In this regard, support vector machine, maximum likelihood, artificial neural network, Minimum Distance to Mean, parallelepiped and Mahalanobis distance were used for classification. Classification results indicate that compared to other pixelbased methods, maximum likelihood method and Minimum Distance to Mean method show a precision of 85% or higher. In present study, geometric properties of land use classes (including scale, shape, and compactness) were used for segmentation and this process was performed by multiresolution method. For this purpose, results of image segmentation process were analyzed based on different parameters (with different scales) and spatial resolution of the image. In this way, appropriate values for segmentation were selected based on the specific features of the study area (an urban environment) through trial and error. Then, the proper image segmentation was selected and prepared for the classification stage using the above mentioned parameters. In the next step, 20 effective parameters including statistical indices, mean score of bands, NDVI index, standard deviation of the bands and geometric index were used for classification. Conclusion The present study took advantage of six pixelbased methods (Support Vector Machine, Maximum Likelihood, Neural Network, Minimum Distance to Mean, Parallelepiped, and Mahalanobis) along with objectoriented classification method to produce a landuse map for Zanjan city. The accuracy of classification in different methods were compared and statistically analyzed using overall accuracy coefficient, kappa coefficient, user’s accuracy, and producer’s accuracy. The results of statistical analysis of the accuracy coefficients indicated that Minimum Distance to Mean and Maximum Likelihood method with a Kappa coefficient of 90% and 85% respectively are acceptable methods for land use mapping. Moreover, comparing pixelbased and objectoriented methods, it is possible to conclude that objectoriented approach with a Kappa coefficient of 0.95% and overall accuracy of 97.9% shows a higher potentiality. Nearest Neighbor algorithm is one of the most important reasons for achieving this high accuracy in objectoriented classification. In addition to the spectral information, this method uses information collected about issues like texture, form, position, and content for the classification process. Methods used in this study prove the accuracy of objectiveoriented technique by employing effective parameters and developing rules to modify the initial classification of objectoriented technique. Another advantage of objectoriented method (as compared to pixelbased methods) is that apart from spectral information and statistical data, it is possible to apply several other indicators such as shape, texture, color, dimensions and altitude of the phenomena in the final land use map produced by this method. Finally, it should be noted that objectoriented classification has been developed for high resolution spatial data.