مقایسه روش پیکسل پایه ( بیشترین شباهت ) و شی‌گراء ( ماشین بردار پشتیبان ) در طبقه بندی کاربری اراضی ( منطقه اهر – ورزقان )

چکیدهدر سالهای اخیر تهیه نقشه های کاربری اراضی از طریق طبقه بندی رقومی داده های سنجش از دور به عنوان جایگزینی مناسب برای تهیه این نوع نقشه ها مورد توجه قرار گرفته است، تهیه نقشه های کاربری اراضی از طریق طیقه بندی رقومی داده های سنجش از دور به روش های مورد استفاده در طبقه بندی، وضعیت پوشش زمین و شرایط محیطی منطقه مورد مطالعه بستگی دارد. نتایج حاصله در این زمینه بر حسب روش های طبقه بندی مورد استفاده، شرایط منطقه مورد مطالعه و داده های بکار گرفته شده متفاوت بوده است. در نتیجه در سال های اخیر با پیشرفت تکنولوژی پردازش کامپیوتری روش های جدیدی پیشنهاد شده است. بر اساس ویژگیهای پردازش تصویر، جهت استخراج اطلاعات از تصاویر ماهواره ای در این روش ها، آنها را می توان در دو گروه عمده تقسیم بندی نمود که عبارتند از: روش طبقه بندی مبتنی بر ارزش های عددی عناصر تصویری یا پیکسل ( پیکسل پایه ) و روش طبقه بندی مبتنی بر شی های تصویری  (شی گرا ). هدف از این تحقیق، مقایسه روش های طبقه بندی پیکسل پایه ( الگوریتم بیشترین شباهت ) و شی پایه ( ماشین بردار پشتیبان ) برای تهیه نقشه کاربری اراضی با استفاده ازتصویرسنجنده hdr ماهواره ای spot5 و تصویر سنجنده oli ماهواره landsat8 در محدوده ی حوضه آبریز اهر چای از منطقه اهر تا ورزقان است.  بدین منظور نقشه کاربری اراضی منطقه اهر – ورزقان با هر دو روش در نرم افزار envi 5.3 طبقه بندی شده است. مقایسه نتایج مربوط به صحت کلی و ضریب کاپای طبقه بندی ها نشان می دهد که روش طبقه بندی شی گرا با افزایش دقت معادل 5.6 درصد صحّت کلی و 0.04 درصد ضریب کاپا، در طبقه بندی تصاویر ماهواره ای از دقت بالاتری برخوردار است .

Comparison of Pixelbased Algorithm (maximum liklihood) and Objectbased Method (Support Vector Machine) in Classification of Land Use (AharVarzeghan Area)

Extended Abstract:Introduction:In general, satellite data classification with digital interpretation method is separation of similar spectral sets and classification of images into groups or classes placed in each class, spectrum or a value (not being separable statistically). In other words, when a classification is carried out on data sets or images, in fact spectral classification is conducted and in the new image, every class or category is indicator of a specific phenomenon with a unit spectral value. The base for data classification is comparison of spectral value of picture pixels with the samples introduced by its interpreter or with initial classes and   categories, constituted automatically in the time of digital interpretation. Hence, the pixels, values of which are not statistically significant, are placed in the same spectral group or class. So, preparation of land use maps by digital classification of remote data sensing depends on the methods used in classification, land coverage condition and environmental condition of the area. The aim of the present research study is to compare pixelbased classification algorithm (maximum likelihood) with objectbased method (support vector machine) to prepare land use maps with the aid of SPOT5 satellite HDR image sensor and Landsat 8 satellite OLI image sensor in Ahar Chai basin from Ahar area to Varzegan.Methods and materials:In this research study a SPOT5 satellite HDR image sensor dated back to August 23, 2006 with four spectral bands and separation power of 10 m with path and passage 138272, 138273, 139272 and 139273 and Landsat 8 satellite OLI image sensor dated back to 2017/07/21 with route and passage 16833, isolation power of 30m, increased to 15m through combination with band 8 were used to collected the necessary data. Topography map at scale 1/50000 and geological maps of 1/100000, land control data harvested by GPS, Garmin model and ArcGIS 10.4.1 and ENVI 5.3 software were used in this study. Information extraction from remote sensing data especially land cover can be obtained by digital classification. In practical some people are more comfortable using visual interpretation to retrieve land cover information. However, it is highly influenced by subjectivity and knowledge of interpreter, also takes time in the process. Digital classification can be done in several ways, depend on the defined mapping approach and assumptions on data distribution. The study compared several classifiers method for some data type at the same location. Maximum likelihood Classifiers (MLC) which use pixelbased and objectbased classification using advanced supervised machinelearning algorithms such as Support Vector Machine (SVM).Therefore, the aim of the present research is to compare maximum likelihood in pixelbased processing and support vector machine algorithm in objectbased processing in order to evaluate their performance in classification of LANDSAT 8 and SPOT 5   satellite images.  The necessary preprocessing including geometrical corrections and atmosphere corrections were conducted on the image.Discussion and conclusion:Findings of the study indicated that both support vector machine algorithm in objectbased classification and maximum likelihood in pixelbased classification enjoy higher and appropriate accuracy in classification and exploration of land use maps for AharVarzegan area. However, considering the results obtained from the two algorithms used in this research, it can be concluded that   support vector machine algorithm in objectbased classification of satellite images provide the conditions for higher accuracy compared to maximum likelihood in pixelbased method. One of the main reasons of achieving higher accuracy in support vector machine algorithm classification is that in this algorithm, in addition to spectral data the data related to contexture, shape, position and content are also used in classification process, hence classification accuracy is increased significantly. After doing classification procedure using both algorithms of pixel and objectbased method we proceeded on evaluation of the results reliability in themConclusion:The results showed that, Findings obtained from both classification algorithms indicated higher accuracy of objectbased classification with total accuracy of 94.99 % and Kappa coefficient for exploration of land use of AharVarzegan area, this is while pixelbased classification with total accuracy of 89.39% and Kappa coefficient of 0.89% indicated acceptable level of classification. So that Feizizadeh et.al (2009) in exploration of East Azerbaijan land use with the aid of the two pixelbased and objectbased algorithms concluded that objectbased classification with total accuracy of 95.10 % has higher efficiency in exploration of the province land use compared to pixelbased classification with total accuracy of 88.37%.