نوع مقاله : مقاله پژوهشی

نویسندگان

• ابوالفضل قنبری ¹
• مصطفی موسی پور ²
• هابیل خرمی حسین حاجلو ³
• حسین انوری ²

¹ استاد دانشگاه تبریز

² دانشجوی دکتری سنجش از دور و سیستم اطلاعات جغرافیایی دانشگاه تبریز، تبریز، ایران.

³ دانشجوی دکتری سنجش از دور و سیستم اطلاعات جغرافیایی دانشگاه تبریز، تبریز، ایران

چکیده

توسعه فیزیکی مناطق شهری یکی از محرک‌های اصلی تغییرات جهانی است که تأثیرات مستقیم و غیرمستقیم مهمی بر شرایط محیطی و تنوع زیستی دارد. استفاده از تکنیک ­های سنجش از دور، یکی از رویکردهای جدید در برنامه‌ریزی شهری  محسوب می شود. پژوهش حاضر با هدف مقایسه کارآیی طبقه­ بندی کننده ­های یادگیری ماشین مبتنی بر پردازش شیئ­ گرای تصاویر ماهواره ­ای در استخراج محدوده توسعه فیزیکی شهر همدان با استفاده از تصویر ماهواره سنتینل 2 انجام شده است. در این راستا، فرایند قطعه ­بندی بر اساس مقیاس، ضریب شکل و ضریب فشردگی مناسب با هدف تولید اشیاء تصویری انجام شد. پس از قطعه­ بندی و تبدیل تصویر به اشیاء تصویری، با استفاده از طبقه­ بندی کننده ­های یادگیری ماشین مبتنی بر پردازش شیئ­ گرای تصاویر ماهواره ­ای شامل الگوریتم­ های طبقه­ بندی کننده بیز، k - نزدیکترین همسایه، ماشین بردار پشتیبان، درخت تصمیم ­گیری و درخت­ های تصادفی، فرایند طبقه­ بندی انجام و نقشه ­های محدوده توسعه فیزیکی شهری تولید شد. در نهایت، مقدار دقت هر کدام از نقشه­ های تولید شده محاسبه شد. بر اساس نتایج تحقیق، امکان تولید نقشه محدوده توسعه فیزیکی شهری همدان با استفاده از الگوریتم ­های یادگیری ماشین مبتنی بر پردازش شیئ­ گرای تصاویر ماهواره ­ای با دقت قابل قبول وجود دارد. به طوری که طبقه­ بندی کننده بیز دارای دقت کلی 96 درصد و ضریب کاپای 0.95، k - نزدیکترین همسایه دارای دقت کلی 97 درصد و ضریب کاپای 0.96، ماشین بردار پشتیبان دارای دقت کلی 96 درصد و ضریب کاپای 0.95، درخت تصمیم­ گیری دارای دقت کلی 95 درصد و ضریب کاپای 0.94 و درخت­ های تصادفی دارای دقت کلی 95 درصد و ضریب کاپای 0.94 بودند. لذا از بین کلیه الگوریتم ­های مورد استفاده در این تحقیق، k - نزدیکترین همسایه با دقت کلی 97 درصد و ضریب کاپای 0.96 مقدار دقت بیشتری را ارائه نمود.  

کلیدواژه‌ها

• سنجش از دور
• یادگیری ماشین
• سنتینل 2
• شیئ گرا
• همدان

موضوعات

• سیستم اطلاعات جغرافیایی

عنوان مقاله [English]

Comparing the efficiency of machine learning classifiers in extracting the physical development area of Hamedan city using Object-Based Images analysis of satellite images

نویسندگان [English]

• Abolfazl Ghanbari ¹
• Mostafa Mousapour ²
• Habil Khorrami hossein hajloo ³
• Hossein Anvari ²

¹ Academic Member/ University of Tabriz

² Ph.D Candidate, Remote sensing and Geographical Information System, Tabriz University, Tabriz, Iran.

³ Ph.D Candidate, Remote sensing and Geographical Information System, Tabriz University, Tabriz, Iran.

چکیده [English]

Extended Abstract
Introduction:
The urban space is the most important human-made spatial structure on the planet earth. The history of urban development shows the path of human development, political system evolution and technological, technical and industrial developments. The physical development of urban areas is one of the main drivers of global changes that have important direct and indirect effects on environmental conditions and biodiversity. In the process of physical development of the city, due to the transformation of natural and semi-natural ecosystems into impermeable surfaces, it often causes irreversible environmental changes. One of the new approaches in urban planning is the use of remote sensing techniques and geographic information system. The emergence of remote sensing and machine learning techniques offers a new and promising opportunity for accurate and efficient monitoring and analysis of urban issues in order to achieve sustainable development. The process of processing satellite images can generally be divided into two approaches: pixel-based image analysis and object-based image analysis. The pixel-based analysis technique is performed at the level of each pixel of the image and uses only the spectral information available in each pixel. On the other hand, the object-based analysis approach is performed on a homogeneous group of pixels, taking into account the spatial characteristics of the pixels. One of the basic problems in urban remote sensing is the heterogeneity of the urban physical environment. The urban environment usually includes built structures such as buildings and urban transportation networks, several different types of vegetation such as agricultural areas, gardens, as well as barren areas and water bodies. Therefore, in the pixel-based processing approach, the existence of heterogeneity in the urban biophysical environment causes spectral mixing and also spectral similarities in the classification operation of satellite images in such a way that in a place where a pixel is If the surrounding environment is different, it causes Salt and Pepper Noise. Therefore, according to the problems in the pixel-based processing approach, the aim of this research is to compare the accuracy of machine learning algorithms based on object-based processing of satellite images in extracting the physical development area of Hamedan city using Sentinel 2 satellite image.
Materials & Methods:
    The remote sensing data used in this research is a multi-spectral satellite image with a spatial resolution of 10 meters from the Sentinel 2 satellite, including bands 2 (blue), 3 (green), 4 (red) and 8 (near infrared) related to the date is the 23 of August 2023 in the city of Hamadan. The image of the Sentinel 2 satellite was downloaded from the website of the European Space Agency. In ENVI software, the pre-processing operation was performed on the satellite image. Then, in the eCognition software, the segmentation process was performed based on the appropriate scale, shape factor, and compression factor with the aim of producing image objects. After segmenting and converting the image into image objects, using machine learning classifiers based on object-oriented processing of satellite images including Bayes classification algorithms, k-nearest neighbor, support vector machine, decision tree and random trees, the classification process was carried out and maps of urban physical development area were produced. After the segmentation operation and the production of visual objects, three classes of built-up urban land, vegetation and barren land were defined, and some of the built objects in the segmentation stage were selected as training points and some were selected as ground Truth points.
Results & Discussion
After downloading the satellite image from the website of the European Space Organization, in order to apply the radiometric correction of the image and also with the aim of matching the value of the gray levels of the image with the value of the real pixels of the terrestrial reflection, the gray levels are converted to radiance and then, using atmospheric correction, to coefficients. They became terrestrial reflections. In order to apply radiometric correction, Radiometric Calibration tool was used, and to apply atmospheric correction, FLAASH model was used in ENVI software. In order to classify the satellite image based on machine learning algorithms based on object-based processing, eCognition software was used. The satellite image of the study area, which was pre-processed and saved in TIFF format, was called in the environment of this software and saved as a project. In order to produce visual objects, segmentation operations were performed in different scales, shape factor and compression ratio to reach the most appropriate segmentation mode. In this step, the multiple resolution segmentation method was used to segment the image. The most appropriate segmentation included the scale of 100 and the shape factor of 0.6 and the compression factor of 0.4. Because in scales higher than 100, the construction of the visual object was not done correctly, so that several distinct complications were placed in one piece, and in scales less than 100, in some cases, one complication was placed in several pieces. In order to classify the generated image objects, machine learning algorithms were defined separately and after training each algorithm, the classification operation was performed. In this step, the classification was done based on the nearest neighbor method and by selecting the average and standard deviation parameters for each image band. After producing a map of the city physical development range through machine learning classifiers based on object-based processing of satellite images, the classification accuracy of each of the used algorithms was calculated. In order to calculate the accuracy of the above algorithms in eCognition software, using selected ground Truth control points, the overall accuracy and kappa coefficient were calculated for each of the algorithms.
Conclusion:
Based on the results of the research, it is possible to produce a map of Hamedan's urban physical development using machine learning algorithms based on object-based processing of satellite images with acceptable accuracy. Also, among all the algorithms used in this research, k-nearest neighbor with overall accuracy of 97% and kappa coefficient of 0.96 provided more accuracy.

کلیدواژه‌ها [English]

• Remote sensing
• machine learning
• Sentinel 2
• Object-Based
• Hamedan