Revealing urban green space coverage using object-oriented processing of satellite images(Case study: Monajem and Yousefabad neighborhoods of Tabriz)

Urban green space is one of the important indicators in the fields of urban planning, environmental protection and sustainable urban development policies. Knowledge of the location, amount and distribution of urban green space is a necessity. The available green space is decreasing for the purpose of developing residential lands. Today, with the progress made in the production of satellite images with high spatial and spectral resolution and remote sensing techniques, ARCGIS and image processing have made it possible to collect data and make quick and accurate decisions in environmental studies. The main goal of this research is to reveal the coverage of urban green space using object oriented processing. In order to carry out this research, IRS, Sanjande (Liss) satellite images in 2017, as well as Sentinel 2 images, bands 2, 3, 4, 8 (visible) with a spatial resolution of 10 meters were used. After making the necessary corrections, the images in the ENVI5 software environment.1 and eCognition processed that these processes include algorithms (SI, NDSI, NDVI, Brightness, etc.) to identify the area and object-based algorithms are used for evaluation. The results of this research showed that this method had a good accuracy for evaluation with an overall accuracy of 93% and a Kappa coefficient of 92%, and it was possible to detect urban green spaces using the object-oriented processing method, and it was determined that using Satellite images and object-oriented algorithms are possible to identify and investigate urban green space, and its results can be an efficient way to identify object-based algorithms and use them in future research studies