ENVIRONMENTAL APPLICATIONS OF OBJECT-BASED CLASSIFICATION TECHNIQUES IN TIME SERIES ANALYSIS OF DIFFERENT RESOLUTION SATELLITE IMAGES

The environmental impact of technological development and the climate changes have lately increased the need of terrain mapping. In this context, a new class of improved satellite sensors was developed in order to meet the specific needs of certain industries. Remote Sensing technology is becoming more accessible and efficient in terms of costs for image acquisition. Currently, various types of records are available in high quality for different environmental applications. Based on satellite images with different resolution, the present study seeks to compare an object-based classification applied to Constanta city environmental area, located in the South-Eastern part of Romania. The goal is to keep the same types of classes for all images. To achieve this objective, images provided by the SPOT-5 SuperMode, Landsat 7 and the SPOT Multi-spectral (XS) satellites with different resolution (2.5, 30 and 10 m) were used. After processing the data and applying specific algorithms, the results vary from one case to another, depending on the selected classes, their accuracy and correctness. A great importance was given to establishing the appropriate segmentation in accordance with these images, thus with image objects.