Although many technological developments have been made and we are now collecting unimaginable amount of satellite images, we still lack the tools to effectively and efficiently analyze them. Object-based image analysis (OBIA) is devoted to developing automated methods to partition remote sensing imagery into meaningful image objects and assessing their characteristics through spatial, spectral and temporal scales, thus generating new geographic information in a GIS-ready format. During my PhD, I tackled issues related to image segmentation of remote sensing data, methods to improve the accuracy and computational time of segmentation, applied in a variety of application (e.g. urban mapping, agricultural mapping). The outcomes of this research have a significant potential to enable robustness and automation of OBIA applications.
Ovidiu Csillik was a fully funded PhD student at the Doctoral College, GIScience of the University of Salzburg and is curently a postdoc at Carnegie Institution for Science, Stanford, CA.
- Remote sensing
- Object-based image analysis
- Computer vision
- Environmental applications