Research seminar "Computer methods for vegetation detection"

Abstract

Analyzing the state of vegetation from image data is important in the field of remote sensing where it is used for the detection of green areas, detection of changes brought about by urbanization, the detection of vegetation stress and drought, measuring the growth of forests, urban planning, and other similar applications that aim to increase environmental awareness . The need for detection of vegetation in robotics arose when they began to use autonomous vehicles for forest exploration, and later spread to use in navigating robots and autonomous vehicles. Researchers proposed a number of methods to solve the problem of detection and classification of vegetation which we separate, based on the mode of recording, in two groups: ground (e.g. cameras mounted on the vehicle) and airborne (e.g. satellite images) detection of vegetation. People easily detect vegetation on the basis of color and texture features, and there are systems that tend to imitate the human visual system. These systems use features that correspond to the human visual system, i.e., based on the visible spectrum. On the other hand there are systems based on the invisible spectrum (invisible to the human eye). This talk will give an overview of so far developed and most widely used methods for the detection of vegetation and the review of the area will serve as a basis for further research.

CV

Iva Harbaš received her BSc and MSc degree from the Faculty of Electrical Engineering and Computing in Zagreb. She finished her undergraduate study program in Computing in 2010 with a specialization in Information Processing and Multimedia Systems and in 2012 she finished her master study program in Information and Communication Technology specializing in Information Processing. Currently,  she is employed at the Faculty of Electrical Engineering and Computing, University of Zagreb, as a research engineer at the Department of Electronic Systems and Information Processing, where she is pursuing her PhD degree. Her research interests are in the area of image processing and application of machine learning methods for solving problems in computer vision.