As the data acquisition capabilities of Earth observation (EO) satellites have been improved substantially in the past few years, large amount of high-resolution satellite images are downlinked continuously to ground stations. Such amount of data increases rapidly beyond the users' capability to access the images' content in reasonable time. Hence, automatic and fast interpretation of a large data volume is a computationally intensive task. Recently, approximate nearest neighbour search has been used for content-based image retrieval in sub-linear time. Kernelized locality sensitive hashing (KLSH) is a well-known approximate method, which has recently shown promising results for fast remote sensing image retrieval. This paper proposes a novel parallelization of KLSH using Graphical Processing Units (GPU), in order to perform fast parallel image retrieval. The proposed method was tested on high-dimensional feature vectors from two satellite-based image datasets, where an average speedup of 20 times was achieved.
B.03 Paper at an international scientific conference
COBISS.SI-ID: 19151638Data from the forest monitoring programme in Slovenia were used to assess the relationship between tree phenology, crown defoliation and meteorological conditions in Fagus sylvatica, Quercus robur and Picea abies forests in the 2004–2013 period. We hypothesized a species-specific response of first leaf unfolding, general leaf colouring, the length of the growing season to crown defoliation, air temperature, precipitation and soil water.
B.03 Paper at an international scientific conference
COBISS.SI-ID: 4202662The workshop has been organized within the largest world conference on geographic information named Geospatial World Forum and the INSPIRE conference, organised by the European commission. The purpose of the workshop was to inform the audience about the internet of things, big data, linked data and open data. During the workshop, new ideas on key strategic directions in regards to the spatial data integration and the development of supporting tools have been discussed. The outcome of the discussions was a draft of the main policy positions, which were adopted by the European umbrella organisation for geographic information – EUROGI.
F.18 Transfer of new know-how to direct users (seminars, fora, conferences)
COBISS.SI-ID: 18716438