Detection of preconditioned honeybees on data in visible wavelengths range collected from RPAS

A remote sensing method for assessment of spatial-temporal distribution of bees, was derived from 2003 to 2006 while its first operational application started in 2013 in the framework of the TIRAMISU Project. The method derives spatial-temporal distribution of the preconditioned (trained) honeybees above an area that is contaminated by explosive or landmines. For this purpose, a long-wave infrared cameras and high-resolution digital cameras were used. Direct detection of honeybees on an image is limited by the resolution of the electro-optical sensor, so for detection and assessment of spatial-temporal distribution of honeybees the principal components analysis (PCA) is crucial. The key feature of the method is an indirect detection of bees, by detecting their signatures in the principal component raster, obtained by processing the images of the time sequence. Within this project we have tested a several platforms for data acquisition: radio controlled blimp (2013), remotely piloted aircraft system (2014, 2015) and a mast (2013, 2015). The greatest challenge was to find an appropriate airborne platform and operational parameters for visible wavelength data acquisition since it is much harder to detect honeybees in this wavelength range, regarding lower contrast of honeybees to ground surface. Finally, in 2015, successful results were achieved with an RPAS and color camera with these parameters: 4096x2160 pixels, 24 bits and 25 frames/s. The 25 frames per second enables fine temporal resolution and estimation of spatial-temporal density.