Computer vision analysis of biological semi transparent colour objects

This Ph.D. project is mainly concerned with the reconstruction of the 3D structure of plants, mainly the orientations and chronology of their leaves and fix points such as leaf tips and bases. Identification and analysis of the individual 3D elements of a canopy will be the basis for development of descriptive methods for the overall structure of the canopy. The project is also concerned with the problem of getting dense ground truth information about the complex natures of the observed objects. The work proposes using imperfect image sets of ray-traced plant models as a means to perform in-depth analysis of the algorithms in relation to the scenes. Currently, the co-operation also extends outside the ACROSS consortium. Together with KVL, experiments have been conducted to detect leaf area index, leaf tips and bases on barley for automation of sampling of hyper-spectral data. In collaboration with University of California in Davis, 3D computer vision techniques have been used for detecting weeds under tomato canopies. This was used for generating spray maps for micro-sprayers. Funded through the ACROSS project. (Michael Nielsen, Hans Jørgen Andersen, Erik Granum)