Cibiraite-Lukenskiene, DovileDovileCibiraite-LukenskieneGundacker, DominikDominikGundackerBihler, M.M.BihlerHeizmann, M.M.HeizmannSchlüter, FriedrichFriedrichSchlüterAderhold, JochenJochenAderholdRoming, LukasLukasRomingGruna, RobinRobinGrunaJonuscheit, JoachimJoachimJonuscheitFriederich, FabianFabianFriederich2023-11-022024-05-082023-11-022023https://publica.fraunhofer.de/handle/publica/45446710.1109/irmmw-thz57677.2023.10299146This work presents the results of the initial acquisition of a multi-modal dataset that will be utilized to train and test a neural network for wood sorting. The aim of the project is to improve wood recycling from bulky waste by using four complementary sensing systems: visual, infrared, terahertz, and thermography. The four systems were combined to capture 57 multi-modal images of bulky waste samples moving on the conveyor belt at a speed of 10 cm/s. Early fusion results on THz show 0.77 accuracy, whereas the best multi-modal data fusion accuracy equals 0.921.enconference paper