Shoer, I.Gunturk, B.K.Ates, H.F.Baykas, T.2023-10-192023-10-19202297816654962091522-4880https://doi.org/10.1109/ICIP46576.2022.9897467https://hdl.handle.net/20.500.12469/4822The Institute of Electrical and Electronics Engineers Signal Processing Society29th IEEE International Conference on Image Processing, ICIP 2022 --16 October 2022 through 19 October 2022 -- --185922It is expected that unmanned aerial vehicles (UAVs) will play a vital role in future communication systems. Optimum positioning of UAVs, serving as base stations, can be done through extensive field measurements or ray tracing simulations when the 3D model of the region of interest is available. In this paper, we present an alternative approach to optimize UAV base station altitude for a region. The approach is based on deep learning; specifically, a 2D satellite image of the target region is input to a deep neural network to predict path loss distributions for different UAV altitudes. The neural network is designed and trained to produce multiple path loss distributions in a single inference; thus, it is not necessary to train a separate network for each altitude. © 2022 IEEE.eninfo:eu-repo/semantics/closedAccessconvolutional neural networksdeep learningpath loss estimationUAV networks3D modelingAntennasConvolutional neural networksDeep neural networksImage segmentationUnmanned aerial vehicles (UAV)Vehicle to vehicle communicationsAerial vehicleConvolutional neural networkDeep learningLoss distributionLoss estimationPath lossPath loss estimationSatellite imagesUnmanned aerial vehicle networkVehicle networkBase stationsConference Object2471247510.1109/ICIP46576.2022.98974672-s2.0-85146729305N/AN/A2