Print Email Facebook Twitter Semantic Segmentation using Deep Neural Networks for MAVs Title Semantic Segmentation using Deep Neural Networks for MAVs Author Tran, Tommy (TU Delft Aerospace Engineering) Contributor de Croon, G.C.H.E. (mentor) Xu, Y. (mentor) de Wagter, C. (graduation committee) van Gemert, J.C. (graduation committee) Degree granting institution Delft University of Technology Programme Aerospace Engineering | Control & Simulation Date 2022-01-19 Abstract Semantic segmentation methods have been developed and applied to single images for object segmentation. However, for robotic applications such as high-speed agile Micro Air Vehicles (MAVs) in Autonomous Drone Racing (ADR), it is more interesting to consider temporal information as video sequences are correlated over time. In this work, we evaluate the performance of state-of-the-art methods such as Recurrent Neural Networks (RNNs), 3D Convolutional Neural Networks (CNNs), and optical flow for video semantic segmentation in terms of accuracy and inference speed on three datasets with different camera motion configurations. The results show that using an RNN with convolutional operators outperforms all methods and achieves a performance boost of 10.8% on the KITTI (MOTS) dataset with 3 degrees of freedom (DoF) motion and a small 0.6% improvement on the CyberZoo dataset with 6 DoF motion over the single-frame-based semantic segmentation method. The inference speed was measured on the CyberZoo dataset, achieving 321 fps on an NVIDIA GeForce RTX 2060 GPU and 30 fps on an NVIDIA Jetson TX2 mobile computer. Subject Micro Air VehicleSemantic SegmentationDeep LearningConvolutional Neural NetworkRecurrent Neural NetworkOptical Flow To reference this document use: http://resolver.tudelft.nl/uuid:7735d01c-b4cd-4173-a584-652f269c078c Part of collection Student theses Document type master thesis Rights © 2022 Tommy Tran Files PDF Final_Thesis_Tran.pdf 40.41 MB Close viewer /islandora/object/uuid:7735d01c-b4cd-4173-a584-652f269c078c/datastream/OBJ/view