TY - CHAP A1 - Ammalladene-Venkata, Manogna A1 - Seidel, Christian A1 - Halbe, Omkar A1 - Groitl, Christine A1 - Stahl, Christoph T1 - Deep Learning Based Obstacle Awareness from Airborne Optical Sensors T2 - 77th Annual Vertical Flight Society Forum and Technology Display (FORUM 77), the Future of Vertical Flight UR - https://doi.org/10.4050/F-0077-2021-16905 KW - Deep learning KW - Airborne Sensors KW - Obstacle Awareness Y1 - 2021 UR - https://doi.org/10.4050/F-0077-2021-16905 SN - 978-1-7138-3001-6 PB - Vertical Flight Society CY - Fairfax ER - TY - JOUR A1 - Ammalladene-Venkata, Manogna A1 - Halbe, Omkar A1 - Seidel, Christian A1 - Groitl, Christine A1 - Kramel, Lothar A1 - Stahl, Christoph A1 - Seidel, Heiko T1 - Deep Learning Based Obstacle Awareness from Airborne Optical Sensors JF - Journal of the American Helicopter Society N2 - Aviation statistics identify collision with terrain and obstacles as a leading cause of helicopter accidents. Assisting helicopter pilots in detecting the presence of obstacles can greatly mitigate the risk of collisions. However, only a limited number of helicopters in operation have an installed helicopter terrain awareness and warning system (HTAWS), while the cost of active obstacle warning systems remains prohibitive for many civil operators. In this work, we apply machine learning to automate obstacle detection and classification in combination with commercially available airborne optical sensors. While numerous techniques for learning-based object detection have been published in the literature, many of them are data and computation intensive. Our approach seeks to balance the detection and classification accuracy of the method with the size of the training data required and the runtime. Specifically, our approach combines the invariant feature extraction ability of pretrained deep convolutional neural networks (CNNs) and the high-speed training and classification ability of a novel, proprietary frequency-domain support vector machine (SVM) method. We describe our experimental setup comprising the CNN + SVM model and datasets of predefined classes of obstacles—pylons, chimneys, antennas, TV towers, wind turbines, helicopters—synthesized from prerecorded airborne video sequences of low-altitude helicopter flight. We analyze the detection performance using average precision, average recall, and runtime performance metrics on representative test data. Finally, we present a simple architecture for real-time, onboard implementation and discuss the obstacle detection performance of recently concluded flight tests. UR - https://doi.org/10.4050/JAHS.68.042012 Y1 - 2023 UR - https://doi.org/10.4050/JAHS.68.042012 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-43350 SN - 2161-6027 SN - 0002-8711 VL - 68 IS - 4 SP - 42012 EP - 42024 PB - Vertical Flight Society CY - Fairfax ER -