Vision based semantic runway segmentation from simulation with deep convolutional neural networks

Quessy, Alexander D.; Richardson, Thomas S.; Hansen, Mark

Abstract

Manned flight crew rely upon optical imagery to make sense of the world and carry out high level guidance, navigation & control tasks. To advance autonomous aircraft’s capabilities and safety, programmes need to be developed that aim to achieve piloted human-level perception. We designed a simulation environment to train deep Convolutional Neural Networks (CNNs) to semantically segment objects and then test the trained network on imagery collected from the same location on a real aircraft. This approach is capable of achieving state of the art performance on the task of runway segmentation along with providing a proof of concept to rapidly generate training sets on simulation capable of being used on fixed-wing aircraft.

Citation

Quessy, A. D., Richardson, T. S., & Hansen, M. (2022). Vision based semantic runway segmentation from simulation with deep convolutional neural networks. https://doi.org/10.2514/6.2022-0680

• Conference Name: AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2022
• Conference Location: San Diego, CA & Virtual
• Start Date: Jan 3, 2022
• End Date: Jan 7, 2022
• Online Publication Date: Dec 29, 2021
• Publication Date: 2022
• Deposit Date: Feb 2, 2022
• Publisher: American Institute of Aeronautics and Astronautics
• ISBN: 9781624106316
• DOI: https://doi.org/10.2514/6.2022-0680
• Public URL: https://uwe-repository.worktribe.com/output/8809108