Conference proceeding
Real-time lidar feature detection using convolution neural networks
Vol.13049, pp.130490B-130490B-8
06/05/2024
DOI: 10.1117/12.3013563
Abstract
A limitation of traditional airborne and spaceborne lidar instruments is the inability to provide data products in real time. This challenge is compounded by typical research-driven desires to build ever more complicated lidar sensors, which overlooks the need to provide simple, but timely, data products to operational forecast models. Machine learning techniques using convolution neural networks (CNNs) have been developed and applied to single wavelength (e.g., 1064 nm) data from the airborne Cloud Physics Lidar (CPL) and have shown encouraging results for feature detection at finer resolutions compared to traditional methods, notably during noisy daytime conditions. Current technologies and properly scoped measurement goals, not intended as be-all/end-all research tools, permit designs for miniaturized lidar sensors that can be placed on drones and, ultimately, in constellations of minisats. Use of advanced machine learning techniques for data processing permits generation of real time data products that can be quickly assimilated into predictive models (for air quality and human health) and for generating real-time data products for decision making (such as hazardous plume detection and monitoring).
Details
- Title: Subtitle
- Real-time lidar feature detection using convolution neural networks
- Creators
- Matthew J. McGill - University of IowaStephen D. Roberson - Society for Social Studies of ScienceWilliam Ziegler - Society for Social Studies of ScienceRon Smith - Society for Social Studies of ScienceJohn E. Yorks - Goddard Space Flight Center
- Contributors
- Gary W. Kamerman (Editor) - FastMetrix Industries, LLC (United States)Lori A. Magruder (Editor) - Applied Research Laboratories, The University of Texas at AustinMonte D. Turner (Editor) - National Geospatial-Intelligence Agency
- Resource Type
- Conference proceeding
- Publication Details
- Vol.13049, pp.130490B-130490B-8
- Publisher
- SPIE
- DOI
- 10.1117/12.3013563
- ISSN
- 0277-786X
- Language
- English
- Date published
- 06/05/2024
- Academic Unit
- Chemical and Biochemical Engineering; Physics and Astronomy
- Record Identifier
- 9984648260002771
Metrics
7 Record Views