Search for: All records

FLAME 3 is the third dataset in the FLAME series of aerial UAV-collected side-by-side multi-spectral wildlands fire imagery (see FLAME 1 and FLAME 2). This set contains a single-burn subset of the larger FLAME 3 dataset focusing specifically on Computer Vision tasks such as fire detection and segmentation. Included are 622 image quartets labeled Fire and 116 image quartets labeled No Fire. The No Fire images are of the surrounding forestry of the prescribed burn plot. Each image quartet is composed of four images - a raw RGB image, a raw thermal image, a corrected FOV RGB image, and a thermal TIFF. Each of the four data types are detailed in the below Table 1. More information on data collection methods, data processing procedures, and data labeling can be found in https://arxiv.org/abs/2412.02831. This dataset also contains a NADIR Thermal Fire set, providing georeferenced overhead thermal imagery, captured by UAV every 3-5 seconds, focusing on monitoring fire progression and burn behaviors over time. This data, when processed, enables centimeter-grade measurements of fire spread and energy release over time. Pre, post, and during burn imagery are included, along with ground control point (GCP) data.  This dataset is based on the research conducted in the paper: FLAME 3 Dataset: Unleashing the Power of Radiometric Thermal UAV Imagery for Wildfire Management. It provides detailed insights and analysis related to forest fire monitoring and modeling.If you use this dataset in your research or projects, please cite the original paper as follows: APA: Hopkins, B., ONeill, L., Marinaccio, M., Rowell, E., Parsons, R., Flanary, S., Nazim I, Seielstad C, Afghah, F. (2024). FLAME 3 Dataset: Unleashing the Power of Radiometric Thermal UAV Imagery for Wildfire Management. arXiv preprint arXiv:2412.02831.BibTeX: @misc{hopkins2024flame3datasetunleashing, title={FLAME 3 Dataset: Unleashing the Power of Radiometric Thermal UAV Imagery for Wildfire Management}, author={Bryce Hopkins and Leo ONeill and Michael Marinaccio and Eric Rowell and Russell Parsons and Sarah Flanary and Irtija Nazim and Carl Seielstad and Fatemeh Afghah}, year={2024}, eprint={2412.02831}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2412.02831}, } 

In our ever-expanding world of advanced satellite and communications systems, there's a growing challenge for passive radiometer sensors used in the Earth observation like 5G. These passive sensors are challenged by risks from radio frequency interference (RFI) caused by anthropogenic signals. To address this, we urgently need effective methods to quantify the impacts of 5G on Earth observing radiometers. Unfortunately, the lack of substantial datasets in the radio frequency (RF) domain, especially for active/passive coexistence, hinders progress. Our study introduces a controlled testbed featuring a calibrated L-band radiometer and a 5G wireless communication system. In a controlled chamber, this unique setup allows us to observe and quantify transmission effects across different frequency bands. By creating a comprehensive dataset, we aim to standardize and benchmark both wireless communication and passive sensing. With the ability to analyze raw measurements, our testbed facilitates RFI detection and mitigation, fostering the coexistence of wireless communication and passive sensing technologies while establishing crucial standards. 

Drone based wildfire detection and modeling methods enable high-precision, real-time fire monitoring that is not provided by traditional remote fire monitoring systems, such as satellite imaging. Precise, real-time information enables rapid, effective wildfire intervention and management strategies. Drone systems’ ease of deployment, omnidirectional maneuverability, and robust sensing capabilities make them effective tools for early wildfire detection and evaluation, particularly so in environments that are inconvenient for humans and/or terrestrial vehicles. Development of emerging drone-based fire monitoring systems has been inhibited by a lack of well-annotated, high quality aerial wildfire datasets, largely as a result of UAV flight regulations for prescribed burns and wildfires. The included dataset provides a collection of side-by-side infrared and visible spectrum video pairs taken by drones during an open canopy prescribed fire in Northern Arizona in 2021. The frames have been classified by two independent classifiers with two binary classifications. The Fire label is applied when the classifiers visually observe indications of fire in either RGB or IR frame for each frame pair. The Smoke label is applied when the classifiers visually estimate that at least 50% of the RGB frame is filled with smoke. To provide additional context to the main dataset’s aerial imagery, the provided supplementary dataset includes weather information, the prescribed burn plan, a geo-referenced RGB point cloud of the preburn area, an RGB orthomosaic of the preburn area, and links to further information.