Geolocating and Mosaicking Airborne Infrared Video for Wildfire Risk Analysis over Time without IMU Information
Bibliographic record
Abstract
Airborne infrared (IR) surveys of wildfires allow for quantifying the energy produced by a fire, which can be used in wildfire risk management. If several flights are completed across the same location over time, the evolution of the burn can also be analyzed. However, for this to be done, accurate geolocation of the imagery must be completed. Once the images are geolocated, additional products such as a mosaic can be produced, which in turn can be used for further analysis or to validate satellite products. These are common tasks across most airborne remote sensing data, whose approaches are often highly dependent on how the data were collected, and what associated positional (GPS and IMU) information is available. Here we show a simple yet effective method using a mid-wave (3-5um) IR FLIR SC8300 camera's video, for cases when IMU data is not recorded. Our study is based on a series of surveys flown over a naturally-occurring wildfire in northern Ontario, Canada. These data were collected at different times of day over a 48 hour period, resulting in imagery that records the development of the wildfire. Additionally, four integration times (ITs) were concurrently collected to ensure the broad spectrum of temperatures could be properly measured. To compare and analyse the datasets, we developed a custom solution to geolocate and mosaic the videos using Matlab. Our solution is a simple and flexible method that computes an iterative frame registration followed by mosaicking using a grid-based approach. One of the key reasons for this custom development was to ensure that all ITs could be correctly mosaicked. The shorter ITs offer very little background information to use as points of interest (POIs) to work with for frame registration, as they are only effective at very high temperatures. Therefore, we developed this method to allow the shorter ITs to utilize the same registration transformations as calculated from the longest IT data, which contained many more POIs, such as surrounding rivers. We show results for wildfire imagery collected during an afternoon flight and a night flight with 1m resolution, as well as our final processed imagery, which was georeferenced to GeoEye satellite imagery using ArcGIS 10.6 and ENVI 5.5 to further improve accuracy.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".