| Résumé | 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. |
|---|
