HPWREN Fire Ignition images Library for neural network training

The HPWREN Fire Ignition images Library for neural network training
18 August 2020 - last update: 21 August 2020

This page provides access to the HPWREN Fire Ignition image Library (FIgLib), usually based on sequences of wildland fire images as seen from fixed cameras at HPWREN sites. It contains hundreds of such sequences of different fires or different cameras, where a camera may even be separate imagers for color, or monochrome with more light and near-IR sensitivity.

This data is provided as-is, no guarantees for anything is included.

The primary purpose of this large archive, many gigabytes in size, is the creation of baseline data sets for 40 minutes before and after individual fire ignitions for neural network training, specifically AI-based detections of wildland fire ignitions based of content within a single or across multiple images. For illustration purposes full resolution MP4 video animations per individual data set are included as well. The image file names for the principal data set are:

origin_timestamp _ offset_(sec)_from_visible_plume_appearance .jpg

While we are making the data publicly available, its use requires a credit reference to "http://hpwren.ucsd.edu/" in derivative work. We encourage people and projects working with the data to contact us via the feedback form on the main HPWREN web site about what the archive is being used for.

Image data availability

  • Access to the individual sequences, images, and animations is provided via the FIgLib images data pointer. It will show a directory view of the sequences named, e.g., like:

    - 20170708_Whittier_syp-n-mobo-m
    - meaning: YYYYMMDD_firename_camera/imager
    - specifically here the July 8 2017 ignition of the Whittier Fire, as seen from the camera on Santa Ynez Peak near Santa Barbara in the "n"orth direction, using the "m"onochrome chip.

    Clicking one of the sequences will show the contents of the specific directory, including the MP4 animation and the individual JPEG files utilizing the file name format mentioned above.

  • The whole archive is also accessible via a very large (many gigabytes) tar file of the sequences of image data.

  • Data sets of notable long fire data sequences, along with a large tar file of those sequences are available for comparison purposes, as well as to consider neural networks to interpret fire behavior. The JPEG file names here do not follow the FIgLib naming convention, and just use the image-origin Unix Epoch time stamp.

  • To investigate temporal aspects of a fire plume, using motion vectors to estimate movement, the HPWREN-FIgLib-Motionvectors directory contains files along the objectives in the http://hpwren.ucsd.edu/news/20190823/ summary. A large tar file of the motion vector experimental data is available as well.

    Image labels

    There is a chance that we may be able to make quality labels, perhaps bounding boxes and contours, available in the relatively near future. For the time being we labeled a few fires with Bounding Boxes, using Jim Davidson's labelem.py python3 script. Some data sets for this are available in CSV and in XML format.

    Regarding labelem.py: It makes things easier to start by pressing "End" to go to the end of a fire data set and work backwards on labeling the images, pulling the bounding box with the left mouse button, and then "Shift-leftarrow" to carry over the bounding box to the previous image in this time series. Don't forget "Save and Exit" at the end to write out the output files. The program has been tested on Ubuntu Linux, and can be run like:

    python3 ./labelem.py "--image=imagedir/*.jpg" --bbfile=bboxfile.csv --screensize 2540x1508 --vocdir=VOC/xmloutfile

    The screensize parameter depends on your screen. While labelem.py generally works, it is not a finished product, so your mileage may vary. Some disclaimers are in the source code.