×

back Laser point detection

The automatic laser point detection is used to determine the visual footprint of images.

For many collections of benthic images a geometric laser point pattern is used to determine the pixel-to-centimetre ratio of displayed sea floor. BIIGLE can assist in the evaluation of your data and provides a method [1] to automatically detect laser points and compute the visual footprint of the images.

Before you can start an automatic laser point detection you have to manually annotate a few example laser points in your images. Use point annotations with the "Laser Point" label of the global label tree to mark individual laser points. You have to annotate at least 4 images this way. BIIGLE currently supports the following types of geometric laser point patterns:

  • 2 parallel lasers painting two points
  • 3 parallel lasers painting the points of an equilateral triangle
  • 4 parallel lasers painting the points of a square

You can also annotate the laser points on all of your images manually. In this case BIIGLE will skip the automatic detection and will directly compute the visual footprint of the images. This is the most accurate method to determine the visual footprint but it may be very time consuming.

The laser point detection and visual footprint calculation can be requested for a whole volume in the volume overview. Just open the laser point tab in the sidebar on the left (), enter the distance of the laser points in centimetre and submit your request.

Depending on the size of your volume the automatic laser point detection may take some time. You can check the progress using the "detected laser points" filter of the volume overview. This will show you all images where the automatic laser point detection was successful. You can view the detailed results for an individual image on the image information page (). Here you can also (re-)submit the laser point detection for an individual image.

If you choose to detect laser points automatically, make sure you check the results before further processing your data. The easiest way is to apply the "detected laser points" filter in the volume overview and then cycle through all images that contain automatically detected laser points using the annotation tool. Detected laser points will be displayed as small circles on the image. If the detected laser points were not correct for an image, annotate them manually with the "Laser Point" label and resubmit the laser point detection for the image.

References

  1. Schoening Timm, Kuhn Thomas, Bergmann Melanie, Nattkemper Tim W. (2015) DELPHI—fast and adaptive computational laser point detection and visual footprint quantification for arbitrary underwater image collections. Front. Mar. Sci. 2:20. doi: 10.3389/fmars.2015.00020