Quality report details

Hello All,

I am a new user of WebODM and I need a little bit of help to understand some parts of the Quality Report.
I am creating ortophotos of crops, and I am trying to process images with max. 0.5 GSD and I am trying to find the best settings for the image processing. I believe the built in Quality report can help me to do so.
Can someone explain to me what does the “Reconstructed Points (Sparse)” and “Dense” mean in the report? Is there a manual where I can look for this information?
If I understand that correctly the higher the percentage the better the outcome will be.
Is there a way to increase the percentage during processing or is it simply effected by the method of photography during a drone mission. (GSD, Overlaps, etc)?

Thank you in advance!

Gabor

1 Like

Welcome!

OpenSFM has a quick guide here:
https://opensfm.org/docs/quality_report.html

Pix4D’s documentation is pretty applicable as well:

The sparse points should be the tiepoints that are used to then do the full dense reconstruction. If you increase --feature-quality and then push up --min-num-features and/or --matcher-neighbors this should help increase the sparse point count a bit.

The dense count should be helped by --pc-quality and --pc-filter. You can try easing up the pc-filter by setting it to 5 or optionally disabling it entirely by setting it to 0.

2 Likes

Thank you so much! This is the document, that I was looking for!

2 Likes

We’re working on our own documentation here for other aspects, though I need to write up a detailed analysis of the Processing Report still :slight_smile:
docs.opendronemap.org

3 Likes

Hi Gabor,

As you may know, we can divide the initial stages into the following:

  • Feature extraction (find things to match)
  • Matching
  • Structure from Motion (including bundle adjustment)
  • Multi-view stereo

Sparse points are the 3D representation of the matches between photos from structure from motion.

Dense points are the ones extracted in the multi-view stereo stage, which uses filtered depth maps from the pairs of matched images to increase the density of points.

They are quantitative measures, but there may be better ways to discern improvements. Human visual acuity I find to be far more useful.

The other things to look at in the report are how even are the sparse points and are there important areas that are not well covered. This one is pretty even:
image

vs. this one which has no matches through the center (it’s a river, so this is understandable in this case):

It is useful to look at the survey data. How many images are available for the reconstruction at any given area. This is the same as the first dataset which has decent sparse matching, but as it is over a vegetated area, there are lots of occlusions. We like to see 4 or 5+ from all locations, but we have a fair amount of 2, 3, and missing coverage:

This doesn’t necessarily mean we have bad data, but it does mean that the data in the green areas will be much better than the data in other areas.

We can also look at the strength of the matching between images in Track Details, feature use across the image frame in Feature Details, and finally it’s useful to look at Camera Models Details and see whether we see a strong pattern in the camera model, which is not a good sign, or if it’s relatvely noise residuals which is a good sign – it means we probably got a representative self-calibration of the camera.

Looks like Saijin has you on the right track too. Cheers.

4 Likes

Thank you for the detailed explanation. Much appreciated!

2 Likes

Can you share the config settings you used that got you such a colorful survey data result? I always get red ones, and the last I heard it might be because of the matcher I use.

1 Like