Segmentation & classification of petroglyphs

My purpose for learning, Deep Learning, is to ultimately record rock art, and then do analysis on the records.
The steps I Invision will be;

  1. Identify region of interest (ROI). By recognition of petroglyphs using a mobile net model on an AIY vision bonnet. (Google’s add on bonnot for raspberry pi camera, runs tensorflow models :disappointed:)

  2. Using bounding box, to aim “Tiny Lidar” to scan roi. (Petroglyphs can be hard to see visually)

  3. Uploading to a server with more GPU power, to perform instance segmentation.

  4. Classifying of styles.
    (GPS & geolocation info for view shed analysis) also included.

The last 20 minutes of course #7 with class activation maps, is as close as I’ve gotten so far,
I’m accumulating my dataset, to practice with the dog vs cats lessons.
I am also watching bits and pieces of course 2, lessons 13 & 14, just for entertainment really!
Of course mask-rcnn is the “state of the art” for instance segmentation. & pytorch models exist.

Zeppelzauer, M., Poier, G., Seidl, M., Reinbacher, C., Breiteneder, C., Bischof, H., Schulter, S., 2015, Interactive Segmentation of Rock-Art in High-Resolution 3D Reconstructions, Proceedings of the Conference on Digital Heritage 2015. Granada, Spain 10/2015.
is my starting point inspiration.

They used EDM enhanced deviation maps, to segment with supervision.

I also like the effect of the method from,
Automatic Color Image Segmentation Using a Square Elemental Region-Based Seeded Region Growing and Merging Method Hisashi Shimodaira

After attempting to label my Dataset, for pixelwise segmentation, I realized that would never do.
In images of “Pecked” rocks, I can’t distinguish between petroglyphs and ‘maybe petroglyphs’!
I want the neural network to be better at it than me.
So unsupervised learning seems to be the way to go!
And all I need to start is folders with names a-la the cats vs. Dogs.

A. Possible 2nd step will be some G.A.N and instance segmentation to follow.
(Because I still want bit mask of the pecking for classification.)

thanks for the encouragement!