Geomorphological Analysis Using Unpiloted Aircraft Systems, Structure from Motion, and Deep Learning. (arXiv:1909.12874v5 [cs.RO] UPDATED)

Geomorphological Analysis Using Unpiloted Aircraft Systems, Structure from Motion, and Deep Learning. (arXiv:1909.12874v5 [cs.RO] UPDATED)
<a href="http://arxiv.org/find/cs/1/au:+Chen_Z/0/1/0/all/0/1">Zhiang Chen</a>, <a href="http://arxiv.org/find/cs/1/au:+Scott_T/0/1/0/all/0/1">Tyler R. Scott</a>, <a href="http://arxiv.org/find/cs/1/au:+Bearman_S/0/1/0/all/0/1">Sarah Bearman</a>, <a href="http://arxiv.org/find/cs/1/au:+Anand_H/0/1/0/all/0/1">Harish Anand</a>, <a href="http://arxiv.org/find/cs/1/au:+Keating_D/0/1/0/all/0/1">Devin Keating</a>, <a href="http://arxiv.org/find/cs/1/au:+Scott_C/0/1/0/all/0/1">Chelsea Scott</a>, <a href="http://arxiv.org/find/cs/1/au:+Arrowsmith_J/0/1/0/all/0/1">J Ramon Arrowsmith</a>, <a href="http://arxiv.org/find/cs/1/au:+Das_J/0/1/0/all/0/1">Jnaneshwar Das</a>

We present a pipeline for geomorphological analysis that uses structure from
motion (SfM) and deep learning on close-range aerial imagery to estimate
spatial distributions of rock traits (size, roundness, and orientation) along a
tectonic fault scarp. The properties of the rocks on the fault scarp derive
from the combination of initial volcanic fracturing and subsequent tectonic and
geomorphic fracturing, and our pipeline allows scientists to leverage UAS-based
imagery to gain a better understanding of such surface processes. We start by
using SfM on aerial imagery to produce georeferenced orthomosaics and digital
elevation models (DEM). A human expert then annotates rocks on a set of image
tiles sampled from the orthomosaics, and these annotations are used to train a
deep neural network to detect and segment individual rocks in the entire site.
The extracted semantic information (rock masks) on large volumes of unlabeled,
high-resolution SfM products allows subsequent structural analysis and shape
descriptors to estimate rock size, roundness, and orientation. We present
results of two experiments conducted along a fault scarp in the Volcanic
Tablelands near Bishop, California. We conducted the first, proof-of-concept
experiment with a DJI Phantom 4 Pro equipped with an RGB camera and inspected
if elevation information assisted instance segmentation from RGB channels.
Rock-trait histograms along and across the fault scarp were obtained with the
neural network inference. In the second experiment, we deployed a hexrotor and
a multispectral camera to produce a DEM and five spectral orthomosaics in red,
green, blue, red edge, and near infrared. We focused on examining the
effectiveness of different combinations of input channels in instance
segmentation.

We present a pipeline for geomorphological analysis that uses structure from
motion (SfM) and deep learning on close-range aerial imagery to estimate
spatial distributions of rock traits (size, roundness, and orientation) along a
tectonic fault scarp. The properties of the rocks on the fault scarp derive
from the combination of initial volcanic fracturing and subsequent tectonic and
geomorphic fracturing, and our pipeline allows scientists to leverage UAS-based
imagery to gain a better understanding of such surface processes. We start by
using SfM on aerial imagery to produce georeferenced orthomosaics and digital
elevation models (DEM). A human expert then annotates rocks on a set of image
tiles sampled from the orthomosaics, and these annotations are used to train a
deep neural network to detect and segment individual rocks in the entire site.
The extracted semantic information (rock masks) on large volumes of unlabeled,
high-resolution SfM products allows subsequent structural analysis and shape
descriptors to estimate rock size, roundness, and orientation. We present
results of two experiments conducted along a fault scarp in the Volcanic
Tablelands near Bishop, California. We conducted the first, proof-of-concept
experiment with a DJI Phantom 4 Pro equipped with an RGB camera and inspected
if elevation information assisted instance segmentation from RGB channels.
Rock-trait histograms along and across the fault scarp were obtained with the
neural network inference. In the second experiment, we deployed a hexrotor and
a multispectral camera to produce a DEM and five spectral orthomosaics in red,
green, blue, red edge, and near infrared. We focused on examining the
effectiveness of different combinations of input channels in instance
segmentation.

http://arxiv.org/icons/sfx.gif