Abstract Title

Mapping Dirt Roads from Imagery Using Deep Learning

Additional Funding Sources

The project described was supported by the USDA Forest Service - Boise National Forest, as well as an Institutional Development Award (IDeA) from the National Institute of General Medical Sciences of the National Institutes of Health under Grant #P20GM103408.

Abstract

Throughout the past couple of years, the NNU FireMAP research project in collaboration with the Boise National Forest has been obtaining a substantial amount of aerial imagery using a small unmanned aircraft system. The majority of the imagery gathered is of forests and post burn areas. A lot of this imagery contains certain archeological features, such as, hand stacks, dredge tailings, roads, and rail grades. These features can be quite tedious to find but can be very important to archaeology, as these features can often lead to the discovery of other archeological artifacts. The previous methods of finding these features was to walk through a suspected archaeological site hoping you happen upon an artifact or feature. The goal of this research project will be to construct a more dynamic approach to finding dirt roads. This goal will be achieved by using a mask region convolution neural network (Mask R-CNN) to find these features within hyperspatial aerial imagery acquired with a small unmanned aircraft system. The desired result of this program is to use the imagery to identify and map any dirt roads, giving a specific geo-referenced poly-line representing the located feature.

Comments

T80

This document is currently not available here.

COinS
 

Mapping Dirt Roads from Imagery Using Deep Learning

Throughout the past couple of years, the NNU FireMAP research project in collaboration with the Boise National Forest has been obtaining a substantial amount of aerial imagery using a small unmanned aircraft system. The majority of the imagery gathered is of forests and post burn areas. A lot of this imagery contains certain archeological features, such as, hand stacks, dredge tailings, roads, and rail grades. These features can be quite tedious to find but can be very important to archaeology, as these features can often lead to the discovery of other archeological artifacts. The previous methods of finding these features was to walk through a suspected archaeological site hoping you happen upon an artifact or feature. The goal of this research project will be to construct a more dynamic approach to finding dirt roads. This goal will be achieved by using a mask region convolution neural network (Mask R-CNN) to find these features within hyperspatial aerial imagery acquired with a small unmanned aircraft system. The desired result of this program is to use the imagery to identify and map any dirt roads, giving a specific geo-referenced poly-line representing the located feature.