Deep Learning Automatic Detection of the Wet/Dry Shoreline at Fish Pass, Texas

Abstract

Automatically detection the wet/dry shoreline would facilitates several applications in geological, and societal tasks such as biodiversity or beach management in coastal areas. High resolution remote imagery from UAVs simplifies detecting tiny wet/dry lines. Recently, deep learning models have shown much success compared to conventional image processing techniques for line/edge detection in terms of accuracy and automation. In this paper, an end-to-end deep learning model originated from Holistically-Nested Edge Detection (HED) model has been proposed to automatically detect the wet/dry shoreline in Fish Pass area, Texas, USA. The results shown 81% ODS (Optimal Dataset Scale), 100% OIS (per-Image best threshold), and 78.1% AP (Average Precision) score.