Deep Semantic Model Fusion for Ancient Agricultural Terrace Detection

TL;DR

This paper introduces a deep semantic model fusion approach combining DeepLabv3+ and UNet with EfficientNet backbones to automatically detect ancient agricultural terraces from aerial and LiDAR data, winning an international challenge.

Contribution

It presents a novel fusion method of two deep segmentation models for archaeological landscape detection using aerial and LiDAR data.

Findings

Achieved first place in the International AI Archaeology Challenge.

Demonstrated effective segmentation of ancient terraces and walls.

Provided open-source code for the proposed method.

Abstract

Discovering ancient agricultural terraces in desert regions is important for the monitoring of long-term climate changes on the Earth's surface. However, traditional ground surveys are both costly and limited in scale. With the increasing accessibility of aerial and satellite data, machine learning techniques bear large potential for the automatic detection and recognition of archaeological landscapes. In this paper, we propose a deep semantic model fusion method for ancient agricultural terrace detection. The input data includes aerial images and LiDAR generated terrain features in the Negev desert. Two deep semantic segmentation models, namely DeepLabv3+ and UNet, with EfficientNet backbone, are trained and fused to provide segmentation maps of ancient terraces and walls. The proposed method won the first prize in the International AI Archaeology Challenge. Codes are available at https://github.com/wangyi111/international-archaeology-ai-challenge.