Semantic Segmentation of Airborne LiDAR Data in Maya Archaeology

作     者：Bundzel, Marek Jascur, Miroslav Kovac, Milan Lieskovsky, Tibor Sincak, Peter Tkacik, Tomas 

作者机构：Tech Univ Kosice Fac Elect Engn & Informat Dept Cybernet & Artificial Intelligence Letna 9 Kosice 04200 Slovakia Comenius Univ Fac Arts Ctr Mesoamer Studies Gondova 2 Bratislava 81102 Slovakia Slovak Univ Technol Bratislava Fac Civil Engn Dept Theoret Geodesy Radlinskeho 11 Bratislava 81005 Slovakia 

出 版 物：《REMOTE SENSING》 (遥感)

年 卷 期：2020年第12卷第22期

页      面：3685-3685页

核心收录：

学科分类：0830[工学-环境科学与工程（可授工学、理学、农学学位）] 1002[医学-临床医学] 070801[理学-固体地球物理学] 07[理学] 08[工学] 0708[理学-地球物理学] 0816[工学-测绘科学与技术] 

基　　金：Slovak Research and Development Agency [APVV-17-0648] Scientific Grant Agency [VEGA 1/0858/17] AI4EU-A European AI On Demand Platform and Ecosystem [H2020-825619] 

主　　题：LiDAR Maya archaeology convolutional neural network semantic segmentation decision support U-Net Mask R-CNN 

摘      要：Airborne LiDAR produced large amounts of data for archaeological research over the past decade. Labeling this type of archaeological data is a tedious process. We used a data set from Pacunam LiDAR Initiative survey of lowland Maya region in Guatemala. The data set contains ancient Maya structures that were manually labeled, and ground verified to a large extent. We have built and compared two deep learning-based models, U-Net and Mask R-CNN, for semantic segmentation. The segmentation models were used in two tasks: identification of areas of ancient construction activity, and identification of the remnants of ancient Maya buildings. The U-Net based model performed better in both tasks and was capable of correctly identifying 60-66% of all objects, and 74-81% of medium sized objects. The quality of the resulting prediction was evaluated using a variety of quantifiers. Furthermore, we discuss the problems of re-purposing the archaeological style labeling for production of valid machine learning training sets. Ultimately, we outline the value of these models for archaeological research and present the road map to produce a useful decision support system for recognition of ancient objects in LiDAR data.