利用时间序列卫星图像和改进的深度学习模型检测泰国东北部的淤地物体

IF 2.6 1区 地球科学 Q1 ANTHROPOLOGY
{"title":"利用时间序列卫星图像和改进的深度学习模型检测泰国东北部的淤地物体","authors":"","doi":"10.1016/j.jas.2024.106070","DOIUrl":null,"url":null,"abstract":"<div><p>Moated sites are crucial for revealing the formation of early civilizations and societies in Southeast Asia, and a significant amount of effort has been expended in investigating their distribution. This work is the first application of deep learning object detection methods to identify moated sites from time series satellite images. We presented multi-information fusion data (N-RGB) based on the fusion of multispectral and vegetation indices from Sentinel-2 time series imagery, generated a dataset of moated sites via the data augmentation method, and improved the YOLOv5s model by adding bidirectional feature pyramid network (BiFPN) structures for automatically identifying moated sites. <strong>The results</strong> indicate that the model trained with time series N-RGB data improves precision, recall, and mAP by more than 20.0% compared with single image data. The improved model was able to enhance the identification of small, moated sites and achieved 100% detection in a test of 100 moated sites. <strong>Ultimately</strong>, 629 targets were detected in northeast Thailand, with a false-negative rate of less than 3%, and 116 probable sites were identified. Among these, 6 probable sites were highly likely to be moated sites, as visually verified by high-resolution GEE imagery. <strong>In addition</strong>, among the targets automatically detected in other regions of continental Southeast Asia, the 5, 3, 2, 1, and 7 most probable sites were identified in Cambodia, Myanmar, Laos, Vietnam and other regions of Thailand, respectively. <strong>In summary</strong>, our approach enables the automatic detection of exposed and visible moated sites from satellite imagery, and could improve site discovery and documentation capabilities, opening new perspectives in larger geographic site units and even in civilization surveys.</p></div>","PeriodicalId":50254,"journal":{"name":"Journal of Archaeological Science","volume":null,"pages":null},"PeriodicalIF":2.6000,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Moated site object detection using time series satellite imagery and an improved deep learning model in northeast Thailand\",\"authors\":\"\",\"doi\":\"10.1016/j.jas.2024.106070\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Moated sites are crucial for revealing the formation of early civilizations and societies in Southeast Asia, and a significant amount of effort has been expended in investigating their distribution. This work is the first application of deep learning object detection methods to identify moated sites from time series satellite images. We presented multi-information fusion data (N-RGB) based on the fusion of multispectral and vegetation indices from Sentinel-2 time series imagery, generated a dataset of moated sites via the data augmentation method, and improved the YOLOv5s model by adding bidirectional feature pyramid network (BiFPN) structures for automatically identifying moated sites. <strong>The results</strong> indicate that the model trained with time series N-RGB data improves precision, recall, and mAP by more than 20.0% compared with single image data. The improved model was able to enhance the identification of small, moated sites and achieved 100% detection in a test of 100 moated sites. <strong>Ultimately</strong>, 629 targets were detected in northeast Thailand, with a false-negative rate of less than 3%, and 116 probable sites were identified. Among these, 6 probable sites were highly likely to be moated sites, as visually verified by high-resolution GEE imagery. <strong>In addition</strong>, among the targets automatically detected in other regions of continental Southeast Asia, the 5, 3, 2, 1, and 7 most probable sites were identified in Cambodia, Myanmar, Laos, Vietnam and other regions of Thailand, respectively. <strong>In summary</strong>, our approach enables the automatic detection of exposed and visible moated sites from satellite imagery, and could improve site discovery and documentation capabilities, opening new perspectives in larger geographic site units and even in civilization surveys.</p></div>\",\"PeriodicalId\":50254,\"journal\":{\"name\":\"Journal of Archaeological Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2024-09-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Archaeological Science\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0305440324001389\",\"RegionNum\":1,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ANTHROPOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Archaeological Science","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0305440324001389","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ANTHROPOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

有护城河的遗址对于揭示东南亚早期文明和社会的形成至关重要,因此人们花费了大量精力调查这些遗址的分布情况。这项工作是首次应用深度学习对象检测方法从时间序列卫星图像中识别护城河遗址。我们提出了基于哨兵-2 时间序列图像的多光谱和植被指数融合的多信息融合数据(N-RGB),通过数据增强方法生成了护城河遗址数据集,并通过添加双向特征金字塔网络(BiFPN)结构改进了 YOLOv5s 模型,用于自动识别护城河遗址。结果表明,与单幅图像数据相比,使用时间序列 N-RGB 数据训练的模型在精确度、召回率和 mAP 方面提高了 20.0% 以上。改进后的模型能够提高对小型护城河遗址的识别率,并在 100 个护城河遗址的测试中实现了 100% 的检测率。最终,在泰国东北部检测到 629 个目标,假阴性率低于 3%,并确定了 116 个可能的遗址。其中,经高分辨率 GEE 图像直观验证,6 个可能的遗址极有可能是护城河遗址。此外,在东南亚大陆其他地区自动探测到的目标中,柬埔寨、缅甸、老挝、越南和泰国其他地区分别发现了 5、3、2、1 和 7 个最有可能的遗址。总之,我们的方法能够从卫星图像中自动检测暴露和可见的护城河遗址,并能提高遗址发现和记录能力,为更大的遗址地理单元甚至文明调查开辟新的视角。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Moated site object detection using time series satellite imagery and an improved deep learning model in northeast Thailand

Moated sites are crucial for revealing the formation of early civilizations and societies in Southeast Asia, and a significant amount of effort has been expended in investigating their distribution. This work is the first application of deep learning object detection methods to identify moated sites from time series satellite images. We presented multi-information fusion data (N-RGB) based on the fusion of multispectral and vegetation indices from Sentinel-2 time series imagery, generated a dataset of moated sites via the data augmentation method, and improved the YOLOv5s model by adding bidirectional feature pyramid network (BiFPN) structures for automatically identifying moated sites. The results indicate that the model trained with time series N-RGB data improves precision, recall, and mAP by more than 20.0% compared with single image data. The improved model was able to enhance the identification of small, moated sites and achieved 100% detection in a test of 100 moated sites. Ultimately, 629 targets were detected in northeast Thailand, with a false-negative rate of less than 3%, and 116 probable sites were identified. Among these, 6 probable sites were highly likely to be moated sites, as visually verified by high-resolution GEE imagery. In addition, among the targets automatically detected in other regions of continental Southeast Asia, the 5, 3, 2, 1, and 7 most probable sites were identified in Cambodia, Myanmar, Laos, Vietnam and other regions of Thailand, respectively. In summary, our approach enables the automatic detection of exposed and visible moated sites from satellite imagery, and could improve site discovery and documentation capabilities, opening new perspectives in larger geographic site units and even in civilization surveys.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Archaeological Science
Journal of Archaeological Science 地学-地球科学综合
CiteScore
6.10
自引率
7.10%
发文量
112
审稿时长
49 days
期刊介绍: The Journal of Archaeological Science is aimed at archaeologists and scientists with particular interests in advancing the development and application of scientific techniques and methodologies to all areas of archaeology. This established monthly journal publishes focus articles, original research papers and major review articles, of wide archaeological significance. The journal provides an international forum for archaeologists and scientists from widely different scientific backgrounds who share a common interest in developing and applying scientific methods to inform major debates through improving the quality and reliability of scientific information derived from archaeological research.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信