Deep learning-based vehicle detection from orthophoto and spatial accuracy analysis

IF 3.1 Q2 ENGINEERING, GEOLOGICAL International Journal of Engineering and Geosciences Pub Date : 2022-06-24 DOI:10.26833/ijeg.1080624
Muhammed Yahya Bıyık, M. E. Atik, Z. Duran
{"title":"Deep learning-based vehicle detection from orthophoto and spatial accuracy analysis","authors":"Muhammed Yahya Bıyık, M. E. Atik, Z. Duran","doi":"10.26833/ijeg.1080624","DOIUrl":null,"url":null,"abstract":"Deep Learning algorithms are used by many different disciplines for various purposes, thanks to their ever-developing data processing skills. Convolutional neural network (CNN) are generally developed and used for this integration purpose. On the other hand, the widespread usage of Unmanned Aerial Vehicles (UAV) enables the collection of aerial photographs for Photogrammetric studies. In this study, these two fields were brought together and it was aimed to find the equivalents of the objects detected from the UAV images using deep learning in the global coordinate system and to evaluate their accuracy over these values. For these reasons, v3 and v4 versions of the YOLO algorithm, which prioritizes detecting the midpoint of the detected object, were trained in Google Colab’s virtual machine environment using the prepared data set. The coordinate values read from the orthophoto and the coordinate values of the midpoints of the objects, which were derived according to the estimations made by the YOLO-v3 and YOLO-v4 models, were compared and their spatial accuracy was calculated. Accuracy of 16.8 cm was obtained with the YOLO-v3 and 15.5 cm with the YOLO-v4.","PeriodicalId":42633,"journal":{"name":"International Journal of Engineering and Geosciences","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Engineering and Geosciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.26833/ijeg.1080624","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, GEOLOGICAL","Score":null,"Total":0}
引用次数: 1

Abstract

Deep Learning algorithms are used by many different disciplines for various purposes, thanks to their ever-developing data processing skills. Convolutional neural network (CNN) are generally developed and used for this integration purpose. On the other hand, the widespread usage of Unmanned Aerial Vehicles (UAV) enables the collection of aerial photographs for Photogrammetric studies. In this study, these two fields were brought together and it was aimed to find the equivalents of the objects detected from the UAV images using deep learning in the global coordinate system and to evaluate their accuracy over these values. For these reasons, v3 and v4 versions of the YOLO algorithm, which prioritizes detecting the midpoint of the detected object, were trained in Google Colab’s virtual machine environment using the prepared data set. The coordinate values read from the orthophoto and the coordinate values of the midpoints of the objects, which were derived according to the estimations made by the YOLO-v3 and YOLO-v4 models, were compared and their spatial accuracy was calculated. Accuracy of 16.8 cm was obtained with the YOLO-v3 and 15.5 cm with the YOLO-v4.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于深度学习的正射影像车辆检测与空间精度分析
深度学习算法因其不断发展的数据处理技能而被许多不同学科用于各种目的。卷积神经网络(CNN)通常被开发并用于这种集成目的。另一方面,无人机的广泛使用使得能够收集用于摄影测量研究的航空照片。在这项研究中,这两个领域被结合在一起,目的是在全球坐标系中使用深度学习找到从无人机图像中检测到的物体的等效物,并评估其在这些值上的准确性。出于这些原因,YOLO算法的v3和v4版本优先检测检测到的对象的中点,使用准备好的数据集在Google Colab的虚拟机环境中进行了训练。比较从正射照片读取的坐标值和根据YOLO-v3和YOLO-v4模型进行的估计导出的物体中点的坐标值,并计算它们的空间精度。YOLO-v3和YOLO-v4的精确度分别为16.8cm和15.5cm。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
4.00
自引率
0.00%
发文量
12
审稿时长
30 weeks
期刊最新文献
Registration of Interferometric DEM by Deep Artificial Neural Networks Using GPS Control Points’ Coordinates as Network Target Comparative Analysis of Non-Invasive Measurement Methods for Optimizing Architectural Documentation A benchmark dataset for deep learning-based airplane detection: HRPlanes Methodology of real-time 3D point cloud mapping with UAV lidar Proliferation of Dichotomy Urban Settlements Plight: Land Governance And Sustainable Built Environment In Tanzania
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1