An Optimal Retinanet Model For Automatic Satellite Image Based Missile Site Detection

IF 0.8 4区 工程技术 Q3 MULTIDISCIPLINARY SCIENCES
Ashwin Yadav, K. Jain, Akshay Pandey, Eshta Ranyal, Joydeep Majumdar
{"title":"An Optimal Retinanet Model For Automatic Satellite Image Based Missile Site Detection","authors":"Ashwin Yadav, K. Jain, Akshay Pandey, Eshta Ranyal, Joydeep Majumdar","doi":"10.14429/dsj.72.18215","DOIUrl":null,"url":null,"abstract":"Satellite image processing is a manually tedious job and offers scope for automation as part of the information extraction process from satellite images. The process of information extraction involves object detection and one of the challenges is ascertaining the minimum number of images required to train the deep learning model to achieve a certain minimum accuracy. To the best of the authors’ knowledge, work in missile site detection is relatively limited, with an existing exploration of the latest one-shot detection methods, such as RetinaNet, being absent. This work proposes an optimal deep learning model based on the RetinaNet framework and training on a minimal dataset. A comparative analysis with previous work paves the road for future research in one-shot methods and optimally trained models. As part of the study, the key findings are that an optimal training scheme based on a minimal training dataset is possible. This step enables a reduction in training time for the development of an optimal missile site detection model is concerned. One of the many techniques to determine the minimal number of training images required to train the object detection model is plotting the number of training images versus the mean average precision. The same is validated in our work. Further, a hybrid scheme based on the two-model concept is tested wherein one model prioritizes Recall while the other prioritizes Precision. Thus a combination of both models to detect a set of targets provides an optimal framework for object detection. Lastly, the study finds that the single-stage RetinaNet algorithm offers the advantage of balancing speed and accuracy over erstwhile two-stage and other single-stage methods.","PeriodicalId":11043,"journal":{"name":"Defence Science Journal","volume":" ","pages":""},"PeriodicalIF":0.8000,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Defence Science Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14429/dsj.72.18215","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

Satellite image processing is a manually tedious job and offers scope for automation as part of the information extraction process from satellite images. The process of information extraction involves object detection and one of the challenges is ascertaining the minimum number of images required to train the deep learning model to achieve a certain minimum accuracy. To the best of the authors’ knowledge, work in missile site detection is relatively limited, with an existing exploration of the latest one-shot detection methods, such as RetinaNet, being absent. This work proposes an optimal deep learning model based on the RetinaNet framework and training on a minimal dataset. A comparative analysis with previous work paves the road for future research in one-shot methods and optimally trained models. As part of the study, the key findings are that an optimal training scheme based on a minimal training dataset is possible. This step enables a reduction in training time for the development of an optimal missile site detection model is concerned. One of the many techniques to determine the minimal number of training images required to train the object detection model is plotting the number of training images versus the mean average precision. The same is validated in our work. Further, a hybrid scheme based on the two-model concept is tested wherein one model prioritizes Recall while the other prioritizes Precision. Thus a combination of both models to detect a set of targets provides an optimal framework for object detection. Lastly, the study finds that the single-stage RetinaNet algorithm offers the advantage of balancing speed and accuracy over erstwhile two-stage and other single-stage methods.
基于卫星图像的导弹阵地自动检测的最优retanet模型
卫星图像处理是一项手工繁琐的工作,作为卫星图像信息提取过程的一部分,它为自动化提供了空间。信息提取过程涉及目标检测,其中一个挑战是确定训练深度学习模型所需的最小图像数量,以达到一定的最小精度。据作者所知,导弹阵地探测方面的工作相对有限,缺乏对最新的一次性探测方法(如RetinaNet)的现有探索。本文提出了一种基于retanet框架的最优深度学习模型,并在最小数据集上进行训练。通过与以往工作的比较分析,为未来的一次性方法和最优训练模型的研究铺平了道路。作为研究的一部分,关键发现是基于最小训练数据集的最佳训练方案是可能的。这一步骤能够减少训练时间,为研制一种最优的导弹阵地探测模型所关注。确定训练目标检测模型所需的最小训练图像数量的许多技术之一是绘制训练图像数量与平均精度的关系。我们的工作也证实了这一点。此外,测试了基于双模型概念的混合方案,其中一个模型优先考虑召回率,而另一个模型优先考虑精度。因此,结合两种模型来检测一组目标,为目标检测提供了一个最佳框架。最后,研究发现单阶段retanet算法比以往的两阶段和其他单阶段算法具有平衡速度和精度的优势。
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 求助全文
来源期刊
Defence Science Journal
Defence Science Journal 综合性期刊-综合性期刊
CiteScore
1.80
自引率
11.10%
发文量
69
审稿时长
7.5 months
期刊介绍: Defence Science Journal is a peer-reviewed, multidisciplinary research journal in the area of defence science and technology. Journal feature recent progresses made in the field of defence/military support system and new findings/breakthroughs, etc. Major subject fields covered include: aeronautics, armaments, combat vehicles and engineering, biomedical sciences, computer sciences, electronics, material sciences, missiles, naval systems, etc.
×
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