Nilgai管理中使用野生动物特定深度学习的自动相机陷阱分类

IF 0.9 4区 环境科学与生态学 Q4 BIODIVERSITY CONSERVATION
Matthew Kutugata, Jeremy A. Baumgardt, J. Goolsby, A. Racelis
{"title":"Nilgai管理中使用野生动物特定深度学习的自动相机陷阱分类","authors":"Matthew Kutugata, Jeremy A. Baumgardt, J. Goolsby, A. Racelis","doi":"10.3996/jfwm-20-076","DOIUrl":null,"url":null,"abstract":"\n Camera traps provide a low-cost approach to collect data and monitor wildlife across large scales but hand-labeling images at a rate that outpaces accumulation is difficult. Deep learning, a subdiscipline of machine learning and computer science, can address the issue of automatically classifying camera-trap images with a high degree of accuracy. This technique, however, may be less accessible to ecologists or small-scale conservation projects, and has serious limitations. In this study, we trained a simple deep learning model using a dataset of 120,000 images to identify the presence of nilgai Boselaphus tragocamelus, a regionally specific nonnative game animal, in camera-trap images with an overall accuracy of 97%. We trained a second model to identify 20 groups of animals and one group of images without any animals present, labeled as “none,” with an accuracy of 89%. Lastly, we tested the multigroup model on images collected of similar species, but in the southwestern United States, resulting in significantly lower precision and recall for each group. This study highlights the potential of deep learning for automating camera-trap image processing workflows, provides a brief overview of image-based deep learning, and discusses the often-understated limitations and methodological considerations in the context of wildlife conservation and species monitoring.","PeriodicalId":49036,"journal":{"name":"Journal of Fish and Wildlife Management","volume":" ","pages":""},"PeriodicalIF":0.9000,"publicationDate":"2021-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Automatic Camera-Trap Classification Using Wildlife-Specific Deep Learning in Nilgai Management\",\"authors\":\"Matthew Kutugata, Jeremy A. Baumgardt, J. Goolsby, A. Racelis\",\"doi\":\"10.3996/jfwm-20-076\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n Camera traps provide a low-cost approach to collect data and monitor wildlife across large scales but hand-labeling images at a rate that outpaces accumulation is difficult. Deep learning, a subdiscipline of machine learning and computer science, can address the issue of automatically classifying camera-trap images with a high degree of accuracy. This technique, however, may be less accessible to ecologists or small-scale conservation projects, and has serious limitations. In this study, we trained a simple deep learning model using a dataset of 120,000 images to identify the presence of nilgai Boselaphus tragocamelus, a regionally specific nonnative game animal, in camera-trap images with an overall accuracy of 97%. We trained a second model to identify 20 groups of animals and one group of images without any animals present, labeled as “none,” with an accuracy of 89%. Lastly, we tested the multigroup model on images collected of similar species, but in the southwestern United States, resulting in significantly lower precision and recall for each group. This study highlights the potential of deep learning for automating camera-trap image processing workflows, provides a brief overview of image-based deep learning, and discusses the often-understated limitations and methodological considerations in the context of wildlife conservation and species monitoring.\",\"PeriodicalId\":49036,\"journal\":{\"name\":\"Journal of Fish and Wildlife Management\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.9000,\"publicationDate\":\"2021-07-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Fish and Wildlife Management\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://doi.org/10.3996/jfwm-20-076\",\"RegionNum\":4,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"BIODIVERSITY CONSERVATION\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Fish and Wildlife Management","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.3996/jfwm-20-076","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"BIODIVERSITY CONSERVATION","Score":null,"Total":0}
引用次数: 4

摘要

相机陷阱提供了一种低成本的方法来收集数据并大规模监测野生动物,但很难以超过积累的速度手动标记图像。深度学习是机器学习和计算机科学的一个分支学科,可以高精度地解决相机陷阱图像的自动分类问题。然而,生态学家或小规模保护项目可能不太容易使用这种技术,并且存在严重的局限性。在这项研究中,我们使用120000张图像的数据集训练了一个简单的深度学习模型,以识别相机陷阱图像中是否存在nilgai Boselaphus tragocamelus,这是一种特定于地区的非本地狩猎动物,总体准确率为97%。我们训练了第二个模型来识别20组动物和一组没有任何动物的图像,标记为“无”,准确率为89%。最后,我们在美国西南部收集的类似物种的图像上测试了多组模型,导致每组的准确率和召回率显著降低。这项研究强调了深度学习在自动相机陷阱图像处理工作流程中的潜力,简要概述了基于图像的深度学习,并讨论了野生动物保护和物种监测中经常被低估的局限性和方法上的考虑。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Automatic Camera-Trap Classification Using Wildlife-Specific Deep Learning in Nilgai Management
Camera traps provide a low-cost approach to collect data and monitor wildlife across large scales but hand-labeling images at a rate that outpaces accumulation is difficult. Deep learning, a subdiscipline of machine learning and computer science, can address the issue of automatically classifying camera-trap images with a high degree of accuracy. This technique, however, may be less accessible to ecologists or small-scale conservation projects, and has serious limitations. In this study, we trained a simple deep learning model using a dataset of 120,000 images to identify the presence of nilgai Boselaphus tragocamelus, a regionally specific nonnative game animal, in camera-trap images with an overall accuracy of 97%. We trained a second model to identify 20 groups of animals and one group of images without any animals present, labeled as “none,” with an accuracy of 89%. Lastly, we tested the multigroup model on images collected of similar species, but in the southwestern United States, resulting in significantly lower precision and recall for each group. This study highlights the potential of deep learning for automating camera-trap image processing workflows, provides a brief overview of image-based deep learning, and discusses the often-understated limitations and methodological considerations in the context of wildlife conservation and species monitoring.
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 Fish and Wildlife Management
Journal of Fish and Wildlife Management BIODIVERSITY CONSERVATION-ECOLOGY
CiteScore
1.60
自引率
0.00%
发文量
43
审稿时长
>12 weeks
期刊介绍: Journal of Fish and Wildlife Management encourages submission of original, high quality, English-language scientific papers on the practical application and integration of science to conservation and management of native North American fish, wildlife, plants and their habitats in the following categories: Articles, Notes, Surveys and Issues and Perspectives. Papers that do not relate directly to native North American fish, wildlife plants or their habitats may be considered if they highlight species that are closely related to, or conservation issues that are germane to, those in North America.
×
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