从高分辨率无人机图像中检测掉落的原木

IF 1.5 4区 农林科学 Q2 FORESTRY New Zealand Journal of Forestry Science Pub Date : 2019-03-03 DOI:10.33494/NZJFS492019X26X
D. Panagiotidis, Azadeh Abdollahnejad, P. Surový, Karel Kuželka
{"title":"从高分辨率无人机图像中检测掉落的原木","authors":"D. Panagiotidis, Azadeh Abdollahnejad, P. Surový, Karel Kuželka","doi":"10.33494/NZJFS492019X26X","DOIUrl":null,"url":null,"abstract":"Background: High-resolution images from unmanned aerial vehicles (UAVs) can be used to describe the state of forests at regular time periods in a cost-effective manner. The purpose of this study was to assess the performance of a line template matching algorithm, the Hough transformation, for detecting fallen logs from UAV-based high-resolution RGB images. The suggested methodology does not aim to replace any known aerial method for log detection, rather it is more oriented to the detection of fallen logs in open forest stands with a high percentage of log visibility and straightness. \nMethods: This study describes a line template matching algorithm that can be used for the detection of fallen logs in an automated process. The detection technique was based on object-based image analysis, using both pixel-based and shape descriptors. To determine the actual number of fallen logs, and to compare with the ones predicted by the algorithm, manual visual assessment was used based on six high-resolution orthorectified images. To evaluate if a line matched, we used a voting scheme. The total number of detected fallen logs compared with the actual number of fallen logs based on several accuracy metrics. To evaluate predictive models we tested the cross-validation mean error. Finally, to test how close our results were to chance, we used the Cohen`s Kappa coefficient. \nResults: The detection algorithm found 136 linear objects, of which 92 of them were detected as fallen logs. From the 92 detected fallen logs, 86 were correctly predicted by the algorithm and 24 were falsely detected as fallen logs. The calculated amount of observed agreement was equal to 0.78, whereas the expected agreement by chance was 0.61. Finally, the kappa statistic was 0.44. \nConclusions: Our methodology had high reliability for detecting fallen logs based on total user‘s accuracy (94.9%), whereas a Kappa of 0.44 indicated there was good agreement between the observed and predicted values. Also, the cross-validation analysis denoted the efficiency of the proposed method with an average error of 16%.","PeriodicalId":19172,"journal":{"name":"New Zealand Journal of Forestry Science","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2019-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"14","resultStr":"{\"title\":\"Detection of fallen logs from high-resolution UAV images\",\"authors\":\"D. Panagiotidis, Azadeh Abdollahnejad, P. Surový, Karel Kuželka\",\"doi\":\"10.33494/NZJFS492019X26X\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Background: High-resolution images from unmanned aerial vehicles (UAVs) can be used to describe the state of forests at regular time periods in a cost-effective manner. The purpose of this study was to assess the performance of a line template matching algorithm, the Hough transformation, for detecting fallen logs from UAV-based high-resolution RGB images. The suggested methodology does not aim to replace any known aerial method for log detection, rather it is more oriented to the detection of fallen logs in open forest stands with a high percentage of log visibility and straightness. \\nMethods: This study describes a line template matching algorithm that can be used for the detection of fallen logs in an automated process. The detection technique was based on object-based image analysis, using both pixel-based and shape descriptors. To determine the actual number of fallen logs, and to compare with the ones predicted by the algorithm, manual visual assessment was used based on six high-resolution orthorectified images. To evaluate if a line matched, we used a voting scheme. The total number of detected fallen logs compared with the actual number of fallen logs based on several accuracy metrics. To evaluate predictive models we tested the cross-validation mean error. Finally, to test how close our results were to chance, we used the Cohen`s Kappa coefficient. \\nResults: The detection algorithm found 136 linear objects, of which 92 of them were detected as fallen logs. From the 92 detected fallen logs, 86 were correctly predicted by the algorithm and 24 were falsely detected as fallen logs. The calculated amount of observed agreement was equal to 0.78, whereas the expected agreement by chance was 0.61. Finally, the kappa statistic was 0.44. \\nConclusions: Our methodology had high reliability for detecting fallen logs based on total user‘s accuracy (94.9%), whereas a Kappa of 0.44 indicated there was good agreement between the observed and predicted values. Also, the cross-validation analysis denoted the efficiency of the proposed method with an average error of 16%.\",\"PeriodicalId\":19172,\"journal\":{\"name\":\"New Zealand Journal of Forestry Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2019-03-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"14\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"New Zealand Journal of Forestry Science\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.33494/NZJFS492019X26X\",\"RegionNum\":4,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"FORESTRY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"New Zealand Journal of Forestry Science","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.33494/NZJFS492019X26X","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"FORESTRY","Score":null,"Total":0}
引用次数: 14

摘要

背景:无人驾驶飞行器(uav)的高分辨率图像可用于以经济有效的方式描述定期的森林状况。本研究的目的是评估线模板匹配算法(霍夫变换)的性能,该算法用于从基于无人机的高分辨率RGB图像中检测掉落的原木。所建议的方法并不旨在取代任何已知的木材检测的航空方法,而是更倾向于在原木可见性和直线度高的开放林分中检测倒下的原木。方法:本研究描述了一种线模板匹配算法,该算法可用于自动化过程中原木掉落的检测。检测技术基于基于物体的图像分析,同时使用基于像素和形状描述符。为了确定实际倒下的原木数量,并与算法预测的数量进行比较,基于6张高分辨率正射影像进行了人工视觉评估。为了评估一行是否匹配,我们使用了投票方案。将检测到的掉落日志总数与基于几个准确性指标的实际掉落日志数量进行比较。为了评估预测模型,我们检验了交叉验证的平均误差。最后,为了测试我们的结果与概率的接近程度,我们使用了科恩Kappa系数。结果:检测算法发现了136个线性物体,其中92个被检测为掉落的原木。在92个检测到的掉落日志中,86个被算法正确预测,24个被错误检测为掉落日志。观察到的一致性的计算量等于0.78,而偶然的期望一致性为0.61。最后kappa统计量为0.44。结论:我们的方法在检测掉落的原木方面具有很高的可靠性,基于用户的总准确率(94.9%),而Kappa为0.44表明观测值和预测值之间有很好的一致性。交叉验证分析表明该方法的有效性,平均误差为16%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Detection of fallen logs from high-resolution UAV images
Background: High-resolution images from unmanned aerial vehicles (UAVs) can be used to describe the state of forests at regular time periods in a cost-effective manner. The purpose of this study was to assess the performance of a line template matching algorithm, the Hough transformation, for detecting fallen logs from UAV-based high-resolution RGB images. The suggested methodology does not aim to replace any known aerial method for log detection, rather it is more oriented to the detection of fallen logs in open forest stands with a high percentage of log visibility and straightness. Methods: This study describes a line template matching algorithm that can be used for the detection of fallen logs in an automated process. The detection technique was based on object-based image analysis, using both pixel-based and shape descriptors. To determine the actual number of fallen logs, and to compare with the ones predicted by the algorithm, manual visual assessment was used based on six high-resolution orthorectified images. To evaluate if a line matched, we used a voting scheme. The total number of detected fallen logs compared with the actual number of fallen logs based on several accuracy metrics. To evaluate predictive models we tested the cross-validation mean error. Finally, to test how close our results were to chance, we used the Cohen`s Kappa coefficient. Results: The detection algorithm found 136 linear objects, of which 92 of them were detected as fallen logs. From the 92 detected fallen logs, 86 were correctly predicted by the algorithm and 24 were falsely detected as fallen logs. The calculated amount of observed agreement was equal to 0.78, whereas the expected agreement by chance was 0.61. Finally, the kappa statistic was 0.44. Conclusions: Our methodology had high reliability for detecting fallen logs based on total user‘s accuracy (94.9%), whereas a Kappa of 0.44 indicated there was good agreement between the observed and predicted values. Also, the cross-validation analysis denoted the efficiency of the proposed method with an average error of 16%.
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
CiteScore
2.20
自引率
13.30%
发文量
20
审稿时长
39 weeks
期刊介绍: The New Zealand Journal of Forestry Science is an international journal covering the breadth of forestry science. Planted forests are a particular focus but manuscripts on a wide range of forestry topics will also be considered. The journal''s scope covers forestry species, which are those capable of reaching at least five metres in height at maturity in the place they are located, but not grown or managed primarily for fruit or nut production.
期刊最新文献
Climate influence seed production in managed and unmanaged Nothofagus pumilio forests of Southern Patagonia Assessing the impacts of experimental mid-rotation forest fertiliser treatments on water quality Mid-term results and prospects for irregular shelterwood systems in hardwood-dominated temperate rainforests in Chile Use of nitrogen-fixing plants to improve planted forest soil fertility and productivity in New Zealand: A review Diversity and growth patterns of woody species in the Mediterranean Coastal range of Chile: A case study in Altos de Cantillana
×
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