Arid
DOI10.3390/s18020605
UAVs and Machine Learning Revolutionising Invasive Grass and Vegetation Surveys in Remote Arid Lands
Sandino, Juan1,2; Gonzalez, Felipe1,2; Mengersen, Kerrie3,4; Gaston, Kevin J.5
通讯作者Sandino, Juan
来源期刊SENSORS
ISSN1424-8220
出版年2018
卷号18期号:2
英文摘要

The monitoring of invasive grasses and vegetation in remote areas is challenging, costly, and on the ground sometimes dangerous. Satellite and manned aircraft surveys can assist but their use may be limited due to the ground sampling resolution or cloud cover. Straightforward and accurate surveillance methods are needed to quantify rates of grass invasion, offer appropriate vegetation tracking reports, and apply optimal control methods. This paper presents a pipeline process to detect and generate a pixel-wise segmentation of invasive grasses, using buffel grass (Cenchrus ciliaris) and spinifex (Triodia sp.) as examples. The process integrates unmanned aerial vehicles (UAVs) also commonly known as drones, high-resolution red, green, blue colour model (RGB) cameras, and a data processing approach based on machine learning algorithms. The methods are illustrated with data acquired in Cape Range National Park, Western Australia (WA), Australia, orthorectified in Agisoft Photoscan Pro, and processed in Python programming language, scikit-learn, and eXtreme Gradient Boosting (XGBoost) libraries. In total, 342,626 samples were extracted from the obtained data set and labelled into six classes. Segmentation results provided an individual detection rate of 97% for buffel grass and 96% for spinifex, with a global multiclass pixel-wise detection rate of 97%. Obtained results were robust against illumination changes, object rotation, occlusion, background cluttering, and floral density variation.


英文关键词biosecurity buffel grass Cenchrus ciliaris drones remote surveillance spinifex Triodia sp. unmanned aerial vehicles (UAV) vegetation assessments xgboost
类型Article
语种英语
国家Australia ; England
收录类别SCI-E
WOS记录号WOS:000427544000288
WOS关键词BUFFEL GRASS ; CENCHRUS-CILIARIS ; CENTRAL AUSTRALIA ; IMPACTS ; BIODIVERSITY ; IMAGERY ; FIRE
WOS类目Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS研究方向Chemistry ; Engineering ; Instruments & Instrumentation
资源类型期刊论文
条目标识符http://119.78.100.177/qdio/handle/2XILL650/213151
作者单位1.QUT, Inst Future Environm, 2 George St, Brisbane, Qld 4000, Australia;
2.QUT, Robot & Autonomous Syst, 2 George St, Brisbane, Qld 4000, Australia;
3.QUT, Sch Math Sci, 2 George St, Brisbane, Qld 4000, Australia;
4.QUT, ARC Ctr Excellence Math & Stat Frontiers ACEMS, 2 George St, Brisbane, Qld 4000, Australia;
5.Univ Exeter, Environm & Sustainabil Inst, Penryn TR10 9FE, Cornwall, England
推荐引用方式
GB/T 7714
Sandino, Juan,Gonzalez, Felipe,Mengersen, Kerrie,et al. UAVs and Machine Learning Revolutionising Invasive Grass and Vegetation Surveys in Remote Arid Lands[J],2018,18(2).
APA Sandino, Juan,Gonzalez, Felipe,Mengersen, Kerrie,&Gaston, Kevin J..(2018).UAVs and Machine Learning Revolutionising Invasive Grass and Vegetation Surveys in Remote Arid Lands.SENSORS,18(2).
MLA Sandino, Juan,et al."UAVs and Machine Learning Revolutionising Invasive Grass and Vegetation Surveys in Remote Arid Lands".SENSORS 18.2(2018).
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Sandino, Juan]的文章
[Gonzalez, Felipe]的文章
[Mengersen, Kerrie]的文章
百度学术
百度学术中相似的文章
[Sandino, Juan]的文章
[Gonzalez, Felipe]的文章
[Mengersen, Kerrie]的文章
必应学术
必应学术中相似的文章
[Sandino, Juan]的文章
[Gonzalez, Felipe]的文章
[Mengersen, Kerrie]的文章
相关权益政策
暂无数据
收藏/分享

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。