DOI: 10.1016/j.jag.2016.04.005
Scopus记录号: 2-s2.0-84997523905
论文题名: Comparison of sampling strategies for object-based classification of urban vegetation from Very High Resolution satellite images
作者: Rougier S ; , Puissant A ; , Stumpf A ; , Lachiche N
刊名: International Journal of Applied Earth Observation and Geoinformation
ISSN: 15698432
出版年: 2016
卷: 51 起始页码: 60
结束页码: 73
语种: 英语
英文关键词: Active learning
; Object-based classification
; Random forest
; Sampling strategies evaluation
; Urban vegetation mapping
; VHR satellite images
英文摘要: Vegetation monitoring is becoming a major issue in the urban environment due to the services they procure and necessitates an accurate and up to date mapping. Very High Resolution satellite images enable a detailed mapping of the urban tree and herbaceous vegetation. Several supervised classifications with statistical learning techniques have provided good results for the detection of urban vegetation but necessitate a large amount of training data. In this context, this study proposes to investigate the performances of different sampling strategies in order to reduce the number of examples needed. Two windows based active learning algorithms from state-of-art are compared to a classical stratified random sampling and a third combining active learning and stratified strategies is proposed. The efficiency of these strategies is evaluated on two medium size French cities, Strasbourg and Rennes, associated to different datasets. Results demonstrate that classical stratified random sampling can in some cases be just as effective as active learning methods and that it should be used more frequently to evaluate new active learning methods. Moreover, the active learning strategies proposed in this work enables to reduce the computational runtime by selecting multiple windows at each iteration without increasing the number of windows needed. © 2016 Elsevier B.V. Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/80066
Appears in Collections: 气候变化事实与影响
There are no files associated with this item.
作者单位: Laboratoire Image, Ville, Environnement, LIVE, Université de Strasbourg, UMR 7362 CNRS, France; Institut de Physique du Globe de Strasbourg, IPGS, Université de Strasbourg, UMR 7516 CNRS, France; Laboratoire des Sciences de l'Ingénieur, de l'Informatique et de l'Imagerie, ICUBE, Université de Strasbourg, UMR 7357, France
Recommended Citation:
Rougier S,, Puissant A,, Stumpf A,et al. Comparison of sampling strategies for object-based classification of urban vegetation from Very High Resolution satellite images[J]. International Journal of Applied Earth Observation and Geoinformation,2016-01-01,51