气候变化领域集成服务门户(CCPortal): Scale Sequence Joint Deep Learning (SS-JDL) for land use and land cover classification

CCPortal

DOI	10.1016/j.rse.2019.111593
	Scale Sequence Joint Deep Learning (SS-JDL) for land use and land cover classification
	Zhang C.; Harrison P.A.; Pan X.; Li H.; Sargent I.; Atkinson P.M.
发表日期	2020
ISSN	00344257
卷号	237
英文摘要	Choosing appropriate scales for remotely sensed image classification is extremely important yet still an open question in relation to deep convolutional neural networks (CNN), due to the impact of spatial scale (i.e., input patch size) on the recognition of ground objects. Currently, the optimal scale selection processes are extremely cumbersome and time-consuming requiring repetitive experiments involving trial-and-error procedures, which significantly reduce the practical utility of the corresponding classification methods. This issue is crucial when trying to classify large-scale land use (LU) and land cover (LC) jointly (Zhang et al., 2019). In this paper, a simple and parsimonious Scale Sequence Joint Deep Learning (SS-JDL) method is proposed for joint LU and LC classification, in which a sequence of scales is embedded in the iterative process of fitting the joint distribution implicit in the joint deep learning (JDL) method, thus, replacing the previous paradigm of scale selection. The sequence of scales, derived autonomously and used to define the CNN input patch sizes, provides consecutive information transmission from small-scale features to large-scale representations, and from simple LC states to complex LU characterisations. The effectiveness of the novel SS-JDL method was tested on aerial digital photography of three complex and heterogeneous landscapes, two in Southern England (Bournemouth and Southampton) and one in North West England (Manchester). Benchmark comparisons were provided in the form of a range of LU and LC methods, including the state-of-the-art joint deep learning (JDL) method. The experimental results demonstrated that the SS-JDL consistently outperformed all of the state-of-the-art baselines in terms of both LU and LC classification accuracies, as well as computational efficiency. The proposed SS-JDL method, therefore, represents a fast and effective implementation of the state-of-the-art JDL method. By creating a single, unifying joint distribution framework for classifying higher order feature representations, including LU, the SS-JDL method has the potential to transform the classification paradigm in remote sensing, and in machine learning more generally. © 2019 Elsevier Inc.
英文关键词	Convolutional neural network; Hierarchical representations; Joint classification; Multi-scale deep learning; Optimal scale selection
语种	英语
scopus关键词	Antennas; Complex networks; Computational efficiency; Convolution; Deep neural networks; Iterative methods; Land use; Neural networks; Remote sensing; Classification accuracy; Convolutional neural network; Heterogeneous landscapes; Hierarchical representation; Information transmission; Land-use and land cover classifications; Optimal scale; Trial-and-error procedures; Classification (of information); classification; digital photogrammetry; experimental study; hierarchical system; image classification; land cover; land use change; machine learning; remote sensing; Bournemouth [England]; England; Manchester [England]; Southampton [England]; United Kingdom
来源期刊	Remote Sensing of Environment
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/179523
作者单位	Lancaster Environment Centre, Lancaster University, Lancaster, LA1 4YQ, United Kingdom; Centre for Ecology & Hydrology, Library Avenue, Bailrigg, Lancaster, LA1 4AP, United Kingdom; School of Computer Technology and Engineering, Changchun Institute of Technology, Changchun, 130012, China; The Key Laboratory of Changbai Mountain Historical Culture and VR Technology Reconfiguration, Changchun Institute of Technology, Changchun, 130012, China; Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun, 130102, China; Ordnance Survey, Adanac Drive, Southampton, SO16 0AS, United Kingdom; Faculty of Science and Technology, Lancaster University, Lancaster, LA1 4YR, United Kingdom; School of Natural and Built Environment, Queen's University Belfast, Belfast, Northern Ireland BT7 1NN, United Kingdom; Geography and Environmental Science, University of Southampton, Highfield, Southampton, SO17 1BJ, United Kingdom; Institute of Geographic Science and Natural Resources Research, Chinese ...
推荐引用方式 GB/T 7714	Zhang C.,Harrison P.A.,Pan X.,et al. Scale Sequence Joint Deep Learning (SS-JDL) for land use and land cover classification[J],2020,237.
APA	Zhang C.,Harrison P.A.,Pan X.,Li H.,Sargent I.,&Atkinson P.M..(2020).Scale Sequence Joint Deep Learning (SS-JDL) for land use and land cover classification.Remote Sensing of Environment,237.
MLA	Zhang C.,et al."Scale Sequence Joint Deep Learning (SS-JDL) for land use and land cover classification".Remote Sensing of Environment 237(2020).