Scale Sequence Joint Deep Learning (SS-JDL) for land use and land cover classification

Zhang, Ce ORCID: https://orcid.org/0000-0001-5100-3584; Harrison, Paula A. ORCID: https://orcid.org/0000-0002-9873-3338; Pan, Xin; Li, Huapeng; Sargent, Isabel; Atkinson, Peter M.. 2020 Scale Sequence Joint Deep Learning (SS-JDL) for land use and land cover classification. Remote Sensing of Environment, 237, 111593. 16, pp. https://doi.org/10.1016/j.rse.2019.111593

Before downloading, please read NORA policies.

Preview

Text
N526260PP.pdf - Accepted Version
Download (1MB) | Preview

Official URL: http://dx.doi.org/10.1016/j.rse.2019.111593

Abstract/Summary

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.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	https://doi.org/10.1016/j.rse.2019.111593
UKCEH and CEH Sections/Science Areas:	Soils and Land Use (Science Area 2017-)
ISSN:	0034-4257
Additional Keywords:	multi-scale deep learning, optimal scale selection, convolutional neural network, joint classification, hierarchical representations
NORA Subject Terms:	Data and Information
Date made live:	18 Dec 2019 15:55 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/526260

Item Type:

Publication - Article

Digital Object Identifier (DOI):

https://doi.org/10.1016/j.rse.2019.111593

UKCEH and CEH Sections/Science Areas:

Soils and Land Use (Science Area 2017-)

ISSN:

0034-4257

Additional Keywords:

multi-scale deep learning, optimal scale selection, convolutional neural network, joint classification, hierarchical representations

NORA Subject Terms:

Data and Information