Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection

By Haobo Lyu, Hui Lu, Lichao Mou. Remote Sensing, 2016

327 citations recorded by the source corpus.

When exploited in remote sensing analysis, a reliable change rule with transfer ability can detect changes accurately and be applied widely. However, in practice, the complexity of land cover changes makes it difficult to use only one change rule or change feature learned from a given multi-temporal dataset to detect any other new target images without applying other learning processes. In this study, we consider the design of an efficient change rule having transferability to detect both binary and multi-class changes. The proposed method relies on an improved Long Short-Term Memory (LSTM) model to acquire and record the change information of long-term sequence remote sensing data. In particular, a core memory cell is utilized to learn the change rule from the information concerning binary changes or multi-class changes. Three gates are utilized to control the input, output and update of the LSTM model for optimization. In addition, the learned rule can be applied to detect changes and transfer the change rule from one learned image to another new target multi-temporal image. In this study, binary experiments, transfer experiments and multi-class change experiments are exploited to demonstrate the superiority of our method. Three contributions of this work can be summarized as follows: (1) the proposed method can learn an effective change rule to provide reliable change information for multi-temporal images; (2) the learned change rule has good transferability for detecting changes in new target images without any extra learning process, and the new target images should have a multi-spectral distribution similar to that of the training images; and (3) to the authors’ best knowledge, this is the first time that deep learning in recurrent neural networks is exploited for change detection. In addition, under the framework of the proposed method, changes can be detected under both binary detection and multi-class change detection.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/198df8ff0009e708e20510e6ce88792b4b4cf9c1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Ecology

In Media Technology

Citations in the corpus

DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation (2022, methodology): “Previous works [25,28,36] have used Cohen’s kappa to measure the performance in similar settings.”
Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-Analysis (2020, background): “[66]- -Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection2016 (126)”
Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery (2018, background): “Recently, Lyu et al. [23] make use of an end-to-end RNN to solve the multi/hyper-spectral image change detection task, since RNN is well known to be good at processing sequential data.”
Deep learning for change detection in remote sensing: a review (2022, methodology): “…detection methods, the DLCD can learn detailed temporal information as well as nonlinear temporal information automatically, supporting the detection of complicated urban land-use change (Lyu, Lu, and Mou 2016; Mou, Bruzzone, and Zhu 2018) and vegetation phenological patterns (Song et al. 2018).”
End-to-End Change Detection for High Resolution Satellite Images Using Improved UNet++ (2019, background): “It is noteworthy that recurrent neural networks (RNNs) were ﬁrstly exploited to model temporal change relations in [48].”
A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection (2020, methodology): “A recurrent neural network (RNN) is good at handling sequential relationships and one has been applied in CD to model temporal dependency [29,31,32].”
Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series (2018, methodology): “In remote sensing, CNNs have been successfully used to exploit the spatial dimension of very high spatial resolution satellite images for object detection [22], land cover classification [23], [24] and land cover change detection [25].”
Semi-Supervised Deep Learning Using Pseudo Labels for Hyperspectral Image Classification (2018, methodology): “In [21], a recurrent neural network (RNN) was used for land cover change detection on multi-spectral images.”
Deep learning in remote sensing: a review (2017, background): “In contrast, for other hyperspectral data analysis tasks, such as change and anomaly detections, deep learning is just beginning to make its mark [37], [38].”
Change Detection in Multisource VHR Images via Deep Siamese Convolutional Multiple-Layers Recurrent Neural Network (2020, methodology): “[27] adopted recurrent neural network (RNN) to learn transferable change-rules between multitemporal homogeneous images.”
Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data (2017, background): “In terms of particular DL architectures, convolutional NNs (CNNs), deep autoencoders, deep belief networks, and recurrent NN with long short-term memory model have already been explored for RS tasks [17], [28]–[31].”
Unsupervised Deep Change Vector Analysis for Multiple-Change Detection in VHR Images (2019, methodology): “[35] proposed a supervised CD method based on”
Self-Attention for Raw Optical Satellite Time Series Classification (2019, methodology): “Methods from multi-temporal Earth observation [39, 40, 41, 42, 43, 44] adapted models from natural language processing.”
Deep Recurrent Neural Networks for Hyperspectral Image Classification (2017, background): “Recently, more and more empirical results have demonstrated that RNNs are not just powerful in theory [42], [44], [45] but can also be reliably learned in practice for processing long-term sequential data [36], [46], [47].”