Progressive Domain Adaptation for Change Detection Using Season-Varying Remote Sensing Images

Rong Kou,Gang Chen,Lizhe Wang,Bo Fang

doi:10.3390/rs12223815

Rong Kou, Gang Chen + Show 2 more

Open Access

https://doi.org/10.3390/rs12223815

Copy DOI

Journal: Remote sensing	Publication Date: Nov 20, 2020
Citations: 12	License type: CC BY 4.0

Affiliation: Wuhan University, China University of Geosciences

Abstract

The development of artificial intelligence technology has prompted an immense amount of researches on improving the performance of change detection approaches. Existing deep learning-driven methods generally regard changes as a specific type of land cover, and try to identify them relying on the powerful expression capabilities of neural networks. However, in practice, different types of land cover changes are generally influenced by environmental factors at different degrees. Furthermore, seasonal variation-induced spectral differences seriously interfere with those of real changes in different land cover types. All these problems pose great challenges for season-varying change detection because the real and seasonal variation-induced changes are technically difficult to separate by a single end-to-end model. In this paper, by embedding a convolutional long short-term memory (ConvLSTM) network into a conditional generative adversarial network (cGAN), we develop a novel method, named progressive domain adaptation (PDA), for change detection using season-varying remote sensing images. In our idea, two cascaded modules, progressive translation and group discrimination, are introduced to progressively translate pre-event images from their own domain to the post-event one, where their seasonal features are consistent and their intrinsic land cover distribution features are retained. By training this hybrid multi-model framework with certain reference change maps, the seasonal variation-induced changes between paired images are effectively suppressed, and meanwhile the natural and human activity-caused changes are greatly emphasized. Extensive experiments on two types of season-varying change detection datasets and a comparison with other state-of-the-art methods verify the effectiveness and competitiveness of our proposed PDA.

Highlights

Change detection is one of the critical research branches in the field of remote sensing
As a specific recurrent neural network (RNN) structure, long short-term memory (LSTM) is mainly innovative at the memory cell, which essentially acts as an accumulator of the state information, and is accessed, written, and cleared by several self-parameterized controlling gates
With the six couples of bi-temporal remote sensing images in two types of datasets, the binary format change detection results of the proposed progressive domain adaptation (PDA) and several competitors are presented in Figure 8 and 9, respectively, where the pixels in white and black indicate the changed and unchanged regions

Summary

Introduction

Change detection is one of the critical research branches in the field of remote sensing. The emergence of high spatial and high spectral resolution remote sensing imagery provides richer information of the Earth surface and offers the opportunities to promote the performance of change detection methods. Following a two-step workflow, the current change detection methods can be generally seen as composed of two steps: feature extraction and decision making. LSTM has proven powerful and robust for modeling the long-range dependencies in one-dimensional general-purpose sequence data. Along this way, to explore the relationship in two-dimensional paired image data, convolutional blocks are embedded in LSTM units, to form the ConvLSTM model. The interaction of all states and gates along the time dimension is formulated as Equation (1)

Methods

Results

Discussion

Conclusion