Multiscale Change Detection Network Based on Channel Attention and Fully Convolutional BiLSTM for Medium-Resolution Remote Sensing Imagery
Jialu Li, Meiqi Hu, Chen Wu
Abstract
Remote sensing Change Detection (CD) is used to detect the difference in the state of objects or phenomena by observing it at different times. CD is widely used in disaster monitoring, land-use and land-cover change analysis, urban expansion detection, and other fields. Medium-Resolution (MR) remote sensing imagery can be used for global and regional CD due to the real-time acquisition, extensive coverage, and historical data advantages. Therefore, Medium Resolution remote sensing imagery Change Detection (MRCD) is a very important topic. Compared with Very-High-Resolution (VHR) imagery, MR imagery has less texture and edge information. Besides, the object has a large-scale size in VHR imagery scene while the same object will only have a small-scale size in MR imagery scene. To solve the challenge of MRCD, we propose a joint spatial-spectral-temporal network for MRCD, named MC2ABNet. The MC2ABNet consists of Multiscale Convolutional Channel Attention (MC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> A) module and fully Convolutional Bi-directional Long Short-Term Memory (ConvBiLSTM) network. In the encoder, MC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> A module is used to extract multiscale spatial features from multi-temporal imagery at each encoding level by sharing structure, parameters, and weights. In each MC2A module, the multiscale convolution extracts multiscale spatial features with different receptive fields, then the channel attention is used to ease the information redundancy during down-sampling. The ConvBiLSTM is applied to calculate time difference features in both forward and backward directions and utilize spatial information synergistically to smooth change noise for obtaining complete time difference features. Extensive experiments have been conducted on OSCD and SpaceNet7 data sets. Compared with other state-of-the-art methods, our network achieves the highest accuracy on both data sets.