SAR Image Change Detection Based on Multiscale Capsule Network

TL;DR

This paper introduces a Multiscale Capsule Network (Ms-CapsNet) for SAR image change detection, effectively handling speckle noise and deformation sensitivity by exploiting spatial relationships and adaptive feature fusion.

Contribution

The paper proposes a novel Ms-CapsNet architecture with multiscale capsules and adaptive fusion convolution modules to improve change detection accuracy in SAR images.

Findings

Outperforms four state-of-the-art methods on three SAR datasets.

Enhances robustness to speckle noise through adaptive feature fusion.

Achieves better spatial relationship modeling with multiscale capsules.

Abstract

Traditional synthetic aperture radar image change detection methods based on convolutional neural networks (CNNs) face the challenges of speckle noise and deformation sensitivity. To mitigate these issues, we proposed a Multiscale Capsule Network (Ms-CapsNet) to extract the discriminative information between the changed and unchanged pixels. On the one hand, the multiscale capsule module is employed to exploit the spatial relationship of features. Therefore, equivariant properties can be achieved by aggregating the features from different positions. On the other hand, an adaptive fusion convolution (AFC) module is designed for the proposed Ms-CapsNet. Higher semantic features can be captured for the primary capsules. Feature extracted by the AFC module significantly improves the robustness to speckle noise. The effectiveness of the proposed Ms-CapsNet is verified on three real SAR datasets. The comparison experiments with four state-of-the-art methods demonstrate the efficiency of the proposed method. Our codes are available at https://github.com/summitgao/SAR_CD_MS_CapsNet .