LRNet: Change detection of high-resolution remote sensing imagery via strategy of localization-then-refinement

TL;DR

LRNet tackles the challenging boundary discrimination in high-resolution remote sensing change detection by adopting a localization-then-refinement strategy. It employs a three-branch encoder with learnable optimal pooling and novel attention modules (C2A and HCA) to localize change areas, followed by an edge-area constrained refinement stage (E2A) and a decoder that yields precise change boundaries. The method demonstrates state-of-the-art performance on LEVIR-CD and WHU-CD, especially in boundary and edge discrimination, by integrating multi-branch interaction, hierarchical attention propagation, and edge-aware supervision. This approach offers a practical improvement for accurate, boundary-preserving CD in complex urban and natural scenes, with potential for extension to lighter architectures for deployment.

Abstract

Change detection, as a research hotspot in the field of remote sensing, has witnessed continuous development and progress. However, the discrimination of boundary details remains a significant bottleneck due to the complexity of surrounding elements between change areas and backgrounds. Discriminating the boundaries of large change areas results in misalignment, while connecting boundaries occurs for small change targets. To address the above issues, a novel network based on the localization-then-refinement strategy is proposed in this paper, namely LRNet. LRNet consists of two stages: localization and refinement. In the localization stage, a three-branch encoder simultaneously extracts original image features and their differential features for interactive localization of the position of each change area. To minimize information loss during feature extraction, learnable optimal pooling (LOP) is proposed to replace the widely used max-pooling. Additionally, this process is trainable and contributes to the overall optimization of the network. To effectively interact features from different branches and accurately locate change areas of various sizes, change alignment attention (C2A) and hierarchical change alignment module (HCA) are proposed. In the refinement stage, the localization results from the localization stage are corrected by constraining the change areas and change edges through the edge-area alignment module (E2A). Subsequently, the decoder, combined with the difference features strengthened by C2A in the localization phase, refines change areas of different sizes, ultimately achieving accurate boundary discrimination of change areas. The proposed LRNet outperforms 13 other state-of-the-art methods in terms of comprehensive evaluation metrics and provides the most precise boundary discrimination results on the LEVIR-CD and WHU-CD datasets.

Figures (11)

• Figure 1: An illustration of the existing problems.
• Figure 2: Flowchart of the LRNet network.
• Figure 3: Schematic diagram of learnable optimal pooling.
• Figure 4: Structure of the change alignment attention module.
• Figure 5: Structure of the hierarchical change alignment module.