Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images

TL;DR

This paper introduces Bi-SRNet, a novel CNN architecture that enhances semantic change detection in remote sensing images by reasoning bi-temporal semantic correlations, leading to improved accuracy in land-cover change analysis.

Contribution

The paper proposes a new CNN architecture with semantic reasoning blocks and a specialized loss function for better semantic change detection in remote sensing images.

Findings

Significant accuracy improvements over existing methods.

Enhanced segmentation of semantic categories and change areas.

Effective bi-temporal semantic correlation reasoning.

Abstract

Semantic change detection (SCD) extends the multi-class change detection (MCD) task to provide not only the change locations but also the detailed land-cover/land-use (LCLU) categories before and after the observation intervals. This fine-grained semantic change information is very useful in many applications. Recent studies indicate that the SCD can be modeled through a triple-branch Convolutional Neural Network (CNN), which contains two temporal branches and a change branch. However, in this architecture, the communications between the temporal branches and the change branch are insufficient. To overcome the limitations in existing methods, we propose a novel CNN architecture for the SCD, where the semantic temporal features are merged in a deep CD unit. Furthermore, we elaborate on this architecture to reason the bi-temporal semantic correlations. The resulting Bi-temporal Semantic Reasoning Network (Bi-SRNet) contains two types of semantic reasoning blocks to reason both single-temporal and cross-temporal semantic correlations, as well as a novel loss function to improve the semantic consistency of change detection results. Experimental results on a benchmark dataset show that the proposed architecture obtains significant accuracy improvements over the existing approaches, while the added designs in the Bi-SRNet further improves the segmentation of both semantic categories and the changed areas. The codes in this paper are accessible at: github.com/ggsDing/Bi-SRNet.