Bi-Temporal Semantic Reasoning for the Semantic Change Detection of HR Remote Sensing Images
share
Semantic change detection (SCD) extends the change detection (CD) task to provide not only the change locations but also the detailed semantic categories (before and after the observation intervals). This fine-grained change information is more useful in land-cover/land-use (LC/LU) 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 connections between the temporal branches and the change branch are weak. To overcome these limitations, we propose a novel CNN architecture for the SCD, where the temporal features are re-used and are deeply merged in the temporal branch. Furthermore, we elaborate on this architecture to model 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: https://github.com/ggsDing/Bi-SRNet
READ FULL TEXT
