Abstract
Change detection methods for optical remote sensing images play an important role in environmental resource management. Although recent methods based on deep learning demonstrate incredible ability by constructing networks, first, extracting bitemporal features in a separate manner; second, fusing bitemporal images before forwarding them into the single-level network. Both severely neglect the effect of spatial-temporal feature correlation between bitemporal images. In addition, most existing methods represent multiscale feature pairs in a layer-wise manner like ResNet, failing to consider the inner multilevel structure. In this work, we propose a new siamese change detection feature encoder backbone named cross-siamese Res2Net (CSRes2Net), by establishing crossed and hierarchical residual-like connections within one single residual block. The CSRes2Net represents dual features in a fine-grained manner and fully leads to the flow of bitemporal features. In addition, recent learning-based methods designed some spatial-temporal relation modules to capture the pixel-level pairwise relationship and channel dependency based on self-attention mechanism, but they only consider spatial and channel dimension corrections separately with excessive parameters. So we propose a lightweight cross spatial-channel triplet attention module to capture cross-dimensional long-range relationship between triplet combinations: channel with height, channel with width, channel with channel. Finally, we propose a hierarchical-split block for generating multiscale feature representations in a coarse-to-fine fashion. The experiments results on LEVIR-CD and season-varying change detection dataset outperform most state-of-the-art models.
Highlights
T HE difference of multi-temporal images has important applications in understanding land surface change, global resource monitoring, land use change detection, disaster assessment, visual monitoring and urban management [1]
The main contributions of this paper can be summarized as follows: 1. We propose a new remote sensing image change detection backbone named CSRes2Net based on ResNet and Res2Net, which constructs crossed and hierarchical residual-like connections within single residual block for representing interactive change saliency information
Extra evaluation indexes widely used in semantic segmentation: mean pixel accuracy (MPA), mean intersection over union, frequency weighted intersection over union (FWIOU) and dice coefficient (Dice) supply other comprehensive criteria to assess the performance of our method
Summary
T HE difference of multi-temporal images has important applications in understanding land surface change, global resource monitoring, land use change detection, disaster assessment, visual monitoring and urban management [1]. We propose a new remote sensing image change detection backbone named CSRes2Net based on ResNet and Res2Net, which constructs crossed and hierarchical residual-like connections within single residual block for representing interactive change saliency information. This backbone can be taken as a plug-and-play siamese feature extractor for change detection task.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have