With the development of deep learning techniques in the field of remote sensing change detection, many change detection algorithms based on convolutional neural networks (CNNs) and nonlocal self-attention (NLSA) mechanisms have been widely used and have obtained good detection accuracy. However, these methods mainly extract semantic features on images from different periods without taking into account the temporal dependence between these features. This will lead to more “pseudo-change” in complex scenes. In this paper, we propose a network architecture named UVACD for bitemporal image change detection. The network combines a CNNs extraction backbone for extracting high-level semantic information with a visual transformer. Here, visual transformer constructs change intensity tokens to complete the temporal information interaction and suppress irrelevant information weights to help extract more distinguishable change features. Our network is validated and tested on both the LEVIR-CD and WHU datasets. For the LEVIR-CD dataset, we achieve an intersection over union (IoU) of 0.8398 and an F1 score of 0.9130. For the WHU dataset, we achieve an IoU of 0.8664 and an F1 score of 0.9284. The experimental results show that the proposed method outperforms some previous state of the art change detection methods.

Remote sensing change detection (CD) identifies changes in each pixel of certain classes of interest from a set of aligned image pairs. It is challenging to accurately identify natural changes in feature categories due to unstructured and temporal changes. This research proposed an effective bi-temporal remote sensing CD comprising an encoder that could extract multiscale features, a decoder that focused on semantic alignment between temporal features, and a classification head. In the decoder, we constructed a new convolutional attention structure based on pre-generation of depthwise-separable change-salient maps (PDACN) that could reduce the attention of the network on unchanged regions and thus reduce the potential pseudo-variation in the data sources caused by semantic differences in illumination and subtle alignment differences. To demonstrate the effectiveness of the PDA attention structure, we designed a lightweight network structure for encoders under both convolution-based and transformer architectures. The experiments were conducted on a single-building CD dataset (LEVIR-CD) and a more complex multivariate change type dataset (SYSU-CD). The results showed that our PDA attention structure generated more discriminative change variance information while the entire network model obtained the best performance results with the same level of network model parameters in the transformer architecture. For LEVIR-CD, we achieved an intersection over union (IoU) of 0.8492 and an F1 score of 0.9185. For SYSU-CD, we obtained an IoU of 0.7028 and an F1 score of 0.8255. The experimental results showed that the method proposed in this paper was superior to some current state-of-the-art CD methods.