Y-Net: A Multiclass Change Detection Network for Bi-temporal Remote Sensing Images

The multiclass change detection task aims to segment an area of land change and to identify the type of ground change exploiting bi-temporal remote-sensing images. In recent years, this technology has become an important means of analysing remote-sensing data and has shown great potential in accurately understanding changes on the earth’s surface. However, the existing methods are mainly for binary change detection tasks and cannot detect the specific information of the change category. Hence, in this paper, we propose an end-to-end densely connected network, entitled Y-Net, employing a Siamese structure for multiclass change detection. The proposed network uses a dual-stream DenseNet to extract bi-temporal change features during the encoding stage and introduces the attention fusion mechanism for the decoding stage to enhance the attention to changing features. Add the dice loss to reduce the impact of sample imbalance on multiclass change detection. The suggested network utilizes a deep supervision strategy for each decoding layer to achieve change graph reconstruction of different levels. Y-Net is evaluated on the challenging multiclass change detection data set SECOND, and the ablation study verified the effectiveness of the attention fusion module and dice loss for multiclass change detection, considering both visual interpretation and quantitative evaluation, confirming that the proposed method is superior to current state-of-the-art change detection methods.