RaSRNet: An End-to-End Relation-Aware Semantic Reasoning Network for Change Detection in Optical Remote Sensing Images

Optical remote sensing images (RSIs) are used in surface observation, and one of the most interesting research topics is change detection (CD). The internal problem of RSIs, including multiscales changed objects and cluttered background, still deserves attention. Existing methods make great efforts to solve this problem but inevitably miss detection, which affects the model performance. To address this dilemma, this article proposes a relation-aware semantic reasoning network (RaSRNet) in an end-to-end manner to pop-out change objects in RSIs, where the key point is to perceive contextual semantic information. The relation-aware (Ra) module in RaSRNet combats the lack of contextual information caused by the limited receptive field (RF) of the general convolutional layer, which facilitates all-around changed object detection. The multilevel semantic reasoning encoder-decoder (ED) backbone in RaSRNet extracts and reconstructs pixel semantic information, alleviates the interference of background noise, and improves the integrity recognition of changed objects. In addition, the decoder backend undertakes two semantic segmentation branches and introduces a semantic reasoning loss between the two branches to infer pixel semantic categories, which provides more accurate semantic features for the CD. Extensive experiments are conducted on the three public RSI CD datasets, and the results demonstrate that the proposed RaSRNet can accurately locate changed objects, which consistently outperforms the state-of-the-art CD competitors.