BuildMon: Building Extraction and Change Monitoring in Time Series Remote Sensing Images

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 17; pp. 10813 - 10826
• Main Authors: Wang, Yuxuan, Chen, Shuailin, Zhang, Ruixiang, Xu, Fang, Liang, Shuo, Wang, Yujing, Yang, Wen
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aggregation; Building extraction; Buildings; change monitoring; change-guided loss; Disaster management; Emergency preparedness; Feature extraction; Ground truth; Imagery; Masks; Monitoring; Remote monitoring; Remote sensing; spatial-temporal (ST) transformer; Task analysis; Time series; Time series analysis; time series images; Tracking; Transformers; Urban planning
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2024.3404781

Building extraction and change monitoring in remote sensing (RS) imagery play pivotal roles in various applications, including urban planning, disaster management, and infrastructure monitoring. While significant progress has been made in single and bitemporal RS images, effectively harnessing the rich temporal information of time series RS images remains a challenge. Time series RS images offer an extended temporal span for monitoring dynamic changes in building instances. However, they often exhibit noticeable appearance discrepancies and feature variations, presenting substantial obstacles to effective multitemporal information aggregation. To address these challenges, we introduce a Building Extraction and Change Monitoring Network (BuildMon), which jointly explores the segmentation masks, location tracking, and construction status of building instances. Our approach incorporates a spatial-temporal transformer to model relationships between images at different time spans. The windowed attention module within it can capture spatial-temporal context for a larger scope of feature aggregation. For enhancing the performance on both tasks, we adopted ground truth masks and semantic change information together as supervisory signals for BuildMon. This is complemented by the specially designed change-guided loss function, which specifically highlights regions of change and assigns targeted weights to building areas within the imagery. To validate the effectiveness of our method, we conduct comprehensive experiments on the SpaceNet 7 dataset. The results showcase the state-of-the-art performance of our approach, achieving mIoU and SpaceNet Change and Object Tracking metrics of 67.90 and 39.73, respectively.