Change detection in images using shape-aware siamese convolutional network. (September 2020)

• Record Type: Journal Article
• Authors: Li, Suicheng; Han, Pengcheng; Bu, Shuhui; Tong, Pinmo; Li, Qing; Li, Ke; Wan, Gang
• Is Part Of: Engineering applications of artificial intelligence. Volume 94(2020)
• Publication Date: 2020-09
• Subjects: Change detection in images -- SASCNet -- Change map fusion -- Fine-tune; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2020.103819
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Change detection gradually becomes a core technique due to its wide applications of image or video analysis like land cover analysis and real-time monitoring system. Recently, siamese convolutional networks have been adopted for change detection which demonstrate the state-of-the-art performance. Although most of the previous works have better location accuracy, these methods cannot avoid side effects such as coarse boundaries and empty holes. In this paper, we propose a shape-aware siamese convolutional network (SASCNet) to simultaneously integrate different information for change detection with three steps in an unified network. In the first step, we extract multi-dimension features from paired images and select multi-level change maps generated by a novel siamese encoder–decoder network with multi-scale supervisions. In the second step, we integrate these change maps to obtain complementary information in detail. Finally, we use a residual fine-tune module to refine the predicted change maps and enhance the performance. Because of rich information in different levels and multi-scale supervisions, the predicted change maps could provide precise positioning as well as high-quality shapes. Experimental results on "CDnet 2014 dataset" and "AICD-2012 dataset" show that our method outperforms the state-of-the-art methods in most challenging conditions.