Automated generalization of road network data is of great concern to the map generalization community because of the importance of road data and the difficulty involved. Complex junctions are where roads meet and join in a complicated way and identifying them is a key issue in road network generalization. In addition to their structural complexity, complex junctions don’t have regular geometric boundary and their representation in spatial data is scale-dependent. All these together make them hard to identify. Existing methods use geometric and topological statistics to characterize and identify them, and are thus error-prone, scale-dependent and lack generality. More significantly, they cannot ensure the integrity of complex junctions. This study overcomes the obstacles by clarifying the topological boundary of a complex junction, which provides the basis for straightforward identification of them. Test results show the proposed method can find and isolate complex junctions in a road network with their integrity and is able to handle different road representations. The integral identification achieved can help to guarantee connectivity among roads when simplifying complex junctions, and greatly facilitate the geometric and semantic simplification of them.

Building change detection (BCD) from remote sensing images is essential in various practical applications. Recently, inspired by the achievement of deep learning in semantic segmentation (SS), methods that treat the BCD problem as a binary SS task using deep siamese networks have attracted increasing attention. However, similar to their counterparts, these approaches still face the challenge of collecting massive pixel-level annotations. To address this issue, this article presents a novel weakly supervised method for BCD from remote sensing images using image-level labels. The proposed method elaborately designs a siamese network to integrate a multiscale joint supervision (MJS) module and an improved consistency regularization (ICR) module into a unified framework to improve the so-called class activation maps (CAMs), which is vital for producing high-quality pseudomasks using imagelevel annotations to support pixel-level BCD. To be specific, the MSJ is used for generating refined multiscale CAMs to well capture changes at different scales corresponding to various buildings of varying sizes. The ICR contributes to improving the consistency of CAMs to highlight the boundaries of changed buildings. Extensive experiments on two public BCD datasets have demonstrated that the proposed method outperforms the current state-of-the-art approaches. Furthermore, the visual detection maps also indicate that the proposed method can achieve scale-adaptive change detection results and preserve object boundaries more effectively.

No abstract