Building extraction based on high-resolution remote sensing imagery has been widely used in automatic surveying and mapping. However, few methods have been developed for building instance extraction, i.e., extracting each building's footprint separately, which is required in a number of applications, such as the smallest unit of a cadastral database. In building instance extraction, there are two challenges: 1) buildings with various scales exist in the imagery and 2) precise building footprints are difficult to extract due to the blurry boundaries. In this article, to solve these problems, a multiscale U-shaped convolutional neural network building instance extraction framework with edge constraint (EMU-CNN) for high-spatial-resolution remote sensing imagery is proposed. The proposed framework consists of three components: 1) a multiscale fusion U-shaped network (MFUN); 2) a region proposal network (RPN); and 3) an edge-constrained multitask network (ECMN). First, in the proposed method, the MFUN includes three parallel branches to learn multiple building features with different scales. The RPN then detects the positions of the building instances, even for buildings that are connected with each other. Moreover, according to the instance positions, the ECMN is proposed to extract a precise mask and suppress overfitting. The experiments conducted on a self-annotated data set and two public data sets (the ISPRS Vaihingen semantic labeling contest data set and the WHU aerial image data set) show that the EMU-CNN method can achieve excellent performance and shows great robustness at different scales.

Synthetic aperture radar (SAR) change detection is an essential yet challenging task in the field of ground surface observation. Existing transformer-based methods have promising context modeling capabilities for change detection tasks, yet they struggle to preserve change-related details in high-resolution data. To deal with this limitation, a directional-aware dual-branch fusion network (DAFNet) is proposed based on dual-branch backbone and gated cross-fusion module (GCFM) for SAR image change detection. First, an enhanced difference image is developed by integrating log-ratio operator and A-law companding for high-quality training data generation. In the dual-branch backbone, a multi-directional convolution module (MDCM) is then constructed to extract high-frequency features comprehensively via multi-gradient Sobel operators with eight directions, which selectively captures details and contexts of images in a parallel manner with vision transformer. Finally, the GCFM based on GeLU activation and cross-attention is designed to fuse different dimensional features, enhancing related information against irrelevant interference. Experimental evaluations across three real SAR datasets verify the effectiveness of the proposed DAFNet in terms of visualization and quantitative indicators in change detection.

Continuous building footprint extraction requires learning new building patterns from remote sensing imagery without forgetting old knowledge. It is inherently challenging due to the spatial layout heterogeneity, which leads to the problem of knowledge forgetting in two aspects: complex background could have distinct patterns (background diversity), and buildings could have similar patterns to the background (foreground-background similarity). To solve the issues, we propose a domainin-incremental continual learning algorithm named layout-anchored prioritizing learning network (LAPNet), including a latent layout anchoring module and layout-aware prioritizing learning module. The latent layout anchoring aggregates background information into latent layout features and employs a herding strategy to select representative layout anchors iteratively. This module maintains a memory buffer to narrow the background differences by dynamically discarding unrepresentative experiences and storing layout-anchored experiences. Furthermore, layout-aware prioritizing learning uses these experiences to identify and emphasize the most valuable knowledge for maximizing interclass distance. This module leverages layout variance metric to measure interclass discrepancies and employs prioritizing learning to reweight the optimization function based on this layout prior. We established a Global-CL dataset to validate the proposed LAPNet framework, containing six study areas across four continents with different remote sensing sensors. Experiments showed that LAPNet achieves state-of-the-art performance in continuous building footprint extraction by effectively correlating knowledge across various domains. The code is available at: https://github.com/Dingyuan-Chen/LAPNet.

Multi-unmanned aerial vehicle (UAV) cooperative maritime object recognition aims to maintain high accuracy under dynamic aerial perspectives for maritime search and rescue missions. Existing continual learning methods retain knowledge by approximating the global distribution of prior data but fail to address cross-perspective knowledge conflicts caused by distribution shifts across aerial perspectives, leading to gradient perturbations that harm consistency and accuracy in dynamic maritime environments. To address the issues, we propose a conflict-modulated generative continual learning (ConMod) framework, comprising generative perspective-robust conflict estimation and conflict-modulated continual learning modules. The generative perspective-robust conflict estimation employs a perspective-aware scene generator that embeds maritime knowledge priors as perspective constraints to augment the data distribution, thereby facilitating explainable cross-perspective conflict association and promoting robust conflict index estimation. It also incorporates a dual-modal conflict index estimator that integrates geometric distortion and environmental variation branches to estimate conflict indices by associating simulated scenes with perspective-robust data distributions. Furthermore, conflict-modulated continual learning introduces a perspective-specific triplet loss to regularize consistency by aligning geometric and environmental features within perspective-specific representation space. Additionally, a conflict-modulated loss treats conflict indices as modulation weights to identify and reinforce representative conflict experiences from a cross-perspective memory buffer, guiding gradient updates toward global optimization. Results on the SeaDronesSee-CL and SeaDronesSee-CL-v2 datasets show that ConMod effectively improves multi-UAV cooperative maritime object recognition by identifying and mitigating cross-perspective knowledge conflicts.