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.

Land-use maps are instrumental to inform urban planning and environmental research. Street view images (SVIs) have shown great potential for automated land-use classification for land-use mapping. However, previous studies overlooked SVI-derived location contextual information that may help improve land-use classification. This study proposes a novel land-use classification method that synthesizes location semantics from SVIs to account for contextual information from SVIs, land parcels and roads around the SVIs. The proposed method first generates land-use scene images (LUSIs) by using an SVI-derived straightforward algorithm. The LUSIs are then relocated to land parcels by using a displacement strategy and classified into land-use types by using a deep learning network. This study determines the land-use types of land parcels with classified LUSIs. Two case studies, consisting of LUSIs for five land-use types, show that introducing location semantics of SVIs can remarkably improve the classification accuracy of land-use types.

Building instances extraction is an essential task for surveying and mapping. Challenges still exist in extracting building instances from high-resolution remote sensing imagery mainly because of complex structures, variety of scales, and interconnected buildings. This study proposes a coarse-to-fine contour optimization network to improve the performance of building instance extraction. Specifically, the network contains two special sub-networks: attention-based feature pyramid sub-network (AFPN) and coarse-to-fine contour sub-network. The former sub-network introduces channel attention into each layer of the original feature pyramid network (FPN) to improve the identification of small buildings, and the latter is designed to accurately extract building contours via two cascaded contour optimization learning. Furthermore, the whole network is jointly optimized by multiple losses, that is, a contour loss, a classification loss, a box regression loss and a general mask loss. Experimental results on three challenging building extraction datasets demonstrated that the proposed method outperformed the state-of-the-art methods’ accuracy and quality of building contours.

Image-level weakly supervised semantic segmentation (WSSS) methods have greatly facilitated the extraction of buildings from remote sensing (RS) images. However, the lack of the locations and extents of individual buildings in image-level labels results in some limitations of the methods, especially in the cases of cluttered backgrounds, diverse building shapes and sizes. By utilizing bounding box annotations, a novel WSSS model is developed to improve building extraction from RS images in this paper. Specifically, during the training phase, a multiscale feature retrieval (MFR) module is designed to learn multiscale building features and suppress the background noise inside the bounding box. In the inference phase, multiscale class activation maps (CAM) are generated from multiscale features to achieve accurate building localization. Finally, a pseudo mask generation and correction (PGC) module refines the CAMs to generate and correct the building pseudo masks. Experiments are conducted to examine the proposed model in three datasets, namely, the WHU aerial building dataset, the CrowdAI building dataset, and a self-annotated building dataset. Experimental results demonstrate that the proposed method outperforms baselines, achieving 76.99%, 75.51% and 67.35% in terms of IoU scores on the three challenging datasets, respectively. This paper provides a methodological reference for the application of weakly supervised learning on RS images.

Automatic remote sensing (RS) image to map translation is a crucial technology for intelligent tile map generation. Although existing methods based on a generative network (GAN) generated unannotated maps at a single level, they have limited capacity in handling multi-resolution map generation at different levels. To address the problem, we proposed a novel conditional scale-consistent generation network (CscGAN) to simultaneously generate multi-level tile maps from multi-scale RS images, using only a single and unified model. Specifically, the CscGAN first uses the level labels and map annotations as prior conditions to guide hierarchical feature learning with different scales. Then, a multi-scale discriminator and two multi-scale generators are introduced to describe both high-resolution and low-resolution representations, aiming to improve the similarity of generated maps and thus produce high-quality multi-level tile maps. Meanwhile, a level classifier is designed for further exploring the characteristics of tile maps at different levels. Moreover, the CscGAN is optimized by jointly multi-scale adversarial loss, level classification loss, and scale-consistent loss in an end-to-end manner. Extensive experiments on multiple datasets and study areas demonstrate that the CscGAN outperforms the state-of-the-art methods in multi-level map translation, with great robustness and efficiency.