Automatic building extraction from optical imagery remains a challenge due to, for example, the complexity of building shapes. Semantic segmentation is an efficient approach for this task. The latest development in deep convolutional neural networks (DCNNs) has made accurate pixel-level classification tasks possible. Yet one central issue remains: the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to their progressive down-sampling. Hence, we introduce a generic framework to overcome the issue, integrating the graph convolutional network (GCN) and deep structured feature embedding (DSFE) into an end-to-end workflow. Furthermore, instead of using a classic graph convolutional neural network, we propose a gated graph convolutional network, which enables the refinement of weak and coarse semantic predictions to generate sharp borders and fine-grained pixel-level classification. Taking the semantic segmentation of building footprints as a practical example, we compared different feature embedding architectures and graph neural networks. Our proposed framework with the new GCN architecture outperforms state-of-the-art approaches. Although our main task in this work is building footprint extraction, the proposed method can be generally applied to other binary or multi-label segmentation tasks.
29 April 2020 in IEEE Transactions on Geoscience and Remote Sensing
Building footprint maps are vital to many remote sensing (RS) applications, such as 3-D building modeling, urban planning, and disaster management. Due to the complexity of buildings, the accurate and reliable generation of the building footprint from RS imagery is still a challenging task. In this article, an end-to-end building footprint generation approach that integrates convolution neural network (CNN) and graph model is proposed. CNN serves as the feature extractor, while the graph model can take spatial correlation into consideration. Moreover, we propose to implement the feature pairwise conditional random field (FPCRF) as a graph model to preserve sharp boundaries and fine-grained segmentation. Experiments are conducted on four different data sets: 1) Planetscope satellite imagery of the cities of Munich, Paris, Rome, and Zurich; 2) ISPRS Benchmark data from the city of Potsdam; 3) Dstl Kaggle data set; and 4) Inria Aerial Image Labeling data of Austin, Chicago, Kitsap County, Western Tyrol, and Vienna. It is found that the proposed end-to-end building footprint generation framework with the FPCRF as the graph model can further improve the accuracy of building footprint generation by using only CNN, which is the current state of the art.
4 December 2024 in IEEE Geoscience and Remote Sensing Magazine
Earth Observation (EO) data analysis has been significantly revolutionized by deep learning (DL), with applications typically limited to grid-like data structures. Graph Neural Networks (GNNs) emerge as an important innovation, propelling DL into the non-Euclidean domain. Naturally, GNNs can effectively tackle the challenges posed by diverse modalities, multiple sensors, and the heterogeneous nature of EO data. To introduce GNNs in the related domains, our review begins by offering fundamental knowledge on GNNs. Then, we summarize the generic problems in EO, to which GNNs can offer potential solutions. Following this, we explore a broad spectrum of GNNs’ applications to scientific problems in Earth systems, covering areas such as weather and climate analysis, disaster management, air quality monitoring, agriculture, land cover classification, hydrological process modeling, and urban modeling. The rationale behind adopting GNNs in these fields is explained, alongside methodologies for organizing graphs and designing favorable architectures for various tasks. Furthermore, we highlight methodological challenges of implementing GNNs in these domains and possible solutions that could guide future research. While acknowledging that GNNs are not a universal solution, we conclude the paper by comparing them with other popular architectures like transformers and analyzing their potential synergies.
23 October 2024 in IEEE Geoscience and Remote Sensing Magazine
Earth observation (EO), aiming at monitoring the state of planet Earth using remote sensing data, is critical for improving our daily lives and living environment. With a growing number of satellites in orbit, an increasing number of datasets with diverse sensors and research domains are being published to facilitate the research of the remote sensing community. This paper presents a comprehensive review of more than 500 publicly published datasets, including research domains like agriculture, land use and land cover, disaster monitoring, scene understanding, vision-language models, foundation models, climate change, and weather forecasting. We systematically analyze these EO datasets from four aspects: volume, resolution distributions, research domains, and the correlation between datasets. Based on the dataset attributes, we propose to measure, rank, and select datasets to build a new benchmark for model evaluation. Furthermore, a new platform for EO, termed EarthNets, is released to achieve a fair and consistent evaluation of deep learning methods on remote sensing data. EarthNets supports standard dataset libraries and cutting-edge deep learning models to bridge the gap between the remote sensing and machine learning communities. Based on this platform, extensive deep-learning methods are evaluated on the new benchmark. The insightful results are beneficial to future research. The platform and dataset collections are publicly available at https://earthnets.github.io/ .
Undocumented building constructions are buildings or stories that were built years ago, but are missing in the official digital cadastral maps (DFK). The detection of undocumented building constructions is essential to urban planning and monitoring. The state of Bavaria, Germany, uses two semi-automatic detection methods for this task that suffer from a high false alarm rate. To solve this problem, we propose a novel framework to detect undocumented building constructions using a Convolutional Neural Network (CNN) and official geodata, including high resolution optical data and the Normalized Digital Surface Model (nDSM). More specifically, an undocumented building pixel is labeled as “building” by the CNN but does not overlap with a building polygon of the DFK. The class of old or new undocumented building can be further separated when a Temporal Digital Surface Model (tDSM) is introduced in the stage of decision fusion. In a further step, undocumented story construction is detected as the pixels that are “building” in both DFK and predicted results from CNN, but shows a height deviation from the tDSM. By doing so, we have produced a seamless map of undocumented building constructions for one-quarter of the state of Bavaria, Germany at a spatial resolution of 0.4 m, which has proved that our framework is robust to detect undocumented building constructions at large-scale. Considering that the official geodata exploited in this research is advantageous because of its high quality and large coverage, a transferability analysis experiment is also designed in our research to investigate the sampling strategies for building detection at large-scale. Our results indicate that building detection results in unseen areas at large-scale can be improved when training samples are collected from different districts. In an area where training samples are available, local training sampless collection and training can save much time and effort.
Accurate and reliable building footprint maps are of great interest in many applications, e.g., urban monitoring, 3D building modeling, and geographical database updating. When compared to traditional methods, the deep-learning-based semantic segmentation networks have largely boosted the performance of building footprint generation. However, they still are not capable of delineating structured building footprints. Most existing studies dealing with this issue are based on two steps, which regularize building boundaries after the semantic segmentation networks are implemented, making the whole pipeline inefficient. To address this, we propose an end-to-end network for the building footprint generation with boundary regularization, which is termed RegGAN. Our method is based on a generative adversarial network (GAN). Specifically, a multiscale discriminator is proposed to distinguish the input between false and true, and a generator is utilized to learn from the discriminator’s response to generate more realistic building footprints. We propose to incorporate regularized loss in the objective function of RegGAN, in order to further enhance sharp building boundaries. The proposed method is evaluated on two datasets with varying spatial resolutions: the INRIA dataset (30 cm/pixel) and the ISPRS dataset (5 cm/pixel). Experimental results show that RegGAN is able to well preserve regular shapes and sharp building boundaries, which outperforms other competitors.