Fully Convolutional Networks for Multisource Building Extraction From an Open Aerial and Satellite Imagery Data Set

Ji, Shunping; Wei, Sha Xin; Lü, Meng

doi:10.1109/tgrs.2018.2858817

Cited by 895 publications

(456 citation statements)

References 26 publications

Supporting

Mentioning

451

Contrasting

Unclassified

Order By: Relevance

“…We check (a) (b) the whole study area at least twice. We cooperate with the team of WHU building dataset (Ji et al, 2018) to finish the annotation work. After refinement, we create a relatively pure ground-truth dataset, which contains 226,342 buildings, for roof segmentation.…”

Section: Reason For Focusing On Roof Segmentationmentioning

confidence: 99%

TEMPORARY REMOVAL: Aerial imagery for roof segmentation: A large-scale dataset towards automatic mapping of buildings

Chen¹,

Wang²,

Wu³

et al. 2019

ISPRS Journal of Photogrammetry and Remote Sensing

103

View full text Add to dashboard Cite

Section: Reason For Focusing On Roof Segmentationmentioning

confidence: 99%

TEMPORARY REMOVAL: Aerial imagery for roof segmentation: A large-scale dataset towards automatic mapping of buildings

Chen¹,

Wang²,

Wu³

et al. 2019

ISPRS Journal of Photogrammetry and Remote Sensing

103

View full text Add to dashboard Cite

“…However, we don't treat this as a shortcoming, as there are plenty of existing building datasets. Besides the open-source datasets such as the WHU [66], Inria [74] and OSM (open street map) [75], there are global building GIS maps in central or local government branches of surveying, mapping and city planning, which can be used in practice. The critical shortage is the change samples.…”

Section: Discussionmentioning

confidence: 99%

“…The dataset used in this paper comes from the WHU building change detection dataset [66]. The study area is in Christchurch, New Zealand, and covers about 120,000 buildings with various architectural styles and usages.…”

Section: Data Set and Evaluation Measuresmentioning

confidence: 99%

“…Our algorithm was evaluated on a larger urban area compared to most of the relevant studies, which guaranteed more rigorous statistical significance and better practical reference values. Specifically, the experiments were executed on an open-source dataset, namely, the WHU building dataset [66]. The test area covers about 120,000 buildings (including 2007 changed buildings) with diverse architectural styles and usages.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Building Instance Change Detection from Large-Scale Aerial Images using Convolutional Neural Networks and Simulated Samples

et al. 2019

Self Cite

View full text Add to dashboard Cite

We present a novel convolutional neural network (CNN)-based change detection framework for locating changed building instances as well as changed building pixels from very high resolution (VHR) aerial images. The distinctive advantage of the framework is the self-training ability, which is highly important in deep-learning-based change detection in practice, as high-quality samples of changes are always lacking for training a successful deep learning model. The framework consists two parts: a building extraction network to produce a binary building map and a building change detection network to produce a building change map. The building extraction network is implemented with two widely used structures: a Mask R-CNN for object-based instance segmentation, and a multi-scale full convolutional network for pixel-based semantic segmentation. The building change detection network takes bi-temporal building maps produced from the building extraction network as input and outputs a building change map at the object and pixel levels. By simulating arbitrary building changes and various building parallaxes in the binary building map, the building change detection network is well trained without real-life samples. This greatly lowers the requirements of labeled changed buildings, and guarantees the algorithm's robustness to registration errors caused by parallaxes. To evaluate the proposed method, we chose a wide range of urban areas from an open-source dataset as training and testing areas, and both pixel-based and object-based model evaluation measures were used. Experiments demonstrated our approach was vastly superior: without using any real change samples, it reached 63% average precision (AP) at the object (building instance) level. In contrast, with adequate training samples, other methods-including the most recent CNN-based and generative adversarial network (GAN)-based ones-have only reached 25% AP in their best cases.

show abstract

“…And, the lack of large-scale, high-resolution dataset limits the development of accurate building segmentation and outline extraction. Recently, due to rapid evolution of imaging sensors, the availability and accessibility of high-quality remote sensing datasets have increased dramatically [6,7]. On the basis of these datasets, many well-optimized and innovative methods, including different variants of fully convolutional networks(FCNs), have been developed for the purpose of accurate building segmentation [8].…”

Section: Introductionmentioning

confidence: 99%

GEOSEG: A Computer Vision Package for Automatic Building Segmentation and Outline Extraction

Guo

Shao

et al. 2019

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

Recently, deep learning algorithms, especially fully convolutional network based methods, are becoming very popular in the field of remote sensing. However, these methods are implemented and evaluated through various datasets and deep learning frameworks. There has not been a package that covers these methods in a unifying manner. In this study, we introduce a computer vision package termed Geoseg that focus on building segmentation and outline extraction. Geoseg implements over nine state-of-the-art models as well as utility scripts needed to conduct model training, logging, evaluating and visualization. The implementation of Geoseg emphasizes unification, simplicity, and flexibility. The performance and computational efficiency of all implemented methods are evaluated by comparison experiment through a unified, high-quality aerial image dataset.

show abstract

Fully Convolutional Networks for Multisource Building Extraction From an Open Aerial and Satellite Imagery Data Set

Cited by 895 publications

References 26 publications

TEMPORARY REMOVAL: Aerial imagery for roof segmentation: A large-scale dataset towards automatic mapping of buildings

TEMPORARY REMOVAL: Aerial imagery for roof segmentation: A large-scale dataset towards automatic mapping of buildings

Building Instance Change Detection from Large-Scale Aerial Images using Convolutional Neural Networks and Simulated Samples

GEOSEG: A Computer Vision Package for Automatic Building Segmentation and Outline Extraction

Contact Info

Product

Resources

About