Semantic Segmentation-Based Building Footprint Extraction Using Very High-Resolution Satellite Images and Multi-Source GIS Data

Li, Weijia; He, Conghui; Fang, Jiayuan; Zheng, Juepeng; Fu, Haohuan; Yu, Le

doi:10.3390/rs11040403

Cited by 161 publications

(80 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This process generated nine feature spaces, and consequently, nine classification results, which were evaluated through the validation set derived from the point samples. The result that presented the highest F1 score, which was a metric capable of simultaneously considering omission and commission errors [46], was considered as the best mapping produced with the random forest, which was used in the accuracy analysis and in the comparison with the other pasture mappings (i.e., produced via deep learning approaches).…”

Section: Feature Engineeringmentioning

confidence: 99%

Next Generation Mapping: Combining Deep Learning, Cloud Computing, and Big Remote Sensing Data

et al. 2019

View full text Add to dashboard Cite

The rapid growth of satellites orbiting the planet is generating massive amounts of data for Earth science applications. Concurrently, state-of-the-art deep-learning-based algorithms and cloud computing infrastructure have become available with a great potential to revolutionize the image processing of satellite remote sensing. Within this context, this study evaluated, based on thousands of PlanetScope images obtained over a 12-month period, the performance of three machine learning approaches (random forest, long short-term memory-LSTM, and U-Net). We applied these approaches to mapped pasturelands in a Central Brazil region. The deep learning algorithms were implemented using TensorFlow, while the random forest utilized the Google Earth Engine platform. The accuracy assessment presented F1 scores for U-Net, LSTM, and random forest of, respectively, 96.94%, 98.83%, and 95.53% in the validation data, and 94.06%, 87.97%, and 82.57% in the test data, indicating a better classification efficiency using the deep learning approaches. Although the use of deep learning algorithms depends on a high investment in calibration samples and the generalization of these methods requires further investigations, our results suggest that the neural network architectures developed in this study can be used to map large geographic regions that consider a wide variety of satellite data (e.g., PlanetScope, Sentinel-2, Landsat-8).

show abstract

Section: Feature Engineeringmentioning

confidence: 99%

Next Generation Mapping: Combining Deep Learning, Cloud Computing, and Big Remote Sensing Data

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Du et al (2015) combined VHR images with GIS map data in a random forest method with fine categories in order to improve the classification of urban buildings [17]. Li et al (2019) combined VHR satellite images in the SpaceNet dataset with GIS map data from multiple sources of map data [18] (e.g., OpenStreetMap (OSM) [19], Google Maps [20], and MapWorld [21]) and explored the enhancement of the total F1-score compared with the methods in the previous SpaceNet Building Detection Competition. We found that semantic segmentation using GIS map data and VHR satellite images or high definition aerial photographs was useful for building extraction.…”

Section: Review and Objectivesmentioning

confidence: 99%

“…Second, we selected GIS map data, including the footprints of individual buildings in Mashiki town, near the time of the earthquake to understand the situation of existing buildings before the earthquake, and to label demolished and remaining buildings by analysis and visual interpretation of satellite images. The OSM data contained suitable building footprint information, because OSM was used in previous research for the improvement of building detection [18]. We found the OSM data that were representing the existing buildings in Mashiki town before the earthquake.…”

Section: Preparation Of Satellite Images and Gis Map Datamentioning

confidence: 99%

Time Series GIS Map Dataset of Demolished Buildings in Mashiki Town after the 2016 Kumamoto, Japan Earthquake

Kushiyama

Matsuoka

2019

Remote Sensing

View full text Add to dashboard Cite

After a large-scale disaster, many damaged buildings are demolished and treated as disaster waste. Though the weight of disaster waste was estimated two months after the 2016 earthquake in Kumamoto, Japan, the estimated weight was significantly different from the result when the disaster waste disposal was completed in March 2018. The amount of disaster waste generated is able to be estimated by an equation by multiplying the total number of severely damaged and partially damaged buildings by the coefficient of generated weight per building. We suppose that the amount of disaster waste would be affected by the conditions of demolished buildings, namely, the areas and typologies of building structures, but this has not yet been clarified. Therefore, in this study, we aimed to use geographic information system (GIS) map data to create a time series GIS map dataset with labels of demolished and remaining buildings in Mashiki town for the two-year period prior to the completion of the disaster waste disposal. We used OpenStreetMap (OSM) data as the base data and time series SPOT images observed in the two years following the Kumamoto earthquake to label all demolished and remaining buildings in the GIS map dataset. To effectively label the approximately 16,000 buildings in Mashiki town, we calculated an indicator that shows the possibility of the buildings to be classified as the remaining and demolished buildings from a change of brightness in SPOT images. We classified 5701 demolished buildings from 16,106 buildings, as of March 2018, by visual interpretation of the SPOT and Pleiades images with reference to this indicator. We verified that the number of demolished buildings was almost the same as the number reported by Mashiki municipality. Moreover, we assessed the accuracy of our proposed method: The F-measure was higher than 0.9 using the training dataset, which was verified by a field survey and visual interpretation, and included the labels of the 55 demolished and 55 remaining buildings. We also assessed the accuracy of the proposed method by applying it to all the labels in the OSM dataset, but the F-measure was 0.579. If we applied test data including balanced labels of the other 100 demolished and 100 remaining buildings, which were other than the training data, the F-measure was 0.790 calculated from the SPOT image of 25 March 2018. Our proposed method performed better for the balanced classification but not for imbalanced classification. We studied the examples of image characteristics of correct and incorrect estimation by thresholding the indicator.

show abstract

“…remains a difficulty and challenge for accurate building extraction. Thus, the efficiency and accuracy of automatic building extraction are still difficult archive and remain a challenging objective which attracts huge research interests [6].…”

Section: Introductionmentioning

confidence: 99%

ARC-Net: An Efficient Network for Building Extraction From High-Resolution Aerial Images

Liu

Zhou

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Automatic building extraction based on high-resolution aerial images has important applications in urban planning and environmental management. In recent years advances and performance improvements have been achieved in building extraction through the use of deep learning methods. However, the design of existing models focuses attention to improve accuracy through an overflowing number of parameters and complex structure design, resulting in large computational costs during the learning phase and low inference speed. To address these issues, we propose a new, efficient end-to-end model, called ARC-Net. The model includes residual blocks with asymmetric convolution (RBAC) to reduce the computational cost and to shrink the model size. In addition, dilated convolutions and multi-scale pyramid pooling modules are utilized to enlarge the receptive field and to enhance accuracy. We verify the performance and efficiency of the proposed ARC-Net on the INRIA Aerial Image Labeling dataset and WHU building dataset. Compared to available deep learning models, the proposed ARC-Net demonstrates better segmentation performance with less computational costs. This indicates that the proposed ARC-Net is both effective and efficient in automatic building extraction from high-resolution aerial images.

show abstract

Semantic Segmentation-Based Building Footprint Extraction Using Very High-Resolution Satellite Images and Multi-Source GIS Data

Cited by 161 publications

References 57 publications

Next Generation Mapping: Combining Deep Learning, Cloud Computing, and Big Remote Sensing Data

Next Generation Mapping: Combining Deep Learning, Cloud Computing, and Big Remote Sensing Data

Time Series GIS Map Dataset of Demolished Buildings in Mashiki Town after the 2016 Kumamoto, Japan Earthquake

ARC-Net: An Efficient Network for Building Extraction From High-Resolution Aerial Images

Contact Info

Product

Resources

About