Next Article in Journal
The Intriguing Structure of Stripes in GRACE Geopotential Models
Previous Article in Journal
Predicting the Impact of Future Land Use and Climate Change on Potential Soil Erosion Risk in an Urban District of the Harare Metropolitan Province, Zimbabwe
Previous Article in Special Issue
Transferable Deep Learning from Time Series of Landsat Data for National Land-Cover Mapping with Noisy Labels: A Case Study of China
Technical Note

Integrating EfficientNet into an HAFNet Structure for Building Mapping in High-Resolution Optical Earth Observation Data

1
CNIT, Pavia Unit, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy
2
Department of Geographic Information Science, University of Nanjing, Nanjing 210093, China
*
Author to whom correspondence should be addressed.
F.D. is also with Ticinum Aerospace, a spin-off company from the University of Pavia, 27100 Pavia, Italy.
Academic Editors: Antonio Robles-Kelly, Ajmal Mian, Jun Zhou, Naveed Akhtar, Pedram Ghamisi and Tat-Jun Chin
Remote Sens. 2021, 13(21), 4361; https://doi.org/10.3390/rs13214361
Received: 18 August 2021 / Revised: 21 October 2021 / Accepted: 25 October 2021 / Published: 29 October 2021
(This article belongs to the Special Issue Deep Learning for Remote Sensing Data)
Automated extraction of buildings from Earth observation (EO) data is important for various applications, including updating of maps, risk assessment, urban planning, and policy-making. Combining data from different sensors, such as high-resolution multispectral images (HRI) and light detection and ranging (LiDAR) data, has shown great potential in building extraction. Deep learning (DL) is increasingly used in multi-modal data fusion and urban object extraction. However, DL-based multi-modal fusion networks may under-perform due to insufficient learning of “joint features” from multiple sources and oversimplified approaches to fusing multi-modal features. Recently, a hybrid attention-aware fusion network (HAFNet) has been proposed for building extraction from a dataset, including co-located Very-High-Resolution (VHR) optical images and light detection and ranging (LiDAR) joint data. The system reported good performances thanks to the adaptivity of the attention mechanism to the features of the information content of the three streams but suffered from model over-parametrization, which inevitably leads to long training times and heavy computational load. In this paper, the authors propose a restructuring of the scheme, which involved replacing VGG-16-like encoders with the recently proposed EfficientNet, whose advantages counteract exactly the issues found with the HAFNet scheme. The novel configuration was tested on multiple benchmark datasets, reporting great improvements in terms of processing times, and also in terms of accuracy. The new scheme, called HAFNetE (HAFNet with EfficientNet integration), appears indeed capable of achieving good results with less parameters, translating into better computational efficiency. Based on these findings, we can conclude that, given the current advancements in single-thread schemes, the classical multi-thread HAFNet scheme could be effectively transformed by the HAFNetE scheme by replacing VGG-16 with EfficientNet blocks on each single thread. The remarkable reduction achieved in computational requirements moves the system one step closer to on-board implementation in a possible, future “urban mapping” satellite constellation. View Full-Text
Keywords: attention mechanism; building mapping; data fusion; EfficientNet; HAFNet; high-resolution imagery (HRI); light detection and ranging (LiDAR); mapping; urban areas attention mechanism; building mapping; data fusion; EfficientNet; HAFNet; high-resolution imagery (HRI); light detection and ranging (LiDAR); mapping; urban areas
Show Figures

Figure 1

MDPI and ACS Style

Ferrari, L.; Dell’Acqua, F.; Zhang, P.; Du, P. Integrating EfficientNet into an HAFNet Structure for Building Mapping in High-Resolution Optical Earth Observation Data. Remote Sens. 2021, 13, 4361. https://doi.org/10.3390/rs13214361

AMA Style

Ferrari L, Dell’Acqua F, Zhang P, Du P. Integrating EfficientNet into an HAFNet Structure for Building Mapping in High-Resolution Optical Earth Observation Data. Remote Sensing. 2021; 13(21):4361. https://doi.org/10.3390/rs13214361

Chicago/Turabian Style

Ferrari, Luca, Fabio Dell’Acqua, Peng Zhang, and Peijun Du. 2021. "Integrating EfficientNet into an HAFNet Structure for Building Mapping in High-Resolution Optical Earth Observation Data" Remote Sensing 13, no. 21: 4361. https://doi.org/10.3390/rs13214361

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop