Automatic Building Extraction on High-Resolution Remote Sensing Imagery Using Deep Convolutional Encoder-Decoder With Spatial Pyramid Pooling

Liu, Yaohui; Gross, Lutz; Li, Zhiqiang; Li, Xiaoli; Fan, Xiwei; Qi, Wenbao

doi:10.1109/access.2019.2940527

Cited by 102 publications

(71 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As presented in Table 6, the model with ASPP shows an obvious improvement over the model without ASPP across all evaluation metrics. The comparison result demonstrates the efficiency and applicability of the ASPP module as a connector for building extraction from high-resolution aerial images [38,71].…”

Section: B the Effect Of Atrous Spatial Pyramid Poolingmentioning

confidence: 76%

“…The DeepLab_v2 [37] employs atrous convolution and atrous spatial pyramid pooling (ASPP) to enlarge the receptive field on different levels. Liu et al [38] merged the spatial pyramid pooling module into the encoder-decoder architecture with a particular focus on building extraction. The JointNet [39] introduced a new, dense atrous convolution block combining a dense connectivity block and atrous convolution to obtain multi-scale features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Liu

Zhou

et al. 2020

IEEE Access

Self Cite

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

Section: B the Effect Of Atrous Spatial Pyramid Poolingmentioning

confidence: 76%

Section: Introductionmentioning

confidence: 99%

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

Liu

Zhou

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The improvement after the combination of the bright detector and the dark detector of the image is obvious. (Liu et al, 2019). All models used the same test data.…”

Section: Resultsmentioning

confidence: 99%

“…We further conducted a quantitative comparison with different models on the Inria Aerial Image Labeling Dataset. The literature (Liu et al, 2019) quantifies the performance of different methods including SegNet, FCN, U-Net, Tiramisu, FRRN, and USPP on the dataset, using consistent evaluation metrics and the same test data with our method. The results are summarized in Table 2.…”

Section: Resultsmentioning

confidence: 99%

A Method of Building Detection in Remote Sensing Images Based on Deep Learning With Multiple Lightness Detectors

Huang

Zhao

Yao

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Buildings, where most human activities happen, are one of the most important crucial objects in remote sensing images. Extracting building information is of great significance importance for conducting sustainable development-related researches. The extracted building information is a fundamental data source for further researches, including evaluating the living conditions of people, monitoring building conditions, predicting disaster risks and so on. In recent years, convolutional neural networks have been widely employed in building detection, and have gained significant progresses. However, in these automatic detection procedures, the critical brightness information is often neglected, with all buildings simply classified into the same category. To make the building detection more efficient and precise, we propose a simple yet efficient multitask method employing several lightness detectors, each of which is dedicated to the building detection in a specific brightness interval. Experiment results show that the building detection accuracy could be improved by 8.1% with the assistance of the additional lightness information.

show abstract

“…3,4 The full convolutional network (FCN) 5 and its improved network have been applied for land cover classification tasks in high-resolution remote sensing images, which have achieved a certain effect. 6,7 However, the distortion caused by the convolution structure of upsampling and downsampling will inevitably lead to errors, such as edge blurring and holes. Therefore, FCNs often confuse categories and provide unclear boundaries, 8 thereby leading to poor performance in extracting land cover from dense and variable areas.…”

Section: Introductionmentioning

confidence: 99%

Postprocessing framework for land cover classification optimization based on iterative self-adaptive superpixel segmentation

Chu

Chen

Guo³

et al. 2020

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

An increasing number of applications require land cover information from remote sensing images, thereby resulting in an urgent demand for automatic land use and land cover classification. Therefore, effectively improving the accuracy of land cover classification is a main objective in remote sensing image processing. We propose a land cover classification postprocessing framework based on iterative self-adaptive superpixel segmentation (LCPP-ISSS) for remote sensing image data. This framework can further optimize the land cover classification results obtained by neural networks without changing the network structure. First, we propose the iterative self-adaptive superpixel segmentation algorithm for high-resolution remote sensing images to extract the boundary information of different land cover classes. Then, we propose a land cover classification result optimization method based on patch complexity to optimize the classification result by combining the boundary information with the semantic information. In an experiment, we compare the classification accuracy before and after using LCPP-ISSS and with other common methods. The results show that LCPP-ISSS outperforms the dense conditional random field and provides a 4% increase in the mean intersection over union and a 10% increase in overall accuracy. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Automatic Building Extraction on High-Resolution Remote Sensing Imagery Using Deep Convolutional Encoder-Decoder With Spatial Pyramid Pooling

Cited by 102 publications

References 51 publications

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

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

A Method of Building Detection in Remote Sensing Images Based on Deep Learning With Multiple Lightness Detectors

Postprocessing framework for land cover classification optimization based on iterative self-adaptive superpixel segmentation

Contact Info

Product

Resources

About