Refined extraction of buildings with the semantic edge-assisted approach from very high-resolution remotely sensed imagery

Xia, Liegang; Zhang, Xiongbo; Zhang, Junxia; Wu, Wei; Gao, Xingyu

doi:10.1080/01431161.2020.1775322

Cited by 14 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The semantic edge-assisted methods perform edge refinement through a combined classic edge detection model and semantic segmentation/object detection networks [22], [23]. Marmanis et al [22] developed deep convolutional neural network models combining the SegNet model and the HED edge detection model to explicitly extract the class boundaries to boost the semantic segmentation performance of VHR aerial images.…”

Section: Related Workmentioning

confidence: 99%

“…Marmanis et al [22] developed deep convolutional neural network models combining the SegNet model and the HED edge detection model to explicitly extract the class boundaries to boost the semantic segmentation performance of VHR aerial images. Xia et al [23] proposed a refined building footprint extraction approach based on the Faster R-CNN and the CASENet edge detection model. In addition, they proposed a boundary repair algorithm that further refines incomplete building edges with distinct advantages in terms of the quality of extracted building boundaries against Mask R-CNN.…”

Section: Related Workmentioning

confidence: 99%

“…However, they are usually complicated methods. Some studies improve the extracted boundary quality with semantic edge detection networks [22], [23]. They have achieved high quality results, but buildings have highly structured shapes and boundaries rather than all the edges of objects.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CGSANet: A Contour-Guided and Local Structure-Aware Encoder–Decoder Network for Accurate Building Extraction From Very High-Resolution Remote Sensing Imagery

Chen

Shi

Zhou

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Extracting buildings accurately from very highresolution (VHR) remote sensing imagery is challenging due to diverse building appearances, spectral variability, and complex background in VHR remote sensing images. Recent studies mainly adopt a variant of the Fully Convolutional Network (FCN) with an encoder-decoder architecture to extract buildings, which has shown promising improvement over conventional methods. However, FCN-based encoder-decoder models still fail to fully utilize the implicit characteristics of building shapes. This adversely affects the accurate localization of building boundaries, which is particularly relevant in building mapping. A contour-guided and local structure-aware encoder-decoder network (CGSANet) is proposed to extract buildings with more accurate boundaries. CGSANet is a multi-task network composed of a contour-guided (CG) and a multi-region guided (MRG) module. The CG module is supervised by a building contour that effectively learns building contour-related spatial features to retain the shape pattern of buildings. The MRG module is deeply supervised by four building regions that further capture multiscale and contextual features of buildings. In addition, a hybrid loss function was designed to improve the structure learning ability of CGSANet. These three improvements benefit each other synergistically to produce high-quality building extraction results. Experiment results on the WHU and NZ32km2 building datasets demonstrate that compared with the tested algorithms, CGSANet can produce more accurate building extraction results and achieve the best intersection over union (IoU) value 91.55% and 90.02%, respectively. Experiments on the INRIA building dataset further demonstrate the ability for generalization of the proposed framework, indicating great practical potential.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

CGSANet: A Contour-Guided and Local Structure-Aware Encoder–Decoder Network for Accurate Building Extraction From Very High-Resolution Remote Sensing Imagery

Chen

Shi

Zhou

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Wei et al [ 29 ] used the U2-net [ 30 ] semantic segmentation model to detect building edges and replaced the original loss function with a multi-class cross-entropy loss function to directly generate a binary map with edges and backgrounds. Xia et al [ 31 ] proposed a building edge detection method that uses Faster R-CNN [ 32 ] to detect the bounding box of the building and uses the bounding box to assist in the repair of the broken line to completely extract the building outline. These methods are still fully supervised methods, and the labeling of high-resolution remote sensing image samples is more complicated than that of natural images; thus, research into edge extraction methods with a small number of samples is more necessary.…”

Section: Related Workmentioning

confidence: 99%

Enhanced Semantic Information Transfer of Multi-Domain Samples: An Adversarial Edge Detection Method Using Few High-Resolution Remote Sensing Images

Xia

Yang

Zhang

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Edge detection of ground objects is a typical task in the field of remote sensing and has advantages in accomplishing many complex ground object extraction tasks. Although recent mainstream edge detection methods based on deep learning have significant effects, these methods have a very high dependence on the quantity and quality of samples. Moreover, using datasets from other domains in detection tasks often leads to degraded network performance due to variations in the ground objects in different regions. If this problem can be solved to allow datasets from other domains to be reused, the number of labeled samples required in the new task domain can be reduced, thereby shortening the task cycle and reducing task costs. In this paper, we propose a weakly supervised domain adaptation method to address the high dependence of edge extraction networks on samples. The domain adaptation is performed on the edge level and the semantic level, which prevents deviations in the semantic features that are caused by the overgeneralization of edge features. Additionally, the effectiveness of our proposed domain adaptation module is verified. Finally, we demonstrate the superior edge extraction performance of our method in the SEGOS edge extraction network in contrast to other edge extraction methods.

show abstract

“…The extraction of building boundaries is of great significance to social-economic development and urban management [1,2]. Efficient building boundaries extraction from remote sensing imagery has been one of the critical tasks in the domain of interpretation of remote sensing research [3,4].…”

Section: Introductionmentioning

confidence: 99%

Regularized Building Boundary Extraction From Remote Sensing Imagery Based on Augment Feature Pyramid Network and Morphological Constraint

Feng¹,

Xie²,

Xiong³

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Refined extraction of buildings with the semantic edge-assisted approach from very high-resolution remotely sensed imagery

Cited by 14 publications

References 22 publications

CGSANet: A Contour-Guided and Local Structure-Aware Encoder–Decoder Network for Accurate Building Extraction From Very High-Resolution Remote Sensing Imagery

CGSANet: A Contour-Guided and Local Structure-Aware Encoder–Decoder Network for Accurate Building Extraction From Very High-Resolution Remote Sensing Imagery

Enhanced Semantic Information Transfer of Multi-Domain Samples: An Adversarial Edge Detection Method Using Few High-Resolution Remote Sensing Images

Regularized Building Boundary Extraction From Remote Sensing Imagery Based on Augment Feature Pyramid Network and Morphological Constraint

Contact Info

Product

Resources

About