Sequentially Delineation of Rooftops with Holes from VHR Aerial Images Using a Convolutional Recurrent Neural Network

Semantic and instance segmentation methods are commonly used to build extraction from high-resolution images. The semantic segmentation method involves assigning a class label to each pixel in the image, thus ignoring the geometry of the building rooftop, which results in irregular shapes of the roo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wei Huang, Zeping Liu, Hong Tang, Jiayi Ge
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	building extraction rooftop delineation with holes convolutional neural network (CNN) recurrent neural network (RNN) Science Q
Acceso en línea:	https://doaj.org/article/02d214236f074708ab63e707bcb0ead6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:02d214236f074708ab63e707bcb0ead6
record_format	dspace
spelling	oai:doaj.org-article:02d214236f074708ab63e707bcb0ead62021-11-11T18:52:23ZSequentially Delineation of Rooftops with Holes from VHR Aerial Images Using a Convolutional Recurrent Neural Network10.3390/rs132142712072-4292https://doaj.org/article/02d214236f074708ab63e707bcb0ead62021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4271https://doaj.org/toc/2072-4292Semantic and instance segmentation methods are commonly used to build extraction from high-resolution images. The semantic segmentation method involves assigning a class label to each pixel in the image, thus ignoring the geometry of the building rooftop, which results in irregular shapes of the rooftop edges. As for instance segmentation, there is a strong assumption within this method that there exists only one outline polygon along the rooftop boundary. In this paper, we present a novel method to sequentially delineate exterior and interior contours of rooftops with holes from VHR aerial images, where most of the buildings have holes, by integrating semantic segmentation and polygon delineation. Specifically, semantic segmentation from the Mask R-CNN is used as a prior for hole detection. Then, the holes are used as objects for generating the internal contours of the rooftop. The external and internal contours of the rooftop are inferred separately using a convolutional recurrent neural network. Experimental results showed that the proposed method can effectively delineate the rooftops with both one and multiple polygons and outperform state-of-the-art methods in terms of the visual results and six statistical indicators, including IoU, OA, F1, BoundF, RE and Hd.Wei HuangZeping LiuHong TangJiayi GeMDPI AGarticlebuilding extractionrooftop delineation with holesconvolutional neural network (CNN)recurrent neural network (RNN)ScienceQENRemote Sensing, Vol 13, Iss 4271, p 4271 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	building extraction rooftop delineation with holes convolutional neural network (CNN) recurrent neural network (RNN) Science Q
spellingShingle	building extraction rooftop delineation with holes convolutional neural network (CNN) recurrent neural network (RNN) Science Q Wei Huang Zeping Liu Hong Tang Jiayi Ge Sequentially Delineation of Rooftops with Holes from VHR Aerial Images Using a Convolutional Recurrent Neural Network
description	Semantic and instance segmentation methods are commonly used to build extraction from high-resolution images. The semantic segmentation method involves assigning a class label to each pixel in the image, thus ignoring the geometry of the building rooftop, which results in irregular shapes of the rooftop edges. As for instance segmentation, there is a strong assumption within this method that there exists only one outline polygon along the rooftop boundary. In this paper, we present a novel method to sequentially delineate exterior and interior contours of rooftops with holes from VHR aerial images, where most of the buildings have holes, by integrating semantic segmentation and polygon delineation. Specifically, semantic segmentation from the Mask R-CNN is used as a prior for hole detection. Then, the holes are used as objects for generating the internal contours of the rooftop. The external and internal contours of the rooftop are inferred separately using a convolutional recurrent neural network. Experimental results showed that the proposed method can effectively delineate the rooftops with both one and multiple polygons and outperform state-of-the-art methods in terms of the visual results and six statistical indicators, including IoU, OA, F1, BoundF, RE and Hd.
format	article
author	Wei Huang Zeping Liu Hong Tang Jiayi Ge
author_facet	Wei Huang Zeping Liu Hong Tang Jiayi Ge
author_sort	Wei Huang
title	Sequentially Delineation of Rooftops with Holes from VHR Aerial Images Using a Convolutional Recurrent Neural Network
title_short	Sequentially Delineation of Rooftops with Holes from VHR Aerial Images Using a Convolutional Recurrent Neural Network
title_full	Sequentially Delineation of Rooftops with Holes from VHR Aerial Images Using a Convolutional Recurrent Neural Network
title_fullStr	Sequentially Delineation of Rooftops with Holes from VHR Aerial Images Using a Convolutional Recurrent Neural Network
title_full_unstemmed	Sequentially Delineation of Rooftops with Holes from VHR Aerial Images Using a Convolutional Recurrent Neural Network
title_sort	sequentially delineation of rooftops with holes from vhr aerial images using a convolutional recurrent neural network
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/02d214236f074708ab63e707bcb0ead6
work_keys_str_mv	AT weihuang sequentiallydelineationofrooftopswithholesfromvhraerialimagesusingaconvolutionalrecurrentneuralnetwork AT zepingliu sequentiallydelineationofrooftopswithholesfromvhraerialimagesusingaconvolutionalrecurrentneuralnetwork AT hongtang sequentiallydelineationofrooftopswithholesfromvhraerialimagesusingaconvolutionalrecurrentneuralnetwork AT jiayige sequentiallydelineationofrooftopswithholesfromvhraerialimagesusingaconvolutionalrecurrentneuralnetwork
_version_	1718431683517087744

Sequentially Delineation of Rooftops with Holes from VHR Aerial Images Using a Convolutional Recurrent Neural Network

Ejemplares similares