Identifying Damaged Buildings in Aerial Images Using the Object Detection Method

The collapse of buildings caused by the earthquake seriously threatened human lives and safety. So, the quick detection of collapsed buildings from post-earthquake images is essential for disaster relief and disaster damage assessment. Compared with the traditional building extraction methods, the m...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lingfei Shi, Feng Zhang, Junshi Xia, Jibo Xie, Zhe Zhang, Zhenhong Du, Renyi Liu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep learning object detection Yolov4 damaged buildings aerial images Science Q
Acceso en línea:	https://doaj.org/article/dce82f06ed23435999886ee9f1c3d7e6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dce82f06ed23435999886ee9f1c3d7e6
record_format	dspace
spelling	oai:doaj.org-article:dce82f06ed23435999886ee9f1c3d7e62021-11-11T18:50:16ZIdentifying Damaged Buildings in Aerial Images Using the Object Detection Method10.3390/rs132142132072-4292https://doaj.org/article/dce82f06ed23435999886ee9f1c3d7e62021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4213https://doaj.org/toc/2072-4292The collapse of buildings caused by the earthquake seriously threatened human lives and safety. So, the quick detection of collapsed buildings from post-earthquake images is essential for disaster relief and disaster damage assessment. Compared with the traditional building extraction methods, the methods based on convolutional neural networks perform better because it can automatically extract high-dimensional abstract features from images. However, there are still many problems with deep learning in the extraction of collapsed buildings. For example, due to the complex scenes after the earthquake, the collapsed buildings are easily confused with the background, so it is difficult to fully use the multiple features extracted by collapsed buildings, which leads to time consumption and low accuracy of collapsed buildings extraction when training the model. In addition, model training is prone to overfitting, which reduces the performance of model migration. This paper proposes to use the improved classic version of the you only look once model (YOLOv4) to detect collapsed buildings from the post-earthquake aerial images. Specifically, the k-means algorithm is used to optimally select the number and size of anchors from the image. We replace the Resblock in CSPDarkNet53 in YOLOv4 with the ResNext block to improve the backbone’s ability and the performance of classification. Furthermore, to replace the loss function of YOLOv4 with the Focal-EOIU loss function. The result shows that compared with the original YOLOv4 model, our proposed method can extract collapsed buildings more accurately. The AP (average precision) increased from 88.23% to 93.76%. The detection speed reached 32.7 f/s. Our method not only improves the accuracy but also enhances the detection speed of the collapsed buildings. Moreover, providing a basis for the detection of large-scale collapsed buildings in the future.Lingfei ShiFeng ZhangJunshi XiaJibo XieZhe ZhangZhenhong DuRenyi LiuMDPI AGarticledeep learningobject detectionYolov4damaged buildingsaerial imagesScienceQENRemote Sensing, Vol 13, Iss 4213, p 4213 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning object detection Yolov4 damaged buildings aerial images Science Q
spellingShingle	deep learning object detection Yolov4 damaged buildings aerial images Science Q Lingfei Shi Feng Zhang Junshi Xia Jibo Xie Zhe Zhang Zhenhong Du Renyi Liu Identifying Damaged Buildings in Aerial Images Using the Object Detection Method
description	The collapse of buildings caused by the earthquake seriously threatened human lives and safety. So, the quick detection of collapsed buildings from post-earthquake images is essential for disaster relief and disaster damage assessment. Compared with the traditional building extraction methods, the methods based on convolutional neural networks perform better because it can automatically extract high-dimensional abstract features from images. However, there are still many problems with deep learning in the extraction of collapsed buildings. For example, due to the complex scenes after the earthquake, the collapsed buildings are easily confused with the background, so it is difficult to fully use the multiple features extracted by collapsed buildings, which leads to time consumption and low accuracy of collapsed buildings extraction when training the model. In addition, model training is prone to overfitting, which reduces the performance of model migration. This paper proposes to use the improved classic version of the you only look once model (YOLOv4) to detect collapsed buildings from the post-earthquake aerial images. Specifically, the k-means algorithm is used to optimally select the number and size of anchors from the image. We replace the Resblock in CSPDarkNet53 in YOLOv4 with the ResNext block to improve the backbone’s ability and the performance of classification. Furthermore, to replace the loss function of YOLOv4 with the Focal-EOIU loss function. The result shows that compared with the original YOLOv4 model, our proposed method can extract collapsed buildings more accurately. The AP (average precision) increased from 88.23% to 93.76%. The detection speed reached 32.7 f/s. Our method not only improves the accuracy but also enhances the detection speed of the collapsed buildings. Moreover, providing a basis for the detection of large-scale collapsed buildings in the future.
format	article
author	Lingfei Shi Feng Zhang Junshi Xia Jibo Xie Zhe Zhang Zhenhong Du Renyi Liu
author_facet	Lingfei Shi Feng Zhang Junshi Xia Jibo Xie Zhe Zhang Zhenhong Du Renyi Liu
author_sort	Lingfei Shi
title	Identifying Damaged Buildings in Aerial Images Using the Object Detection Method
title_short	Identifying Damaged Buildings in Aerial Images Using the Object Detection Method
title_full	Identifying Damaged Buildings in Aerial Images Using the Object Detection Method
title_fullStr	Identifying Damaged Buildings in Aerial Images Using the Object Detection Method
title_full_unstemmed	Identifying Damaged Buildings in Aerial Images Using the Object Detection Method
title_sort	identifying damaged buildings in aerial images using the object detection method
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/dce82f06ed23435999886ee9f1c3d7e6
work_keys_str_mv	AT lingfeishi identifyingdamagedbuildingsinaerialimagesusingtheobjectdetectionmethod AT fengzhang identifyingdamagedbuildingsinaerialimagesusingtheobjectdetectionmethod AT junshixia identifyingdamagedbuildingsinaerialimagesusingtheobjectdetectionmethod AT jiboxie identifyingdamagedbuildingsinaerialimagesusingtheobjectdetectionmethod AT zhezhang identifyingdamagedbuildingsinaerialimagesusingtheobjectdetectionmethod AT zhenhongdu identifyingdamagedbuildingsinaerialimagesusingtheobjectdetectionmethod AT renyiliu identifyingdamagedbuildingsinaerialimagesusingtheobjectdetectionmethod
_version_	1718431734534504448

Identifying Damaged Buildings in Aerial Images Using the Object Detection Method

Ejemplares similares