基于几何先验约束的高点多视角损毁建筑物检测方法

隋百凯; 曹云刚; 程海波; 杨鹏; 曾雅慧; 谢亚坤; 朱军

doi:10.13203/j.whugis20240297

您当前的位置：

首页 >

文章列表页 >

基于几何先验约束的高点多视角损毁建筑物检测方法

综述 | 更新时间：2026-11-05

- 基于几何先验约束的高点多视角损毁建筑物检测方法
- Damaged Building Detection Method in Multi-view Scenes Based on Geometric Prior Constraints
- 武汉大学学报（信息科学版） 2025年50卷第6期页码：1088-1099
- 作者机构：
  
  西南交通大学地球科学与工程学院，四川成都，611756
- 作者简介：
  
  隋百凯，博士，研究方向为遥感图像智能处理与分析。13012482890@163.com
  曹云刚，博士，教授。yungang@swjtu.edu.cn
- 基金信息：
  
  国家重点研发计划(2022YFC3005703)
- DOI：10.13203/j.whugis20240297
  中图分类号： P237
- 收稿：2024-12-04，
  
  纸质出版：2025-06-05
- 稿件说明：
移动端阅览
隋百凯,曹云刚,程海波，等.基于几何先验约束的高点多视角损毁建筑物检测方法[J].武汉大学学报（信息科学版）,2025,50(6):1088-1099.

SUI Baikai,CAO Yungang,CHENG Haibo,et al.Damaged Building Detection Method in Multi-view Scenes Based on Geometric Prior Constraints[J].Geomatics and Information Science of Wuhan University,2025,50(6):1088-1099.
隋百凯,曹云刚,程海波，等.基于几何先验约束的高点多视角损毁建筑物检测方法[J].武汉大学学报（信息科学版）,2025,50(6):1088-1099. DOI：10.13203/j.whugis20240297

SUI Baikai,CAO Yungang,CHENG Haibo,et al.Damaged Building Detection Method in Multi-view Scenes Based on Geometric Prior Constraints[J].Geomatics and Information Science of Wuhan University,2025,50(6):1088-1099. DOI：10.13203/j.whugis20240297

摘要

建筑物是重要的受灾体之一，损毁建筑物检测与空间映射是应急救援的关键。高点多视角遥感装备为损毁建筑物信息提取提供了一种有效手段，但面临着多视角特征表达不一、建筑信息不全等问题，提出了一种几何先验约束的多视角场景下的损毁建筑物检测方法。首先，基于长距离高点监测摄像机、无人机以及网络搜集等方式构建多视角场景损毁建筑物实例分割数据集；其次，设计了一种结合阶段感知特征增强和细粒度特征对齐的跨视角域建筑特征同步模型，对不同视角下的建筑物进行微观特征同步；然后，提出了一种基于Canny边缘检测和熵混乱程度的实例分割模型，对损毁建筑物进行精准检测；最后，设计了一种基于垂直/水平视场切割的几何约束的空间映射方法，将目标检测信息映射到地理空间场景中。实验结果表明，与现有方法相比，所提方法对于不同视角下的建筑及损毁建筑检测效果更好，边界框平均精度均值和像素平均精度均值分别达到50.33%和46.69%；在预测边界框与真实边界框的交并比阈值为50%时，所提方法在目标检测和实例分割任务中的平均精度均值分别达到83.10%和81.91%。在空间映射方面，所提方法能够较为精准地将图像检测的损毁建筑映射到真实地理位置，为应急救援实时指挥提供技术支持。

Abstract

Objectives

Buildings constitute a critical component that is adversely impacted by disasters. The intelligent detection of damaged building information

coupled with the alignment of 2D to 3D scenes

is pivotal in emergency rescue efforts.

Methods

This paper proposes an innovative method for detecting damaged buildings from multiple perspectives

leveraging geometric prior constraints across various fields of view. First

a large amount of data collected from long-distance high-point monitoring cameras

drones and online gathering are generated by the simulated image generation to construct a multi-view scene data-set for damaged building instance segmentation. This dataset includes data from various perspectives

such as ground-level view

high-point ground view

and low-altitude high-point view. Then

a cross-view domain building feature synchronization model that combines phase-aware feature enhancement and fine-grained feature alignment is designed. This model performs micro-feature synchronization on buildings under different perspectives

and it consists of a multi-branch phase-aware feature enhancement module and a deep-shallow feature synchronization module that aggregates perception and spatial-channel attention. The aim is to enhance deep features rich in semantic information such as building shape and category

as well as deeper features

and to focus on shallow features rich in spatial information such as building edges

textures

and lines. It addresses the spatial and semantic differences brought by features from different perspectives. Subsequently

based on the transformer attention network

an instance segmentation model that takes into account Canny edge detection and entropy disorder is proposed

further enhancing the feature expression of damaged buildings and achieving precise detection of damaged structures. The network consists of three modules: a pixel-level feature extraction module

a transformer attention extraction module

and a detection module. The detection results include both the pixel-level segmentation categories of buildings and the bounding box target detection information for each building. It provides rich data support for subsequent 2D to 3D geographic scene matching and mapping. Finally

a geometric constraint-based position matching method using vertical and horizontal field of view segmentation is designed. This method projects target detection information onto a 3D geographic information scene. It is tailored for cameras rich in angular information

including ground cameras

high-point gimbal cameras

and drone cameras. By leveraging the actual geographic location of cameras and the horizontal and tilt angles of the observed targets

it infers and calculates the real geographic locations of detection targets

and then performs scene matching and mapping based on a 3D model using ray cutting techniques.

Results

The empirical findings reveal that the proposed method outperforms current approaches in detecting buildings and damaged structures from multiple perspectives. The mean average precision of bounding boxes (bbox_mAP) and mean average precision of segmentation (seg_mAP) achieve 50.33% and 46.69%

respectively. At intersection over union (IoU) threshold of 50%

bbox_mAP50 and seg_mAP50 are 83.10% and 81.91%

respectively

showing a signi-ficant enhancement in detection accuracy. In the case studies

high-point long-distance monitoring cameras are used to capture image data

and instance segmentation of damaged and normal buildings is performed to obtain detection results. The detected buildings are then matched to a 3D geographic scene using the proposed geographic matching method

which utilizes vertical and horizontal field of view segmentation and enables the precise matching and mapping of 2D detection results to 3D geographic scene.

Conclusions

The proposed method can not only effectively improve the detection effect of damaged buildings in the high-point multi-view images

but also accurately match with the 3D geographic scene to provide technical support for the emergency rescue command at the disaster site.

关键词

Keywords

references

RUPNIK E ， NEX F ， TOSCHI I ， et al . Contextual Classification Using Photometry and Elevation Data for Damage Detection After an Earthquake Event ［J］. European Journal of Remote Sensing ， 2018 ， 51 （ 1 ）： 543 - 557 .

DUBOIS D ， LEPAGE R . Fast and Efficient Evaluation of Building Damage from very High Resolution Optical Satellite Images ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ， 2014 ， 7 （ 10 ）： 4167 - 4176 .

LU C H ， NI C F ， CHANG C P ， et al . Coherence Difference Analysis of Sentinel-1 SAR Interferogram to Identify Earthquake-Induced Disasters in Urban Areas ［J］. Remote Sensing ， 2018 ， 10 （ 8 ）： 1318 .

WU X ， GHABOUSSI J ， GARRETT J H . Use of Neural Networks in Detection of Structural Damage ［J］. Computers & Structures ， 1992 ， 42 （ 4 ）： 649 - 659 .

FANG X ， LUO H ， TANG J . Structural Damage Detection Using Neural Network with Learning Rate Improvement ［J］. Computers & Structures ， 2005 ， 83 （ 25/26 ）： 2150 - 2161 .

KERLE N ， NEX F ， DUARTE D ， et al . UAV-Based Structural Damage Mapping – Results from 6 Years of Research in Two European Projects ［J］. The International Archives of the Photogrammetry， Remote Sensing and Spatial Information Sciences ， 2019 ， XLII-3/W 8 ： 187 - 194 .

FUJITA A ， SAKURADA K ， IMAIZUMI T ， et al . Damage Detection from Aerial Images via Convolutional Neural Networks ［C］// The 15th IAPR International Conference on Machine Vision Applications （MVA）， Nagoya， Japan ， 2017 .

VOLPI M ， TUIA D . Dense Semantic Labeling of Subdecimeter Resolution Images with Convolutional Neural Networks ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2017 ， 55 （ 2 ）： 881 - 893 .

DUARTE D ， NEX F ， KERLE N ， et al . Multi-resolution Feature Fusion for Image Classification of Building Damages with Convolutional Neural Networks ［J］. Remote Sensing ， 2018 ， 10 ： 1636 .

MA H J ， LIU Y L ， REN Y H ， et al . Improved CNN Classification Method for Groups of Buildings Damaged by Earthquake， Based on High Resolution Remote Sensing Images ［J］. Remote Sensing ， 2020 ， 12 （ 2 ）： 260 .

陈博，宋闯，陈毅，等 . 2023年甘肃积石山Ms 6.2地震同震滑坡和建筑物损毁情况应急识别与影响因素研究［J］. 武汉大学学报（信息科学版）， 2025 ， 50 （ 2 ）： 322 - 332 .

CHEN Bo ， SONG Chuang ， CHEN Yi ， et al . Emergency Identification and Influencing Factor Analysis of Coseismic Landslides and Building Damages Induced by the 2023 Ms 6.2 Jishishan（Gansu， China） Earthquake ［J］. Geomatics and Information Science of Wuhan University ， 2025 ， 50 （ 2 ）： 322 - 332 .

KERLE N ， HOFFMAN R R . Collaborative Damage Mapping for Emergency Response： The Role of Cognitive Systems Engineering ［J］. Natural Hazards and Earth System Sciences ， 2013 ， 13 （ 1 ）： 97 - 113 .

KERLE N . Satellite-Based Damage Mapping Following the 2006 Indonesia Earthquake—How Accurate Was It？［J］. International Journal of Applied Earth Observation and Geoinformation ， 2010 ， 12 （ 6 ）： 466 - 476 .

FATHALLA R ， VOGIATZIS G . A Deep Learning Pipeline for Semantic Facade Segmentation ［C］// British Machine Vision Conference ， London， UK ， 2017 .

WENG X ， YAN Y ， CHEN S ， et al . Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes ［J］. IEEE Transactions on Circuits and Systems for Video Technology ， 2022 ， 32 （ 7 ）： 4444 - 4459 .

MOHAN A ， POOBAL S . Crack Detection Using Image Processing： A Critical Review and Analysis ［J］. Alexandria Engineering Journal ， 2018 ， 57 （ 2 ）： 787 - 798 .

SHAN B H ， ZHENG S J ， OU J P . A Stereovision-Based Crack Width Detection Approach for Concrete Surface Assessment ［J］. KSCE Journal of Civil Engineering ， 2016 ， 20 （ 2 ）： 803 - 812 .

PEREIRA F C ， PEREIRA C E . Embedded Image Processing Systems for Automatic Recognition of Cracks Using UAVs ［J］. IFAC-PapersOnLine ， 2015 ， 48 （ 10 ）： 16 - 21 .

LOVERDOS D ， SARHOSIS V . Automatic Image-Based Brick Segmentation and Crack Detection of Masonry Walls Using Machine Learning ［J］. Automation in Construction ， 2022 ， 140 ： 104389 .

涂继辉，眭海刚，吕枘蓬，等 . 基于基尼系数的倾斜航空影像中建筑物立面损毁检测［J］. 武汉大学学报（信息科学版）， 2017 ， 42 （ 12 ）： 1744 - 1748 .

TU Jihui ， SUI Haigang ， LÜ Ruipeng ， et al . Building Facade Damage Detection Based on the Gini Index from Oblique Aerial Images ［J］. Geoma⁃tics and Information Science of Wuhan University ， 2017 ， 42 （ 12 ）： 1744 - 1748 .

眭海刚，黄立洪，刘超贤 . 利用具有注意力的Mask R-CNN检测震害建筑物立面损毁［J］. 武汉大学学报（信息科学版）， 2020 ， 45 （ 11 ）： 1660 - 1668 .

SUI Haigang ， HUANG Lihong ， LIU Chaoxian . Detecting Building Facade Damage Caused by Earthquake Using CBAM-Improved Mask R-CNN ［J］. Geomatics and Information Science of Wuhan University ， 2020 ， 45 （ 11 ）： 1660 - 1668 .

CHENG B W ， MISRA I ， SCHWING A G ， et al . Masked-Attention Mask Transformer for Universal Image Segmentation ［C］// IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）， New Orleans， USA ， 2022 .

HE K M ， GKIOXARI G ， DOLLÁR P ， et al . Mask R-CNN ［C］// IEEE International Conference on Computer Vision （ICCV）， Venice， Italy ， 2017 .

LIU Z ， LIN Y T ， CAO Y ， et al . Swin Transformer： Hierarchical Vision Transformer Using Shifted Windows ［C］// IEEE/CVF International Conference on Computer Vision （ICCV）， Montreal， Canada ， 2021 .

LIU J J ， HOU Q B ， CHENG M M ， et al . Improving Convolutional Networks with Self-Calibrated Convolutions ［C］// IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）， Seattle， USA ， 2020 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向任务对齐的遥感场景图像非监督域适应分类

海洋目标辐射基准传递不确定度研究进展

复杂空间机器人自主测绘的现状与挑战

时空智能学：理论与应用

多尺度地理空间数据更新方法概述