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 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.

[1]  Yi-Fan Zhang,et al.  Focal and Efficient IOU Loss for Accurate Bounding Box Regression , 2021, ArXiv.

[2]  Danqing Xu,et al.  Improved YOLO-V3 with DenseNet for Multi-Scale Remote Sensing Target Detection , 2020, Sensors.

[3]  Jie Gong,et al.  Community-scale multi-level post-hurricane damage assessment of residential buildings using multi-temporal airborne LiDAR data , 2019, Automation in Construction.

[4]  B. Murgante,et al.  Early estimation of ground displacements and building damage after seismic events using SAR and LiDAR data: The case of the Amatrice earthquake in central Italy, on 24th August 2016 , 2020 .

[5]  Chenkai Shen,et al.  A real-time detection approach for bridge cracks based on YOLOv4-FPM , 2021 .

[6]  Xiwei Fan,et al.  Estimating earthquake-damage areas using Landsat-8 OLI surface reflectance data , 2019, International Journal of Disaster Risk Reduction.

[7]  Ali Mohammadzadeh,et al.  Evaluation of effectiveness of three fuzzy systems and three texture extraction methods for building damage detection from post-event LiDAR data , 2018, Int. J. Digit. Earth.

[8]  Rui Zhang,et al.  Automatic Detection of Earthquake-Damaged Buildings by Integrating UAV Oblique Photography and Infrared Thermal Imaging , 2020, Remote. Sens..

[9]  Tingbo Hou,et al.  MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision , 2020, ArXiv.

[10]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[11]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[12]  En Li,et al.  Apple detection during different growth stages in orchards using the improved YOLO-V3 model , 2019, Comput. Electron. Agric..

[13]  Hong-Yuan Mark Liao,et al.  YOLOv4: Optimal Speed and Accuracy of Object Detection , 2020, ArXiv.

[14]  Masashi Matsuoka,et al.  SAR and LIDAR Datasets for Building Damage Evaluation Based on Support Vector Machine and Random Forest Algorithms—A Case Study of Kumamoto Earthquake, Japan , 2020, Applied Sciences.

[15]  Hiroyuki Miura,et al.  Deep Learning-Based Identification of Collapsed, Non-Collapsed and Blue Tarp-Covered Buildings from Post-Disaster Aerial Images , 2020, Remote. Sens..

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[18]  Xing Qiu,et al.  Damaged buildings recognition of post-earthquake high-resolution remote sensing images based on feature space and decision tree optimization , 2020, Comput. Sci. Inf. Syst..

[19]  Fumio Yamazaki,et al.  Novel Unsupervised Classification of Collapsed Buildings Using Satellite Imagery, Hazard Scenarios and Fragility Functions , 2018, Remote. Sens..

[20]  Bin Wang,et al.  Integration of super-pixel segmentation and deep-learning methods for evaluating earthquake-damaged buildings using single-phase remote sensing imagery , 2020, International Journal of Remote Sensing.

[21]  Peijun Li,et al.  Extraction of urban building damage using spectral, height and corner information from VHR satellite images and airborne LiDAR data , 2017 .

[22]  Qiang Li,et al.  Building Earthquake Damage Analysis Using Terrestrial Laser Scanning Data , 2019, Advances in Civil Engineering.

[23]  Manfred F. Buchroithner,et al.  Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model , 2020 .

[24]  Wei Chen,et al.  GIS-Based Gully Erosion Susceptibility Mapping: A Comparison of Computational Ensemble Data Mining Models , 2020, Applied Sciences.

[25]  M. Janalipour,et al.  A novel and automatic framework for producing building damage map using post-event LiDAR data , 2019, International Journal of Disaster Risk Reduction.

[26]  Zhenhong Du,et al.  Building Damage Detection Using U-Net with Attention Mechanism from Pre- and Post-Disaster Remote Sensing Datasets , 2021, Remote. Sens..

[27]  Guanghui He,et al.  Ship detection based on fused features and rebuilt YOLOv3 networks in optical remote-sensing images , 2021 .