Automated regional seismic damage assessment of buildings using an unmanned aerial vehicle and a convolutional neural network

On September 28, 2018, a large earthquake and its accompanying tsunami waves caused severe damage to the coastal area of Palu Bay, in the central western part of Sulawesi Island, Indonesia. To clarify the distribution of tsunami inundation and run-up heights, and damage to coastal communities due to the tsunami, the authors conducted a field survey 1 month after the event. In the inner part of Palu Bay tsunami inundation and run-up heights of more than 4 m were measured at many locations, and severe damage by the tsunami to coastal low-lying settlements was observed. In the areas to the north of the bay and around its entrance the tsunami inundation and run-up heights were lower than in the inner part of the bay. The tsunami inundation distance depended on the topographical features of coastal areas. The southern shore of the bay experienced a longer inundation distance than other shores, though generally severe damage to houses was limited to within around 200 m from the shoreline. The main lessons that can be learnt from the present event are also discussed.

Field Survey of the 2018 Sulawesi Tsunami: Inundation and Run-up Heights and Damage to Coastal Communities

An Unmanned Aerial Vehicle (UAV) system and its aerial image analysis method are developed to evaluate the damage degree of earthquake area. Both the single-rotor and the six-rotor UAVs are used to capture the visible light image of ground targets. Five types of typical ground targets are considered for the damage degree evaluation: the building, the road, the mountain, the riverway, and the vegetation. When implementing the image analysis, first the Image Quality Evaluation Metrics (IQEMs), that is, the image contrast, the image blur, and the image noise, are used to assess the imaging definition. Second, once the image quality is qualified, the Gray Level Cooccurrence Matrix (GLCM) texture feature, the Tamura texture feature, and the Gabor wavelet texture feature are computed. Third, the Support Vector Machine (SVM) classifier is employed to evaluate the damage degree. Finally, a new damage degree evaluation (DDE) index is defined to assess the damage intensity of earthquake. Many experiment results have verified the correctness of proposed system and method.

Damage Degree Evaluation of Earthquake Area Using UAV Aerial Image

In recent years, remote-sensing (RS) technologies have been used together with image processing and traditional techniques in various disaster-related works. Among these is detecting building damage from orthophoto imagery that was inflicted by earthquakes. Automatic and visual techniques are considered as typical methods to produce building damage maps using RS images. The visual technique, however, is time-consuming due to manual sampling. The automatic method is able to detect the damaged building by extracting the defect features. However, various design methods and widely changing real-world conditions, such as shadow and light changes, cause challenges to the extensive appointing of automatic methods. As a potential solution for such challenges, this research proposes the adaption of deep learning (DL), specifically convolutional neural networks (CNN), which has a high ability to learn features automatically, to identify damaged buildings from pre- and post-event RS imageries. Since RS data revolves around imagery, CNNs can arguably be most effective at automatically discovering relevant features, avoiding the need for feature engineering based on expert knowledge. In this work, we focus on RS imageries from orthophoto imageries for damaged-building detection, specifically for (i) background, (ii) no damage, (iii) minor damage, and (iv) debris classifications. The gist is to uncover the CNN architecture that will work best for this purpose. To this end, three CNN models, namely the twin model, fusion model, and composite model, are applied to the pre- and post-orthophoto imageries collected from the 2016 Kumamoto earthquake, Japan. The robustness of the models was evaluated using four evaluation metrics, namely overall accuracy (OA), producer accuracy (PA), user accuracy (UA), and F1 score. According to the obtained results, the twin model achieved higher accuracy (OA = 76.86%; F1 score = 0.761) compare to the fusion model (OA = 72.27%; F1 score = 0.714) and composite (OA = 69.24%; F1 score = 0.682) models.

Assessment of Convolutional Neural Network Architectures for Earthquake-Induced Building Damage Detection based on Pre- and Post-Event Orthophoto Images

Aerial images can greatly facilitate rescue efforts and recovery in the aftermath of hurricane disasters. Although supervised classification methods have been successfully applied to aerial imaging for building damage evaluation, their use remains challenging since supervised classifiers have to be trained using a large number of labeled samples, which are not available soon after disasters. However, rapid response is crucial for rescue tasks, which places greater demands on classification methods. To accelerate their deployment, a semisupervised classification method is proposed in this paper using a large number of unlabeled samples and only a few labeled samples that could be rapidly obtained. The proposed approach consists of three steps: segmentation, unsupervised pretraining using convolutional autoencoders (CAE), and supervised fine-tuning using convolutional neural networks (CNN). Leveraging the representation capability of CAE, the learned knowledge from CAE could be transferred to the counterparts of CNN. After pretraining, the CNN classifier is further refined with a few labeled samples to improve feature discrimination. To demonstrate this methodology, a recognition strategy of damaged buildings based on context information using only vertical postevent aerial two-dimensional images is presented in this paper. As a case study, a coastal area affected by the 2012 Sandy hurricane is investigated. Experimental results show that the proposed semisupervised method produces an overall accuracy of 88.3% and obtains an improvement of up to 9% against a CNN classifier trained from scratch.

Semisupervised classification of hurricane damage from postevent aerial imagery using deep learning

The invention discloses an air-based large-scene photographing system and method. The system is composed of a multi-rotor unmanned machine set subsystem, a multi-rotor unmanned machine flight ground control subsystem and a ground image data processing and display terminal subsystem. According to the air-based large-scene photographing system and method, multiple multi-rotor unmanned machines are controlled to conduct the formation flight by additionally hanging cameras below the multi-rotor unmanned machines, the reasonable position layout of multiple aircrafts is achieved in space near the ground, and images photographed by the unmanned machines are sent back to the ground in real time; the ground image data processing and display terminal subsystem receives the image data, projection converting and splicing processing are conducted on the images photographed by the multi-rotor unmanned machines through an image analyzing and machine vision technology, and finally two-dimensional splicing on remote large-scene scenes is formed. The system is suitable for rebuilding of large scenes and observing and measuring of points of impact when various military exercises and target practicing and shooting are conducted.

Air-based large-scene photographing system and method

Provided is an earthquake disaster rescue command and dispatch system and a method thereof; the system consists of a command center subsystem, a remote sensing satellite subsystem, an unmanned plane subsystem, a police population information subsystem, a weather information subsystem, a medical information subsystem, a relief goods repertory subsystem and input/output interfaces; by analyzing disaster information and disaster rescue information collected by each aforementioned system, a hierarchical model of earthquake disaster rescue can be built by an analytic hierarchy process; meanwhile, based on the actual situations of former earthquake disaster rescue, respective disaster rescue plan and analytic hierarchy process disaster rescue parameter database can be built. When an actual earthquake disaster happens, the current disaster situations are analyzed by the analytic hierarchy process, and the disaster rescue plan is quickly determined. The designed system and method herein are more applicable to collecting relative information quickly as soon as the earthquake happens, and automatically selecting the rescue plan for the command dispatch of the disaster rescue.

Earthquake disaster rescue command and dispatch system and method

Provided is an earthquake disaster damage degree evaluation method based on unmanned aerial vehicle aerial photos. An unmanned aerial vehicle is adopted to carry out hovering and image collection over an earthquake disaster area, earthquake disaster area image area-of-interest marking and selecting are respectively carried out on seven kinds of typical surface features, namely, houses, roads, bridges, dams, mountains, riverways and vegetation, according to an artificial interactive method, the gray level co-occurrence matrix textural features, the Tamura textural features, the Gabor ripplet textural features and the straight line and circle features of the selected area are selectively calculated, and finally the earthquake disaster surface feature damage degree is evaluated through a support vector machine classifier. The method is suitable for carrying out early information collection and evaluation in the happening area of earthquakes and secondary disasters caused by the earthquakes.

Earthquake disaster damage degree evaluation method based on unmanned aerial vehicle aerial photos

The invention discloses a combined medical disaster rescue system and method based on multi-UAVs. The combined medical disaster rescue system includes an information collection rotor UAV subsystem, a material air-drop rotor UAV subsystem, a data communication rotor UAV subsystem and a UAV control ground workstation. The invention further discloses a combined medical disaster rescue method using the combined medical disaster rescue system based on the multi-UAVs. The invention realizes the information collection and the effective disaster rescue of the affected area by using the mode of cooperation between the plurality of rotor UAV subsystems, and has the advantages of low manufacturing cost and high system integrated reliability.

Haoting Liu

Papers

Damage Degree Evaluation of Earthquake Area Using UAV Aerial Image

Air-based large-scene photographing system and method

Earthquake disaster rescue command and dispatch system and method

Earthquake disaster damage degree evaluation method based on unmanned aerial vehicle aerial photos

Combined medical disaster rescue system and method based on multi-UAVs