:: Volume 4, Issue 3 (12-2016) ::
jgit 2016, 4(3): 77-87 Back to browse issues page
Using Support Vector Machine to Generate Building Damage Map from Post-Event LiDAR Data
Fayezeh Eslamizadeh , Heidar Rastiveis *
University of Tehran
Abstract:   (3781 Views)

Natural disasters such as floods, earthquakes, hurricanes and tsunamis have always been the greatest human problems. Among them, the earthquakes, because of its unpredictability, are more important than the others.  After an earthquake, damage assessment plays an important role in leading rescue teams in order to minimize the damages. Meanwhile, damage map, a map that demonstrates collapsed buildings with their degree of damage count as one of the most important information sources for crisis management. In this paper, we propose an algorithm for automatic generation of damage map after an earthquake using post-event LiDAR data and pre-event vector map. In the proposed method, in order to find the location of all buildings on LiDAR data, in the first step, LiDAR data and vector map are registered by using a few numbers of ground control points. Then, the buildings, in vector map, are overlaid on the LiDAR data to extract all the pixels inside buildings area. After that, Using SVM classification algorithm all the extracted pixels are classified into two classes of “debris”, “intact”. Next, damage degree for every building is estimated based on the relation between the numbers of pixels labeled as “debris” class to the whole building area. To evaluate the ability of the proposed method in generating damage map, a dataset from Port-au-Prince, Haiti’s capital after the 2010 Haiti earthquake was used. In this case, after calculating all buildings in the tested area using the proposed method, the results were compared to the damage degree which estimated through visual interpretation of post-event satellite image. Obtained results proved the reliability of the proposed method in damage map generation using LiDAR data.

Keywords: Earthquake, Building, Support vector machine, LiDAR data, Damage map
Full-Text [PDF 924 kb]   (1414 Downloads)    
Type of Study: Research | Subject: Aerial Photogrammetry
Received: 2016/03/7 | Accepted: 2016/07/11 | Published: 2017/02/28

XML   Persian Abstract   Print

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 4, Issue 3 (12-2016) Back to browse issues page