TY - JOUR
T1 - Quantitative Evaluations of Deep Learning Models for Rapid Building Damage Detection in Disaster Areas
AU - Ser, Junho
AU - Yang, Byungyun
N1 - Publisher Copyright:
© 2022 Korean Society of Surveying. All rights reserved.
PY - 2022
Y1 - 2022
N2 - This paper is intended to find one of the prevailing deep learning models that are a type of AI (Artificial Intelligence) that helps rapidly detect damaged buildings where disasters occur. The models selected are SSD-512, RetinaNet, and YOLOv3 which are widely used in object detection in recent years. These models are based on one-stage detector networks that are suitable for rapid object detection. These are often used for object detection due to their advantages in structure and high speed but not for damaged building detection in disaster management. In this study, we first trained each of the algorithms on xBD dataset that provides the post-disaster imagery with damage classification labels. Next, the three models are quantitatively evaluated with the mAP(mean Average Precision) and the FPS (Frames Per Second). The mAP of YOLOv3 is recorded at 34.39%, and the FPS reached 46. The mAP of RetinaNet recorded 36.06%, which is 1.67% higher than YOLOv3, but the FPS is one-third of YOLOv3. SSD-512 received significantly lower values than the results of YOLOv3 on two quantitative indicators. In a disaster situation, a rapid and precise investigation of damaged buildings is essential for effective disaster response. Accordingly, it is expected that the results obtained through this study can be effectively used for the rapid response in disaster management.
AB - This paper is intended to find one of the prevailing deep learning models that are a type of AI (Artificial Intelligence) that helps rapidly detect damaged buildings where disasters occur. The models selected are SSD-512, RetinaNet, and YOLOv3 which are widely used in object detection in recent years. These models are based on one-stage detector networks that are suitable for rapid object detection. These are often used for object detection due to their advantages in structure and high speed but not for damaged building detection in disaster management. In this study, we first trained each of the algorithms on xBD dataset that provides the post-disaster imagery with damage classification labels. Next, the three models are quantitatively evaluated with the mAP(mean Average Precision) and the FPS (Frames Per Second). The mAP of YOLOv3 is recorded at 34.39%, and the FPS reached 46. The mAP of RetinaNet recorded 36.06%, which is 1.67% higher than YOLOv3, but the FPS is one-third of YOLOv3. SSD-512 received significantly lower values than the results of YOLOv3 on two quantitative indicators. In a disaster situation, a rapid and precise investigation of damaged buildings is essential for effective disaster response. Accordingly, it is expected that the results obtained through this study can be effectively used for the rapid response in disaster management.
KW - Damaged Detection
KW - Deep Learning Model
KW - Disaster Management
KW - One-Stage Detector
KW - Very High-Resolution Satellite Image
UR - http://www.scopus.com/inward/record.url?scp=85149022503&partnerID=8YFLogxK
U2 - 10.7848/ksgpc.2022.40.5.381
DO - 10.7848/ksgpc.2022.40.5.381
M3 - Article
AN - SCOPUS:85149022503
SN - 1598-4850
VL - 40
SP - 381
EP - 391
JO - Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
JF - Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
IS - 5
ER -