Abstract
Earthquake destroyed many buildings, especially wooden ones, in Japan. Collecting information regarding collapsed buildings during the emergency phase (i.e., 72 h after a disaster) is difficult but essential for rescue activities. This study developed an automatic model to detect collapsed buildings using multiple object tracking (MOT) from aerial videos. Roof damage and pancake collapse are destructions unique to traditional Japanese buildings. Previous studies that detected collapsed buildings using the features of debris or damage failed to discriminate between collapsed and held-up buildings when the buildings have the above Japanese feature. Therefore, this study used the deep learning MOT model to classify collapsed and held-up buildings regardless of debris appearance. The recall and precision of each track of collapsed buildings were 29.1% and 36.7%, respectively, based on cross-validation with the drone video of the 2016 Kumamoto Earthquake. Analysis between the recall and other factors indicated that the aspect ratio, speed, and appearance time of the buildings were significant features for the detection. In the relationship between recall and these factors, we deduce that the recall of track increases to 63.9% if the drone operator films aerial videos effectively. Moreover, this study analyzed effective drone filming and flying way to satisfy some conditions for detection. This result provides recommended filming guides to drone operators for future earthquakes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fire and Disaster Management Agency in Japan: Final report about the Great Hanshin-Awaji Earthquake. https://www.fdma.go.jp/disaster/info/assets/post1.pdf. Accessed 5 July 2022. (in Japanese)
Hyogo Prefecture Medical Association: Actual state of affairs of human damage by the Great Hanshin-Awaji Earthquake. https://www.hyogo.med.or.jp/jmat-hyogo/day-after/siryo/. Accessed 5 July 2022. (in Japanese)
Disaster response headquarters of Fukushima prefecture: No. 1778 damage report of the 2011 off the Pacific coast of Tohoku Earthquake. https://www.pref.fukushima.lg.jp/uploaded/life/620025_1725169_misc.pdf. Accessed 5 July 2022. (in Japanese)
Disaster response headquarters of Kumamoto prefecture: No. 325 damage report of the 2016 Kumamoto Earthquake. https://www.pref.kumamoto.jp/uploaded/attachment/182677.pdf. Accessed 5 July 2022. (in Japanese)
Fire and Disaster Management Agency in Japan: Report of review meeting about ideal way of effective initial activity of firefighter headquarter in large-scale disasters. https://www.fdma.go.jp/singi_kento/kento/items/kento004_01_houkoku.pdf. Accessed 5 July 2022. (in Japanese)
Kumamoto city fire department. Activity record journal of Kumamoto city fire department in the 2016 Kumamoto Earthquake. https://www.city.kumamoto.jp/common/UploadFileDsp.aspx?c_id=5&id=19060&sub_id=1&flid=134936. Accessed 5 July 2022. (in Japanese)
Tv Asahi news site. https://news.tv-asahi.co.jp/news_society/articles/000074837.html. Accessed July 2022. (in Japanese)
Murakami, H.: Study on rescue and emergency activities by Kumamoto City fire department after the 2016 Kumamoto earthquake - comparison with the 2004 Niigata Chuuetsu and the 2005 West off Fukuoka Prefecture earthquakes. Report of Tono Research Institute of Earthquake Science, vol. 41, pp. 93–98 (2017). (in Japanese)
The Sankei News. https://www.sankei.com/article/20200115-7M7FDUJP2RLLDJDFXYP23H4J3E/. Accessed 5 July 2022. (in Japanese)
Fire and Disaster Management Agency in Japan: Notice about promotion of drone usage of the fire brigade in disaster response. https://www.fdma.go.jp/laws/tutatsu/items/040331_drone.pdf. Accessed 5 July 2022 (in Japanese)
Nazarov, E.: Emergency response management in Japan, final research report. ASIAN disaster reduction center, FY2011A program (2011)
Anand, V., Markus, G., Norman, K., Francesco, N., George, V.: Disaster damage detection through synergistic use of deep learning and 3D point cloud features derived from very high-resolution oblique aerial images, and multiple-kernel-learning. ISPRS J. Photogramm. Remote Sens. 140, 45–59 (2018)
Johnny, C., Norman, K., Francesco, N.: Usability of aerial video footage for 3-D scene reconstruction and structural damage assessment. Nat. Hazards Earth Syst. Sci. 18(6), 1583–1598 (2018)
Yamazaki, F., Kubo, K., Tanabe, R., Liu, W.: Damage assessment and 3D modeling by UAV flights after the 2016 Kumamoto, Japan earthquake. In: The IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Fort Worth, TX, USA, pp. 3182–3185 (2017)
Fujita, S., Hatayama, M.: Estimation method for roof‐damaged buildings from aero-photo images during earthquakes using deep learning. Inf. Syst. Front. 25(1), 351–363 (2021)
Fujita, S., Hatayama, M.: Automatic calculation of damage rate of roofs based on image segmentation. In: 6th IFIP WG 5.15 International Conference, ITDRR 2021, pp. 3–22, Morioka, Japan, (2022)
Fujita, S., Hatayama, M.: Rapid and accurate detection of building damage investigation using an automatic method to calculate roof damage rate. IDRiM J. 12(1), 89–111 (2022)
Miura, H., Aridome, T., Matsuoka, M.: Deep learning-based identification of collapsed, non-collapsed and blue tarp-covered buildings from post-disaster aerial images. Remote Sens. 12(12) (2020)
Calantropio, A., Chiabrando, F., Codastefano, M., Bourke, E.: Deep learning for automatic building damage assessment: application in post-disaster scenarios using UAV data. ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci. V-1-2021, 113–120 (2021)
Yamazaki, F., et al.: Development of fragility curves of Japanese buildings based on the 2016 Kumamoto earthquake. In: The 2019 Pacific Conference on Earthquake Engineering, Auckland, New Zealand (2019)
Kusaka, A., Nakamura, H., Fujiwara, H., Okano, H.: Bayesian updating of damaged building distribution in post-earthquake assessment. In: The 16th World Conference on Earthquake, 16WCEE 2017, Santiago Chile (2017)
Xie, S., et al.: Crowdsourcing rapid assessment of collapsed buildings early after the earthquake based on aerial remote sensing image: a case study of Yushu earthquake. Remote Sens. 8(9) (2016)
Khajwal, A.B., Noshadravan, A.: An uncertainty-aware framework for reliable disaster damage assessment via crowdsourcing. Int. J. Disaster Risk Reduct. 55 (2021)
Shishido, H., Kobayashi, K., Kameda, Y., Kitahara, I.: Method to generate building damage maps by combining aerial image processing and crowdsourcing. J. Disaster Res. 16(5), 827–839 (2021)
Qi, J., et al.: Search and rescue rotary‐wing UAV and its application to the Lushan Ms 7.0 earthquake. J. Field Robot. 33(3), 290–321 (2016)
Pi, Y., Nath, N.D., Behzadan, A.H.: Convolutional neural networks for object detection in aerial imagery for disaster response and recovery. Adv. Eng. Inform. 43 (2020)
Zhu, X., Liang, J., Hauptmann, A.: MSNet: a multilevel instance segmentation network for natural disaster damage assessment in aerial videos. In: The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2023–2032 (2021)
Scawthorn, C., Yanev, P.I.: Preliminary report 17 January 1995, Hyogo-ken Nambu, Japanese earthquake. Eng. Struct. 17(3), 146–157 (1995)
Okada, S., Takai, N.: Classifications of structural types and damage patterns of buildings for earthquake field investigation. In: 12th World Conference on Earthquake Engineering, Auckland, New Zealand (2000)
Scawthorn, C.: Building aspects of the 2004 Niigata Ken Chuetsu, Japan, Earthquake. Earthq. Spectra 22(1), 75–88 (2006)
Zhang, Y., et al.: Bytetrack: multi-object tracking by associating every detection box. arXiv preprint arXiv:2110.06864 (2021)
Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)
GitHub - ifzhang/ByteTrack: [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box. https://github.com/ifzhang/ByteTrack. Accessed 7 July 2022
Ministry of Internal Affairs and Communications: Result summary of basic tabulation about housing and households in housiPng and land survey. https://www.stat.go.jp/data/jyutaku/2018/pdf/kihon_gaiyou.pdf. Accessed 29 July 2022. (in Japanese)
DJI: Mavic 3 specification. https://www.dji.com/jp/mavic-3/specs. Accessed 29 July 2022. (in Japanese)
Acknowledgements
This work is supported by JSPS KAKENHI Grant Number JP 22J15895.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 IFIP International Federation for Information Processing
About this paper
Cite this paper
Fujita, S., Hatayama, M. (2023). Collapsed Building Detection Using Multiple Object Tracking from Aerial Videos and Analysis of Effective Filming Techniques of Drones. In: Gjøsæter, T., Radianti, J., Murayama, Y. (eds) Information Technology in Disaster Risk Reduction. ITDRR 2022. IFIP Advances in Information and Communication Technology, vol 672. Springer, Cham. https://doi.org/10.1007/978-3-031-34207-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-34207-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34206-6
Online ISBN: 978-3-031-34207-3
eBook Packages: Computer ScienceComputer Science (R0)