Usability of aerial video footage for 3D-scene reconstruction and structural damage assessment

Johnny Cusicanqui, N. Kerle, F. Nex

Research output: Contribution to journalArticleAcademicpeer-review

11 Downloads (Pure)

Abstract

Remote sensing has evolved into the most efficient approach to assess post-disaster structural damage, in extensively affected
areas through the use of space-borne data. For smaller, and in particular, complex urban disaster scenes, multi-perspective aerial
imagery obtained with Unmanned Aerial Vehicles and derived dense colour 3D-models are increasingly being used. These type
of data allow the direct and automated recognition of damage-related features, supporting an effective post-disaster structural
damage assessment. However, the rapid collection and sharing of multi-perspective aerial imagery is still limited due to tight
or lacking regulations and legal frameworks. A potential alternative is aerial video footage, typically acquired and shared by
civil protection institutions or news media, and which tend to be the first type of airborne data available. Nevertheless, inherent
artifacts and the lack of suitable processing means, have long limited its potential use in structural damage assessment and other
post-disaster activities. In this research the usability of modern aerial video data was evaluated based on a comparative quality
and application analysis of video data and multi-perspective imagery (photos), and their derivative 3D point clouds created
using current photogrammetric techniques. Additionally, the effects of external factors, such as topography and the presence of
smoke and moving objects were determined by analyzing two different earthquake-affected sites: Tainan (Taiwan) and Pescara
del Tronto (Italy). Results demonstrated similar usabilities for video and photos. This is shown by the short 2 cm of difference
between the accuracies of video and photo-based 3D Point clouds. Despite the low video resolution, the usability of this data
was compensated by a small ground sampling distance. Instead of video characteristics, low quality and application resulted
from non-data related factors, such as changes in the scene, lack of texture or moving objects. We conclude that current video
data are not only more rapidly available than photos, but they also have a comparable ability to assist in image-based structural
damage assessment and other post-disaster activities.
Original languageEnglish
Pages (from-to)1-23
Number of pages23
JournalNatural hazards and earth systems sciences discussions
DOIs
Publication statusSubmitted - 8 Jan 2018

Fingerprint

Dive into the research topics of 'Usability of aerial video footage for 3D-scene reconstruction and structural damage assessment'. Together they form a unique fingerprint.

Cite this