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

2018 ◽  
Author(s):  
Johnny Cusicanqui ◽  
Norman Kerle ◽  
Francesco Nex
Keyword(s):  
Damage Assessment ◽  
Structural Damage ◽  
Moving Objects ◽  
Point Clouds ◽  
Video Data ◽  
Aerial Imagery ◽  
Video Footage ◽  
3D Point Clouds ◽  
Post Disaster ◽  
Aerial Video

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.

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

2018 ◽  
Vol 18 (6) ◽  
pp. 1583-1598 ◽  
Author(s):  
Johnny Cusicanqui ◽  
Norman Kerle ◽  
Francesco Nex
Keyword(s):  
News Media ◽  
Damage Assessment ◽  
Structural Damage ◽  
Moving Objects ◽  
Point Clouds ◽  
Video Data ◽  
Aerial Imagery ◽  
Video Footage ◽  
Post Disaster ◽  
Aerial Video

Abstract. Remote sensing has evolved into the most efficient approach to assess post-disaster structural damage, in extensively affected areas through the use of spaceborne data. For smaller, and in particular, complex urban disaster scenes, multi-perspective aerial imagery obtained with unmanned aerial vehicles and derived dense color 3-D 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, which is typically acquired and shared by civil protection institutions or news media and which tends 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 3-D 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 3-D point clouds. Despite the low video resolution, the usability of these data was compensated for 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 not only are current video data 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.

scholarly journals Deep Learning Classification of 2D Orthomosaic Images and 3D Point Clouds for Post-Event Structural Damage Assessment

Drones ◽  
2020 ◽  
Vol 4 (2) ◽  
pp. 24 ◽  
Author(s):  
Yijun Liao ◽  
Mohammad Ebrahim Mohammadi ◽  
Richard L. Wood
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Damage Assessment ◽  
Structural Damage ◽  
Point Clouds ◽  
Depth Information ◽  
3D Point Clouds ◽  
Aerial Imaging ◽  
Damage States

Efficient and rapid data collection techniques are necessary to obtain transitory information in the aftermath of natural hazards, which is not only useful for post-event management and planning, but also for post-event structural damage assessment. Aerial imaging from unpiloted (gender-neutral, but also known as unmanned) aerial systems (UASs) or drones permits highly detailed site characterization, in particular in the aftermath of extreme events with minimal ground support, to document current conditions of the region of interest. However, aerial imaging results in a massive amount of data in the form of two-dimensional (2D) orthomosaic images and three-dimensional (3D) point clouds. Both types of datasets require effective and efficient data processing workflows to identify various damage states of structures. This manuscript aims to introduce two deep learning models based on both 2D and 3D convolutional neural networks to process the orthomosaic images and point clouds, for post windstorm classification. In detail, 2D convolutional neural networks (2D CNN) are developed based on transfer learning from two well-known networks AlexNet and VGGNet. In contrast, a 3D fully convolutional network (3DFCN) with skip connections was developed and trained based on the available point cloud data. Within this study, the datasets were created based on data from the aftermath of Hurricanes Harvey (Texas) and Maria (Puerto Rico). The developed 2DCNN and 3DFCN models were compared quantitatively based on the performance measures, and it was observed that the 3DFCN was more robust in detecting the various classes. This demonstrates the value and importance of 3D datasets, particularly the depth information, to distinguish between instances that represent different damage states in structures.

scholarly journals Imaging ground surface deformations in post-disaster settings via small UAVs

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Richard L. Ybañez ◽  
Audrei Anne B. Ybañez ◽  
Alfredo Mahar Francisco A. Lagmay ◽  
Mario A. Aurelio
Keyword(s):  
Surface Deformation ◽  
Ground Surface ◽  
Point Clouds ◽  
Lateral Spreading ◽  
Fault Movement ◽  
Field Surveys ◽  
3D Point Clouds ◽  
Vertical Displacements ◽  
Resolution Imaging ◽  
Post Disaster

AbstractSmall unmanned aerial vehicles have been seeing increased deployment in field surveys in recent years. Their portability, maneuverability, and high-resolution imaging are useful in mapping surface features that satellite- and plane-mounted imaging systems could not access. In this study, we develop and apply a workplan for implementing UAV surveys in post-disaster settings to optimize the flights for the needs of the scientific team and first responders. Three disasters caused by geophysical hazards and their associated surface deformation impacts were studied implementing this workplan and was optimized based on the target features and environmental conditions. An earthquake that caused lateral spreading and damaged houses and roads near riverine areas were observed in drone images to have lengths of up to 40 m and vertical displacements of 60 cm. Drone surveys captured 2D aerial raster images and 3D point clouds leading to the preservation of these features in soft-sedimentary ground which were found to be tilled over after only 3 months. The point cloud provided a stored 3D environment where further analysis of the mechanisms leading to these fissures is possible. In another earthquake-devastated locale, areas hypothesized to contain the suspected source fault zone necessitated low-altitude UAV imaging below the treeline capturing Riedel shears with centimetric accuracy that supported the existence of extensional surface deformation due to fault movement. In the aftermath of a phreatomagmatic eruption and the formation of sub-metric fissures in nearby towns, high-altitude flights allowed for the identification of the location and dominant NE–SW trend of these fissures suggesting horst-and-graben structures. The workplan implemented and refined during these deployments will prove useful in surveying other post-disaster settings around the world, optimizing data collection while minimizing risk to the drone and the drone operators.

Learning-Based Shadow Detection in Aerial Imagery Using Automatic Training Supervision from 3D Point Clouds

2021 ◽  
Author(s):  
Deniz Kavzak Ufuktepe ◽  
Jaired Collins ◽  
Ekincan Ufuktepe ◽  
Joshua Fraser ◽  
Timothy Krock ◽  
...  
Keyword(s):  
Point Clouds ◽  
Shadow Detection ◽  
Aerial Imagery ◽  
3D Point Clouds

Hybrid obstacle avoidance system with vision and ultrasonic sensors for multi-rotor MAVs

2018 ◽  
Vol 45 (2) ◽  
pp. 227-236 ◽  
Author(s):  
Qiang Zhou ◽  
Danping Zou ◽  
Peilin Liu
Keyword(s):  
Path Planning ◽  
Obstacle Avoidance ◽  
Moving Objects ◽  
Point Clouds ◽  
Ultrasonic Sensor ◽  
Content Type ◽  
Stereo Camera ◽  
3D Point Clouds ◽  
Planning Algorithm ◽  
Path Planning Algorithm

Purpose This paper aims to develop an obstacle avoidance system for a multi-rotor micro aerial vehicle (MAV) that flies in indoor environments which usually contain transparent, texture-less or moving objects. Design/methodology/approach The system adopts a combination of a stereo camera and an ultrasonic sensor to detect obstacles and extracts three-dimensional (3D) point clouds. The obstacle map is built on a coarse global map and updated by local maps generated by the recent 3D point clouds. An efficient layered A* path planning algorithm is also proposed to address the path planning in 3D space for MAVs. Findings The authors conducted a lot of experiments in both static and dynamic scenes. The results show that the obstacle avoidance system works reliably even when transparent or texture-less obstacles are present. The layered A* path planning algorithm is much faster than the traditional 3D algorithm and makes the system response quickly when the obstacle map has been changed because of the moving objects. Research limitations/implications The limited field of view of both stereo camera and ultrasonic sensor makes the system need to change heading first before moving side to side or moving backward. But this problem could be addressed when multiple systems are mounted toward different directions on the MAV. Practical implications The developed approach could be valuable to applications in indoors. Originality/value This paper presents a robust obstacle avoidance system and a fast layered path planning algorithm that are easy to be implemented for practical systems.

scholarly journals Post-Earthquake Recovery Phase Monitoring and Mapping Based on UAS Data

2020 ◽  
Vol 9 (7) ◽  
pp. 447
Author(s):  
Nikolaos Soulakellis ◽  
Christos Vasilakos ◽  
Stamatis Chatzistamatis ◽  
Dimitris Kavroudakis ◽  
Georgios Tataris ◽  
...  
Keyword(s):  
Low Cost ◽  
Point Clouds ◽  
Field Studies ◽  
Recovery Phase ◽  
Unmanned Aircraft ◽  
Surface Model ◽  
Building Stock ◽  
Earthquake Scenario ◽  
Video Footage ◽  
3D Point Clouds

Geoinformatics plays an essential role during the recovery phase of a post-earthquake situation. The aim of this paper is to present the methodology followed and the results obtained by the utilization of Unmanned Aircraft Systems (UASs) 4K-video footage processing and the automation of geo-information methods targeted at both monitoring the demolition process and mapping the demolished buildings. The field campaigns took place on the traditional settlement of Vrisa (Lesvos, Greece), which was heavily damaged by a strong earthquake (Mw=6.3) on June 12th, 2017. For this purpose, a flight campaign took place on 3rd February 2019 for collecting aerial 4K video footage using an Unmanned Aircraft. The Structure from Motion (SfM) method was applied on frames which derived from the 4K video footage, for producing accurate and very detailed 3D point clouds, as well as the Digital Surface Model (DSM) of the building stock of the Vrisa traditional settlement, twenty months after the earthquake. This dataset has been compared with the corresponding one which derived from 25th July 2017, a few days after the earthquake. Two algorithms have been developed for detecting the demolished buildings of the affected area, based on the DSMs and 3D point clouds, correspondingly. The results obtained have been tested through field studies and demonstrate that this methodology is feasible and effective in building demolition detection, giving very accurate results (97%) and, in parallel, is easily applicable and suit well for rapid demolition mapping during the recovery phase of a post-earthquake scenario. The significant advantage of the proposed methodology is its ability to provide reliable results in a very low cost and time-efficient way and to serve all stakeholders and national and local organizations that are responsible for post-earthquake management.

Near-Real Time Post-Disaster Damage Assessment with Airborne Oblique Video Data

2005 ◽  
pp. 337-353 ◽  
Author(s):  
Norman Kerle ◽  
Rob Stekelenburg ◽  
Frank van den Heuvel ◽  
Ben Gorte
Keyword(s):  
Real Time ◽  
Damage Assessment ◽  
Video Data ◽  
Post Disaster

scholarly journals EXTRACTING SEMANTICALLY ANNOTATED 3D BUILDING MODELS WITH TEXTURES FROM OBLIQUE AERIAL IMAGERY

2015 ◽  
Vol XL-3/W2 ◽  
pp. 53-58 ◽  
Author(s):  
D. Frommholz ◽  
M. Linkiewicz ◽  
H. Meissner ◽  
D. Dahlke ◽  
A. Poznanska
Keyword(s):  
High Resolution ◽  
Software Package ◽  
Point Clouds ◽  
Aerial Imagery ◽  
Commercial Software ◽  
Camera System ◽  
3D Point Clouds ◽  
Building Models ◽  
Commercial Software Package

This paper proposes a method for the reconstruction of city buildings with automatically derived textures that can be directly used for façade element classification. Oblique and nadir aerial imagery recorded by a multi-head camera system is transformed into dense 3D point clouds and evaluated statistically in order to extract the hull of the structures. For the resulting wall, roof and ground surfaces high-resolution polygonal texture patches are calculated and compactly arranged in a texture atlas without resampling. The façade textures subsequently get analyzed by a commercial software package to detect possible windows whose contours are projected into the original oriented source images and sparsely ray-casted to obtain their 3D world coordinates. With the windows being reintegrated into the previously extracted hull the final building models are stored as semantically annotated CityGML ”LOD-2.5” objects.

Sign in / Sign up

Export Citation Format

Share Document