Quality Assessment of Unmanned Aerial Vehicle (UAV) Based Visual Inspection of Structures
TL;DR: In this paper, the application of UAVs for visual inspection and damage detection on civil structures is discussed and the properties of such flight systems, the factors influencing their movements and the resulting photo quality is discussed.
Abstract: This paper discusses the application of Unmanned Aerial Vehicles (UAV) for visual inspection and damage detection on civil structures. The quality of photos and videos taken by using such airborne vehicles is strongly influenced by numerous parameters such as lighting conditions, distance to the object and vehicle motion induced by environmental effects. Whilst such devices feature highly sophisticated sensors and control algorithms, specifically the effects of fluctuating wind speeds and directions affect the vehicle motion. The nature of vehicle movements during photo and video acquisition in turn affect the quality of the data and hence the degree to which damages can be identified. This paper discusses the properties of such flight systems, the factors influencing their movements and the resulting photo quality. Based on the processed data logged by the high precision sensors on the UAV the influences are studied and a method is shown by which the damage assessment quality may be quantified.
Citations
More filters
TL;DR: An overview of recent advances in computer vision techniques as they apply to the problem of civil infrastructure condition assessment and some of the key challenges that persist toward the goal of automated vision-based civil infrastructure and monitoring are presented.
500 citations
Cites methods from "Quality Assessment of Unmanned Aeri..."
...For example, Morgenthal and Hallermann [137] identified manually inserted changes on a retaining wall using aligned orthomosaics for in-plane changes and C2C comparison using the CloudCompare package for out-ofplane changes [138]....
[...]
TL;DR: This article implements the state‐of‐the‐art deep learning technologies for a civil engineering application, namely recognition of structural damage from images with four naïve baseline recognition tasks: component type identification, spalling condition check, damage level evaluation, and damage type determination.
Abstract: This article implements the state‐of‐the‐art deep learning technologies for a civil engineering application, namely recognition of structural damage from images. Inspired by ImageNet Chall...
460 citations
Cites background from "Quality Assessment of Unmanned Aeri..."
...…into portable hardware or as mobile software application (app) combined with prevailing drone/robot-based detection (Zhang and Elaksher, 2012; Morgenthal and Hallermann, 2014), to help with real-time structural damage recognition and evaluation decisionmaking in postdisaster reconnaissance…...
[...]
TL;DR: The state‐of‐the‐art methods have been presented by conducting a detailed literature review of the recent applications of smartphones, UAVs, cameras, and robotic sensors used in acquiring and analyzing the vibration data for structural condition monitoring and maintenance.
301 citations
TL;DR: A comprehensive review of various literature that addresses this topic is presented, followed by the identification of a standard procedures for operating a UAS for energy audit missions, and a discussion of the findings suggests refining procedure accuracy through further empirical experimentation, as a step towards standardizing the automation of building envelope inspection.
265 citations
TL;DR: The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed.
Abstract: Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.
232 citations
References
More filters
TL;DR: A novel control law based on computer vision for quasi-stationary flights above a planar target is presented, which uses the homography matrix computed from the information obtained from the vision system.
427 citations
TL;DR: An up-to-date review of research in IQA is provided, and several open challenges in this field are highlighted, including key properties of visual perception, image quality databases, existing full-reference, no- reference, and reduced-reference IQA algorithms.
Abstract: Image quality assessment (IQA) has been a topic of intense research over the last several decades. With each year comes an increasing number of new IQA algorithms, extensions of existing IQA algorithms, and applications of IQA to other disciplines. In this article, I first provide an up-to-date review of research in IQA, and then I highlight several open challenges in this field. The first half of this article provides discuss key properties of visual perception, image quality databases, existing full-reference, no-reference, and reduced-reference IQA algorithms. Yet, despite the remarkable progress that has been made in IQA, many fundamental challenges remain largely unsolved. The second half of this article highlights some of these challenges. I specifically discuss challenges related to lack of complete perceptual models for: natural images, compound and suprathreshold distortions, and multiple distortions, and the interactive effects of these distortions on the images. I also discuss challenges related to IQA of images containing nontraditional, and I discuss challenges related to the computational efficiency. The goal of this article is not only to help practitioners and researchers
keep abreast of the recent advances in IQA, but to also raise awareness of the key limitations of current IQA knowledge.
412 citations
06 Sep 2012-ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
TL;DR: At adequate illuminating and weather conditions the presented UAV-based fawn detection via thermal imaging is a comfortable, fast and reliable method.
Abstract: This paper presents a UAV based remote sensing system for the detection of fawns in the meadows. There is a high demand because during pasture mowing many wild animals, especially roe deer fawns are killed by mowing machines. The system was tested in several real situations especially with differing weather and iluminating conditions. Its primary sensor is a lightweight thermal infrared camera. The images are captured onboard of the flight system and also transmitted as analog video stream to the ground station, where the user can follow the camera live stream on a monitor for manual animal detection. Beside a high detection rate a fast workflow is another very important objective for this application. Therefore a waypoint planning software was developed that accelerates the workflow. At adequate illuminating and weather conditions the presented UAV-based fawn detection via thermal imaging is a comfortable, fast and reliable method.
98 citations
TL;DR: In this article, a two-dimensional immersed interface technique for the vortex-in-cell (VIC) method for simulation of flows past bodies of complex geometry is presented, which is augmented by a local particle-particle correction term in a Particle-Particle Particle Mesh (P^3M) context to resolve sub-grid scales incurred by the presence of the immersed interface.
69 citations
16 Aug 2013-ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
TL;DR: In this paper, the results and results of UAS surveys for automatic bird count of the last two years are presented for the bird reserve island Langenwerder, where 1,568 birds were detected on the image mosaic, based on multispectral image classification and GIS-based post processing.
Abstract: The standard procedure to count birds is a manual one. However a manual bird count is a time consuming and cumbersome process, requiring several people going from nest to nest counting the birds and the clutches. High resolution imagery, generated with a UAS (Unmanned Aircraft System) offer an interesting alternative. Experiences and results of UAS surveys for automatic bird count of the last two years are presented for the bird reserve island Langenwerder. For 2011 1,568 birds (± 5 %.) were detected on the image mosaic, based on multispectral image classification and GIS-based post processing. Based on the experiences of 2011 the results and the accuracy of the automatic bird count 2012 became more efficient. For 2012 1,938 birds with an accuracy of approx. ± 3 % were counted. Additionally a separation of breeding and non-breeding birds was performed with the assumption, that standing birds cause a visible shade. The final section of the paper is devoted to the analysis of the 3D-point cloud. Thereby the point cloud was used to determine the height of the vegetation and the extend and depth of closed sinks, which are unsuitable for breeding birds.
58 citations
"Quality Assessment of Unmanned Aeri..." refers background in this paper
...Another field of application is the monitoring of vegetation and animals in agriculture or forestry (Israel 2012) and (Grenzdörffer 2013)....
[...]