Evaluation and Selection of Video Stabilization Techniques for UAV-Based Active Infrared Thermography Application.

Argyrios Zolotas,Nicolas P. Avdelidis,Shakeb Deane,Julio J. Valdes,Parham Nooralishahi,Clemente Ibarra-Castanedo,Shashank Pant,Marc Genest,Xavier P. V. Maldague

doi:10.3390/s21051604

Argyrios Zolotas, Nicolas P. Avdelidis + Show 7 more

Open Access

https://doi.org/10.3390/s21051604

Copy DOI

Abstract

Unmanned Aerial Vehicles (UAVs) that can fly around an aircraft carrying several sensors, e.g., thermal and optical cameras, to inspect the parts of interest without removing them can have significant impact in reducing inspection time and cost. One of the main challenges in the UAV based active InfraRed Thermography (IRT) inspection is the UAV’s unexpected motions. Since active thermography is mainly concerned with the analysis of thermal sequences, unexpected motions can disturb the thermal profiling and cause data misinterpretation especially for providing an automated process pipeline of such inspections. Additionally, in the scenarios where post-analysis is intended to be applied by an inspector, the UAV’s unexpected motions can increase the risk of human error, data misinterpretation, and incorrect characterization of possible defects. Therefore, post-processing is required to minimize/eliminate such undesired motions using digital video stabilization techniques. There are number of video stabilization algorithms that are readily available; however, selecting the best suited one is also challenging. Therefore, this paper evaluates video stabilization algorithms to minimize/mitigate undesired UAV motion and proposes a simple method to find the best suited stabilization algorithm as a fundamental first step towards a fully operational UAV-IRT inspection system.

Highlights

Multi-Scale Structural Similarity (MS-SSIM) was used for comparison, while others performed well when Range of Motion (RoM) and Blank Borders (BB) were used for comparison
11), the stabilization algorithmx-translation managed to reduce the for y-translation (Figure 11), the stabilization algorithm managed to reduce the overall range of motion, which was observed during the first experiment, as shown overall range range of of motion, motion,which whichwas wasalso alsoobserved observedduring duringthe the first experiment, shown first experiment, as as shown in in Figures 7 and
Unmanned Aerial Vehicles (UAVs) inspection is challenging because the UAV carrying the optical and thermal cameras is subject to vibration and undesired motion

Summary

Introduction

The use of Unmanned Aerial Vehicles (UAVs) for the remote inspection of large and/or difficult to access areas has witnessed significant growth in the last few years thanks to their flexibility of movement and their ability to carry multiple sensors. Constant technological evolvement has contributed to making UAVs more affordable, easier and safer to deploy. Thanks to the recent developments in variety of sensors for UAV applications that are low weight, low power consumption, and improved performance, thereby, allowing multiple sensors to be flown at the same time. In some cases, compared to traditional technologies, UAV-based survey systems offer better image spatial resolution (e.g., compared to satellites), and/or are much faster (e.g., compared to ground surveys in remote areas). UAV’s flight operation is becoming more automated, and image processing and data fusion tools are continuously evolving [8]

Methods

Results

Discussion

Conclusion