This chapter presents a compilation of experimental field trials aiming vision-based reconstruction of large-scale infrastructures using micro aerial vehicles (MAVs). The main focus of this study is on the sensor selection, the data-set generation and on the computer vision algorithms for generating three-dimensional (3D) models. In general, MAVs are distinguished for their ability to fly at various speeds, to stabilise their position and to perform manoeuvres close to large-scale infrastructures. The aforementioned merits constitute aerial robots a highly paced evolving robotic platform for infrastructure inspection and maintenance tasks. Different MAV solutions with task-oriented sensory modalities can be developed to address unique tasks, such as 3D modelling of infrastructures. In this chapter, aerial agents navigate around/ along different environments, while collecting visual data for post-processing using structure from motion (SfM) and multi-view stereo (MVS) techniques to generate 3D models [1,2]. The proposed framework has been successfully experimentally demonstrated in real indoor, outdoor and subterranean environments.

Chapter Contents:

• 8.1 Introduction
• 8.2 Related Studies
• 8.3 Visual sensors and mission planner
• 8.3.1 Image projection
• 8.3.2 Path planner
• 8.4 3D reconstruction
• 8.4.1 Stereo mapping
• 8.4.2 Monocular mapping
• 8.5 Data-set collection
• 8.5.1 Experimental setup
• 8.5.2 Data set 1
• 8.5.3 Data set 2
• 8.6 Experimental results
• 8.6.1 Indoor scenario
• 8.6.2 Outdoor Scenario 1
• 8.6.3 Outdoor Scenario 2
• 8.6.4 Underground scenario
• 8.7 Future trends
• 8.8 Conclusions
• References

Inspec keywords: inspection; image reconstruction; autonomous aerial vehicles; image sensors; mobile robots; stereo image processing; robot vision

Other keywords: different MAV solutions; experimental field trials; maintenance tasks; vision-based reconstruction; infrastructure inspection; unique tasks; aerial robots; robotic platform; data-set generation; UAVs; sensor selection; aerial agents; task-oriented sensory modalities; three-dimensional models; computer vision algorithms; visual data; microaerial vehicles; large-scale infrastructures

Subjects: Mobile robots; Optical, image and video signal processing; Computer vision and image processing techniques; Image sensors; Aerospace control