Depth-based Deep Learning for Manhole Detection in UAV Navigation

Andersen, Rasmus Eckholdt; Zajączkowski, Marcin; Jaiswal, Harsh; Xu, Jianan; Wang, Fan; Boukas, Evangelos

doi:10.1109/ist55454.2022.9827720

Cited by 7 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reflecting the increasing use of piloted flying robots inside BWT, the authors in [14] overview the associated ecosystem of drone services. Preliminary results on BWT inspection with aerial robots is discussed in [11,15], while the associated problem of detecting and traversing through narrow manholes is addressed in [16] and [17] using deep learning on dense depth data and a humanengineered detector on LiDAR data respectively. From a different perspective, the authors in [18] discuss the utility of hyperspectral imaging onboard drones for BWT inspection.…”

Section: Related Workmentioning

confidence: 99%

Manhole Detection and Traversal for Exploration of Ballast Water Tanks using Micro Aerial Vehicles

Dharmadhikari

Petris

Nguyen

et al. 2023

2023 International Conference on Unmanned Aircraft Systems (ICUAS)

View full text Add to dashboard Cite

This paper presents a solution for the autonomous exploration and inspection of Ballast Water Tanks (BWTs) of marine vessels using aerial robots. Ballast tank compartments are critical for a vessel's safety and correspond to confined environments often connected through particularly narrow manholes. The method enables their volumetric exploration combined with visual inspection subject to constraints regarding the viewing distance from a surface. We present evaluation studies in simulation, in a mission consisting of 18 BWT compartments, and in 3 field experiments inside real vessels. The data from one of the experiments is also post-processed to generate semantically-segmented meshes of inspection-important geometries. Geometric models can be associated with onboard camera images for detailed and intuitive analysis.

show abstract