English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Advances in Unmanned Aerial Vehicle (UAV) opens venues for application suchas tunnel inspection. Owing to its versatility to fly inside the tunnels, itcan quickly identify defects and potential problems related to safety. However,long tunnels, especially with repetitive or uniform structures pose asignificant problem for UAV navigation. Furthermore, post-processing visualdata from the camera mounted on the UAV is required to generate usefulinformation for the inspection task. In this work, we design a UAV with asingle rotating camera to accomplish the task. Compared to other platforms, oursolution can fit the stringent requirement for tunnel inspection, in terms ofbattery life, size and weight. While the current state-of-the-art can estimatecamera pose and 3D geometry from a sequence of images, they assume largeoverlap, small rotational motion, and many distinct matching points betweenimages. These assumptions severely limit their effectiveness in tunnel-likescenarios where the camera has erratic or large rotational motion, such as theone mounted on the UAV. This paper presents a novel solution which exploitsStructure-from-Motion, Bundle Adjustment, and available geometry priors torobustly estimate camera pose and automatically reconstruct a fully-dense 3Dscene using the least possible number of images in various challengingtunnel-like environments. We validate our system with both Virtual Realityapplication and experimentation with a real dataset. The results demonstratethat the proposed reconstruction along with texture mapping allows for remotenavigation and inspection of tunnel-like environments, even those which areinaccessible for humans.

Dense 3D Reconstruction for Visual Tunnel Inspection using Unmanned Aerial Vehicle