Feature-less Stitching of Cylindrical Tunnel

TL;DR

This paper presents a novel feature-less method for stitching images of cylindrical tunnels using known scene geometry and camera trajectory, enabling immersive panoramic visualization without traditional feature matching.

Contribution

It introduces a feature-less stitching approach leveraging scene geometry and camera trajectory for cylindrical tunnel environments, bypassing the need for feature detection and matching.

Findings

Successfully creates seamless cylindrical panoramas from UAV footage.

Enables immersive visualization in Unity without feature-based stitching.

Applicable to enclosed environments with known geometry.

Abstract

Traditional image stitching algorithms use transforms such as homography to combine different views of a scene. They usually work well when the scene is planar or when the camera is only rotated, keeping its position static. This severely limits their use in real world scenarios where an unmanned aerial vehicle (UAV) potentially hovers around and flies in an enclosed area while rotating to capture a video sequence. We utilize known scene geometry along with recorded camera trajectory to create cylindrical images captured in a given environment such as a tunnel where the camera rotates around its center. The captured images of the inner surface of the given scene are combined to create a composite panoramic image that is textured onto a 3D geometrical object in Unity graphical engine to create an immersive environment for end users.