3D reconstruction of internal pipe
The objective of this project was to develop a straightforward and cost-effective solution for inspecting internal pipes. Unlike many existing solutions that depend on complex and costly arrays of sensors, often amounting to tens of thousands of dollars (such as the Pipe 3DC project employing a high-cost laser profilometer), our approach advocates utilizing a single high-resolution fisheye camera. This camera is employed to generate a 3D reconstruction of the pipe through the application of photogrammetry techniques. Our proposed solution seamlessly transforms a sequence of images captured within the conduit into a textured 3D model through a fully automated process. The project was implemented in Python and C++, utilizing OpenCV library. A live demonstration of the system was showcased at INFRA 2022.
