Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Automatic analysis of sewer pipes based on unrolled monocular fisheye images

: Künzel, Johannes; Werner, Thomas; Eisert, Peter; Waschnewski, Jan; Möller, Ronja; Hilpert, Ralf


Medioni, G. ; Institute of Electrical and Electronics Engineers -IEEE-:
IEEE Winter Conference on Applications of Computer Vision, WACV 2018. Proceedings : 12-15 March 2017, Lake Tahoe, Nevada
Piscataway, NJ: IEEE, 2018
ISBN: 978-1-5386-4886-5
ISBN: 978-1-5386-4887-2
Winter Conference on Applications of Computer Vision (WACV) <18, 2018, Lake Tahoe/Nev.>
Bundesministerium für Bildung und Forschung BMBF
13N13891; AUZUKA
Automatische Zustandsanalyse von Kanalnetzen
Fraunhofer IAIS ()
camera; estimation; mathematical model; robot vision system; neural network; semantic labeling; deep learning; machine learning; fisheye

The task of detecting and classifying damages in sewer pipes offers an important application area for computer vision algorithms. This paper describes a system, which is capable of accomplishing this task solely based on low quality and severely compressed fisheye images from a pipe inspection robot. Relying on robust image features, we estimate camera poses, model the image lighting, and exploit this information to generate high quality cylindrical unwraps of the pipes surfaces. Based on the generated images, we apply semantic labeling based on deep convolutional neural networks to detect and classify defects as well as structural elements.