Automatic Analysis of Sewer Pipes Based on Unrolled Monocular Fisheye Images
This addresses the need for automated sewer pipe inspection, which is a domain-specific application with incremental improvements in image processing and deep learning.
The paper tackles the problem of detecting and classifying damages in sewer pipes using low-quality, compressed fisheye images from inspection robots, resulting in a system that generates high-quality cylindrical unwraps and applies deep convolutional neural networks for semantic labeling.
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.