A Comparative Study of Meter Detection Methods for Automated Infrastructure Inspection
This work addresses automated infrastructure inspection for robotics, but it is incremental as it compares existing method types without introducing a new paradigm.
The study tackled the problem of detecting meter regions from images captured by an autonomous inspection robot with positional errors, comparing shape-based, texture-based, and background information-based methods. It found that the background information-based method could detect the farthest meters regardless of shape and number, achieving stable detection for meters with a diameter of 40px.
In order to read meter values from a camera on an autonomous inspection robot with positional errors, it is necessary to detect meter regions from the image. In this study, we developed shape-based, texture-based, and background information-based methods as meter area detection techniques and compared their effectiveness for meters of different shapes and sizes. As a result, we confirmed that the background information-based method can detect the farthest meters regardless of the shape and number of meters, and can stably detect meters with a diameter of 40px.