Towards computer vision technologies: Semi-automated reading of automated utility meters

TL;DR

This paper compares open-source and commercial computer vision solutions for semi-automated utility meter reading, analyzing their accuracy, inference time, and suitability for real-world deployment.

Contribution

It provides a detailed comparison of Tensorflow Object Detection and Anyline for utility meter reading, highlighting their strengths and limitations.

Findings

Tensorflow offers high customization but has longer inference times.

Anyline provides faster inference with easier deployment.

Both solutions face challenges with meter variations and environmental conditions.

Abstract

In this report we analysed a possibility of using computer vision techniques for automated reading of utility meters. In our study, we focused on two computer vision techniques: an open-source solution Tensorflow Object Detection (Tensorflow) and a commercial solution Anyline. This report extends our previous publication: We start with presentation of a structured analysis of related approaches. After that we provide a detailed comparison of two computer vision technologies, Tensorflow Object Detection (Tensorflow) and Anyline, applied to semi-automated reading of utility meters. In this paper, we discuss limitations and benefits of each solution applied to utility meters reading, especially focusing on aspects such as accuracy and inference time. Our goal was to determine the solution that is the most suitable for this particular application area, where there are several specific challenges.