Vector Detection Network: An Application Study on Robots Reading Analog Meters in the Wild

TL;DR

This paper introduces the Vector Detection Network (VDN), a novel approach for autonomous reading of analog meters by robots, capable of accurately detecting meter pointers in challenging real-world conditions in real-time.

Contribution

The paper presents VDN, a new neural network architecture that models meter pointers as vectors, and introduces the Pointer-10K dataset for evaluating meter reading methods.

Findings

VDN generalizes well to various meters

It is robust to harsh imaging conditions

Runs in real-time with high accuracy

Abstract

Analog meters equipped with one or multiple pointers are wildly utilized to monitor vital devices' status in industrial sites for safety concerns. Reading these legacy meters {\bi autonomously} remains an open problem since estimating pointer origin and direction under imaging damping factors imposed in the wild could be challenging. Nevertheless, high accuracy, flexibility, and real-time performance are demanded. In this work, we propose the Vector Detection Network (VDN) to detect analog meters' pointers given their images, eliminating the barriers for autonomously reading such meters using intelligent agents like robots. We tackled the pointer as a two-dimensional vector, whose initial point coincides with the tip, and the direction is along tail-to-tip. The network estimates a confidence map, wherein the peak pixels are treated as vectors' initial points, along with a two-layer scalar map, whose pixel values at each peak form the scalar components in the directions of the coordinate axes. We established the Pointer-10K dataset composing of real-world analog meter images to evaluate our approach due to no similar dataset is available for now. Experiments on the dataset demonstrated that our methods generalize well to various meters, robust to harsh imaging factors, and run in real-time.