Pointer generation and main scale detection for occluded meter reading based on generative adversarial network

Abstract

The meter reading with machine vision greatly improves the efficiency of industrial monitoring. However, the pointer and scales of the meter can be occluded by rain or dirt, which greatly reduces the accuracy of the meter reading recognition. To solve this problem, we propose a generative adversarial network (PMS-GAN) with pointer generation and main scale detection for occluded meter reading. Specifically, dilated convolution block is designed to correlate separated pointer features. Then multi-scale feature fusion mechanism is proposed to guarantee the precision of pointer generation and main scale detection with guidance of semantic information. Moreover, feature enhancement mechanism is proposed to construct the long-range relationship for generating pointer under high occlusion. Finally, the reading is accomplished by calculating local angle with generated pointer and detected main scales. Experiments show that PMS-GAN can generate more intact pointer and detect main scales to guarantee the success and accuracy of occluded meter reading.