It's About Time: Analog Clock Reading in the Wild

TL;DR

This paper introduces a scalable synthetic data pipeline and a novel recognition architecture for reading analog clocks in natural images and videos, demonstrating effective generalization and minimal manual annotation requirements.

Contribution

It presents a synthetic clock generation pipeline, a spatial transformer network-based recognition model, and a pseudo-labeling approach leveraging clock time properties, advancing clock reading in real-world scenarios.

Findings

Model trained on synthetic data generalizes well to real clocks.

Pseudo-labeling with clock time properties improves accuracy.

Introduces three benchmark datasets with detailed annotations.

Abstract

In this paper, we present a framework for reading analog clocks in natural images or videos. Specifically, we make the following contributions: First, we create a scalable pipeline for generating synthetic clocks, significantly reducing the requirements for the labour-intensive annotations; Second, we introduce a clock recognition architecture based on spatial transformer networks (STN), which is trained end-to-end for clock alignment and recognition. We show that the model trained on the proposed synthetic dataset generalises towards real clocks with good accuracy, advocating a Sim2Real training regime; Third, to further reduce the gap between simulation and real data, we leverage the special property of "time", i.e.uniformity, to generate reliable pseudo-labels on real unlabelled clock videos, and show that training on these videos offers further improvements while still requiring zero manual annotations. Lastly, we introduce three benchmark datasets based on COCO, Open Images, and The Clock movie, with full annotations for time, accurate to the minute.