YOLO-based Object Detection in Industry 4.0 Fischertechnik Model Environment

TL;DR

This paper evaluates YOLO architectures for real-time object detection in an Industry 4.0 Fischertechnik model environment, addressing environmental variations and image distortions to improve monitoring accuracy.

Contribution

It systematically assesses various YOLO models and strategies for prior-shape assignment in a simulated factory setting with diverse image distortions.

Findings

YOLO architectures effectively detect objects under varied conditions

Training strategies mitigate effects of environmental distortions

Model performance varies with architecture complexity

Abstract

In this paper we extensively explore the suitability of YOLO architectures to monitor the process flow across a Fischertechnik industry 4.0 application. Specifically, different YOLO architectures in terms of size and complexity design along with different prior-shapes assignment strategies are adopted. To simulate the real world factory environment, we prepared a rich dataset augmented with different distortions that highly enhance and in some cases degrade our image qualities. The degradation is performed to account for environmental variations and enhancements opt to compensate the color correlations that we face while preparing our dataset. The analysis of our conducted experiments shows the effectiveness of the presented approach evaluated using different measures along with the training and validation strategies that we tailored to tackle the unavoidable color correlations that the problem at hand inherits by nature.