Improved Intelligent Image Segmentation Algorithm for Mechanical Sensors in Industrial IoT: A Joint Learning Approach

Xin Xie,Fengping Hu,Ao Yu,Tiancheng Wan,Tijian Cai,Mohamed Cheriet,Bin Wang

doi:10.3390/electronics10040446

Xin Xie, Fengping Hu + Show 5 more

Open Access

https://doi.org/10.3390/electronics10040446

Copy DOI

Abstract

The industrial Internet of Things (IoT) can monitor production in real-time by collecting the status of parts on the production line with cameras. It is easy to have bright and dark areas in the same image because of the smooth surfaces of mechanical parts and the unstable light source, which affects semantic segmentation’s performance. This paper proposes a joint learning method to eliminate the influence of illumination on semantic segmentation. Semantic image segmentation and image decomposition are jointly trained in the same model, and the reflectance image is used to guide the semantic segmentation task without the illumination component. Moreover, this paper adopts an enhanced convolution kernel to improve the pixel accuracy and BN fusion to enhance the inference speed, optimizing the model to meet real-time detection needs. In the experiments, a dataset of real gear parts was collected from industrial IoT cameras. The experimental results show that the proposed joint learning approach outperforms the state-of-the-art methods in the task of edge mechanical part detection, with about 4% pixel accuracy improvement.

Highlights

With the development of Industry 4.0, promoting the combination of the Internet of Things (IoT) and modern manufacturing is of great significance to promoting industrial production modernization [1]
We use image segmentation attributes as an assistant to improve the performance of other tasks by joint learning
The images of mechanical parts collected by industrial IoT cameras are affected by the light source

Summary

Introduction

With the development of Industry 4.0, promoting the combination of the Internet of Things (IoT) and modern manufacturing is of great significance to promoting industrial production modernization [1]. Common mechanical parts, such as gears and slender shafts, are widely used in the military, aerospace, automobile and manufacturing industries. Ofir N et al [4] regarded edge detection as a group of discrete curves to search for faint edges with noise interference, and effectively detect these faint edges These traditional methods mostly extract the edge by analyzing the shape, texture, color and other features of the target image [5], calculating the parts’ size. We need to have professional knowledge and parameter adjustment process, which cannot be widely applied

Objectives

Methods

Results

Conclusion