Object Detection for Cargo Unloading System Based on Fuzzy C Means

Sunwoo Hwang,Jongun Won,Youngmin Kim,Jaemin Park,Yongjang Kwon

doi:10.32604/cmc.2022.023295

Abstract

With the recent increase in the utilization of logistics and courier services, it is time for research on logistics systems fused with the fourth industry sector. Algorithm studies related to object recognition have been actively conducted in convergence with the emerging artificial intelligence field, but so far, algorithms suitable for automatic unloading devices that need to identify a number of unstructured cargoes require further development. In this study, the object recognition algorithm of the automatic loading device for cargo was selected as the subject of the study, and a cargo object recognition algorithm applicable to the automatic loading device is proposed to improve the amorphous cargo identification performance. The fuzzy convergence algorithm is an algorithm that applies Fuzzy C Means to existing algorithm forms that fuse YOLO(You Only Look Once) and Mask R-CNN(Regions with Convolutional Neuron Networks). Experiments conducted using the fuzzy convergence algorithm showed an average of 33 FPS(Frames Per Second) and a recognition rate of 95%. In addition, there were significant improvements in the range of actual box recognition. The results of this study can contribute to improving the performance of identifying amorphous cargoes in automatic loading devices.

Highlights

Artificial intelligence and deep learning technologies have recently developed faster than in the past few centuries, and with the development of these technologies, various deep learning algorithms are being used in the field of object and pattern recognition
The fuzzy C mean convergence algorithm compensated for the shortcomings of the two existing algorithms and showed high cargo recognition bounding box density of the existing algorithms
This study was proposed based on the YOLOv2 model, which enables rapid object detection and classification for cargo recognition of automatic unloading equipment

Summary

Introduction

Artificial intelligence and deep learning technologies have recently developed faster than in the past few centuries, and with the development of these technologies, various deep learning algorithms are being used in the field of object and pattern recognition. It is difficult to apply the object and pattern recognition field to handle unstructured cargoes of different shapes and sizes. With the recent the growth of the online market, the logistics center is investing in developing innovative technologies to handle the increased volume. CMC, 2022, vol., no.2 for improving cargo handling efficiency must requires a deep running algorithm technology that can recognize objects. Algorithms that are suitable for automatic unloading systems that require the identification of large numbers of unstructured cargo need to be developed. This paper aims to propose a deep learning algorithm for the recognition of cargo objects in automatic unloading devices. We would like to analyze the deep learning algorithm and prior research and develop an applicable improvement plan.

Objectives

Methods

Findings

Conclusion