Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection

Author:

Santos David O.1ORCID,Montalvão Jugurta2ORCID,Araujo Charles A. C.3,Lebre Ulisses D. E. S.3,Ferreira Tarso V.2ORCID,Freire Eduardo O.24ORCID

Affiliation:

1. Department of Electrical Engineering, Federal University of Campina Grande, Campina Grande 58401-490, Brazil

2. Department of Electrical Engineering, Federal University of Sergipe, São Cristóvão 49100-000, Brazil

3. Electrical Operation, Eneva S.A., Barra dos Coqueiros 49140-000, Brazil

4. National Council of Scientific and Technical Research—CONICET, Godoy Cruz, Buenos Aires 2290, Argentina

Abstract

This paper explores a data augmentation approach for images of rigid bodies, particularly focusing on electrical equipment and analogous industrial objects. By leveraging manufacturer-provided datasheets containing precise equipment dimensions, we employed straightforward algorithms to generate synthetic images, permitting the expansion of the training dataset from a potentially unlimited viewpoint. In scenarios lacking genuine target images, we conducted a case study using two well-known detectors, representing two machine-learning paradigms: the Viola–Jones (VJ) and You Only Look Once (YOLO) detectors, trained exclusively on datasets featuring synthetic images as the positive examples of the target equipment, namely lightning rods and potential transformers. Performances of both detectors were assessed using real images in both visible and infrared spectra. YOLO consistently demonstrates F1 scores below 26% in both spectra, while VJ’s scores lie in the interval from 38% to 61%. This performance discrepancy is discussed in view of paradigms’ strengths and weaknesses, whereas the relatively high scores of at least one detector are taken as empirical evidence in favor of the proposed data augmentation approach.

Funder

ENEVA S.A.

Publisher

MDPI AG

Reference46 articles.

1. A survey of modern deep learning based object detection models;Zaidi;Digit. Signal Process.,2022

2. Object detection with deep learning: A review;Zhao;IEEE Trans. Neural Netw. Learn. Syst.,2019

3. Zou, Z., Shi, Z., Guo, Y., and Ye, J. (2019). Object detection in 20 years: A survey. arXiv.

4. Rapid object detection using a boosted cascade of simple features;Viola;Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001,2001

5. Robust real-time face detection;Viola;Int. J. Comput. Vis.,2004

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3