Enhancing Object Detection for VIPs Using YOLOv4_Resnet101 and Text-to-Speech Conversion Model

IF 2.4 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Tahani Jaser Alahmadi, Atta Ur Rahman, Hend Khalid Alkahtani, Hisham Kholidy
{"title":"Enhancing Object Detection for VIPs Using YOLOv4_Resnet101 and Text-to-Speech Conversion Model","authors":"Tahani Jaser Alahmadi, Atta Ur Rahman, Hend Khalid Alkahtani, Hisham Kholidy","doi":"10.3390/mti7080077","DOIUrl":null,"url":null,"abstract":"Vision impairment affects an individual’s quality of life, posing challenges for visually impaired people (VIPs) in various aspects such as object recognition and daily tasks. Previous research has focused on developing visual navigation systems to assist VIPs, but there is a need for further improvements in accuracy, speed, and inclusion of a wider range of object categories that may obstruct VIPs’ daily lives. This study presents a modified version of YOLOv4_Resnet101 as backbone networks trained on multiple object classes to assist VIPs in navigating their surroundings. In comparison to the Darknet, with a backbone utilized in YOLOv4, the ResNet-101 backbone in YOLOv4_Resnet101 offers a deeper and more powerful feature extraction network. The ResNet-101’s greater capacity enables better representation of complex visual patterns, which increases the accuracy of object detection. The proposed model is validated using the Microsoft Common Objects in Context (MS COCO) dataset. Image pre-processing techniques are employed to enhance the training process, and manual annotation ensures accurate labeling of all images. The module incorporates text-to-speech conversion, providing VIPs with auditory information to assist in obstacle recognition. The model achieves an accuracy of 96.34% on the test images obtained from the dataset after 4000 iterations of training, with a loss error rate of 0.073%.","PeriodicalId":52297,"journal":{"name":"Multimodal Technologies and Interaction","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2023-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Multimodal Technologies and Interaction","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/mti7080077","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Vision impairment affects an individual’s quality of life, posing challenges for visually impaired people (VIPs) in various aspects such as object recognition and daily tasks. Previous research has focused on developing visual navigation systems to assist VIPs, but there is a need for further improvements in accuracy, speed, and inclusion of a wider range of object categories that may obstruct VIPs’ daily lives. This study presents a modified version of YOLOv4_Resnet101 as backbone networks trained on multiple object classes to assist VIPs in navigating their surroundings. In comparison to the Darknet, with a backbone utilized in YOLOv4, the ResNet-101 backbone in YOLOv4_Resnet101 offers a deeper and more powerful feature extraction network. The ResNet-101’s greater capacity enables better representation of complex visual patterns, which increases the accuracy of object detection. The proposed model is validated using the Microsoft Common Objects in Context (MS COCO) dataset. Image pre-processing techniques are employed to enhance the training process, and manual annotation ensures accurate labeling of all images. The module incorporates text-to-speech conversion, providing VIPs with auditory information to assist in obstacle recognition. The model achieves an accuracy of 96.34% on the test images obtained from the dataset after 4000 iterations of training, with a loss error rate of 0.073%.
利用YOLOv4_Resnet101和文本-语音转换模型增强vip对象检测
视力受损会影响个人的生活质素,对视障人士在物体识别及日常工作等各方面带来挑战。以前的研究主要集中在开发视觉导航系统来帮助贵宾,但在准确性、速度和包含更广泛的物体类别方面需要进一步提高,这些物体类别可能会阻碍贵宾的日常生活。本研究提出了一个修改版本的YOLOv4_Resnet101作为骨干网络,在多个对象类上训练,以帮助贵宾导航他们的周围环境。与暗网相比,在YOLOv4中使用骨干,YOLOv4_Resnet101中的ResNet-101骨干提供了更深入,更强大的特征提取网络。ResNet-101的更大容量能够更好地表示复杂的视觉模式,从而提高了目标检测的准确性。使用微软公共对象上下文(MS COCO)数据集对该模型进行了验证。使用图像预处理技术来增强训练过程,手动标注确保所有图像的准确标记。该模块结合了文本到语音的转换,为vip提供听觉信息,以帮助识别障碍。经过4000次迭代的训练,该模型对从数据集中获得的测试图像的准确率达到96.34%,损失错误率为0.073%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Multimodal Technologies and Interaction
Multimodal Technologies and Interaction Computer Science-Computer Science Applications
CiteScore
4.90
自引率
8.00%
发文量
94
审稿时长
4 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信