通过频域学习加强低分辨率图像中的物体检测

IF 2.3 Q2 COMPUTER SCIENCE, THEORY & METHODS
Array Pub Date : 2024-03-05 DOI:10.1016/j.array.2024.100342
Shuaiqiang Gao , Yunliang Chen , Ningning Cui , Wenjian Qin
{"title":"通过频域学习加强低分辨率图像中的物体检测","authors":"Shuaiqiang Gao ,&nbsp;Yunliang Chen ,&nbsp;Ningning Cui ,&nbsp;Wenjian Qin","doi":"10.1016/j.array.2024.100342","DOIUrl":null,"url":null,"abstract":"<div><p>To meet the requirements of navigation devices in terms of weight, power consumption, and size, it is necessary to capture low-resolution images or transmit low-resolution images to a server for object detection. However, due to the lack of details and frequency information, even state-of-the-art detection methods face challenges in accurately identifying objects. To tackle this issue, we introduce a novel upsampling method termed multi-wave representation upsampling, accompanied by a training strategy aimed at reinstating high-frequency details and augmenting the precision of object detection. Finally, we conduct empirical experiments showing that compared to alternative methodologies, our proposed approach yields images exhibiting minimal disparities in frequency compared to high-resolution counterparts. Additionally, it exhibits superior performance across objects of varying scales, while simultaneously demonstrating reduced parameter count and enhanced computational efficiency.</p></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":null,"pages":null},"PeriodicalIF":2.3000,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2590005624000080/pdfft?md5=5c4a2e90b7f870b58f73cec79a3a6c25&pid=1-s2.0-S2590005624000080-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Enhancing object detection in low-resolution images via frequency domain learning\",\"authors\":\"Shuaiqiang Gao ,&nbsp;Yunliang Chen ,&nbsp;Ningning Cui ,&nbsp;Wenjian Qin\",\"doi\":\"10.1016/j.array.2024.100342\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>To meet the requirements of navigation devices in terms of weight, power consumption, and size, it is necessary to capture low-resolution images or transmit low-resolution images to a server for object detection. However, due to the lack of details and frequency information, even state-of-the-art detection methods face challenges in accurately identifying objects. To tackle this issue, we introduce a novel upsampling method termed multi-wave representation upsampling, accompanied by a training strategy aimed at reinstating high-frequency details and augmenting the precision of object detection. Finally, we conduct empirical experiments showing that compared to alternative methodologies, our proposed approach yields images exhibiting minimal disparities in frequency compared to high-resolution counterparts. Additionally, it exhibits superior performance across objects of varying scales, while simultaneously demonstrating reduced parameter count and enhanced computational efficiency.</p></div>\",\"PeriodicalId\":8417,\"journal\":{\"name\":\"Array\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2024-03-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2590005624000080/pdfft?md5=5c4a2e90b7f870b58f73cec79a3a6c25&pid=1-s2.0-S2590005624000080-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Array\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2590005624000080\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, THEORY & METHODS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Array","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2590005624000080","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}
引用次数: 0

摘要

为了满足导航设备在重量、功耗和尺寸方面的要求,有必要捕捉低分辨率图像或将低分辨率图像传输到服务器进行目标检测。然而,由于缺乏细节和频率信息,即使是最先进的检测方法在准确识别物体方面也面临挑战。为了解决这个问题,我们引入了一种新颖的上采样方法,称为多波表示上采样,并辅以旨在恢复高频细节和提高物体检测精度的训练策略。最后,我们进行了实证实验,结果表明,与其他方法相比,我们提出的方法生成的图像与高分辨率图像相比,频率差异极小。此外,该方法在不同尺度的物体上都表现出卓越的性能,同时还减少了参数数量,提高了计算效率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Enhancing object detection in low-resolution images via frequency domain learning

To meet the requirements of navigation devices in terms of weight, power consumption, and size, it is necessary to capture low-resolution images or transmit low-resolution images to a server for object detection. However, due to the lack of details and frequency information, even state-of-the-art detection methods face challenges in accurately identifying objects. To tackle this issue, we introduce a novel upsampling method termed multi-wave representation upsampling, accompanied by a training strategy aimed at reinstating high-frequency details and augmenting the precision of object detection. Finally, we conduct empirical experiments showing that compared to alternative methodologies, our proposed approach yields images exhibiting minimal disparities in frequency compared to high-resolution counterparts. Additionally, it exhibits superior performance across objects of varying scales, while simultaneously demonstrating reduced parameter count and enhanced computational efficiency.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Array
Array Computer Science-General Computer Science
CiteScore
4.40
自引率
0.00%
发文量
93
审稿时长
45 days
×
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