改进的SSD,用于小目标检测

Xiang Li, Haibo Luo
{"title":"改进的SSD,用于小目标检测","authors":"Xiang Li, Haibo Luo","doi":"10.1145/3449388.3449391","DOIUrl":null,"url":null,"abstract":"SSD is one of heuristic one-stage target detection approaches. Although it has got impressive results in general target detection, it still struggles in small-size object detection and precise location. In this paper, we proposed an improved SSD which forces on the small-size target detection. We include a shallow and high resolution feature into the hierarchical detection feature which are used for prediction. Then, we fuse the detection features (including the shallow and high resolution one) as a feature pyramid through some convolution layers and unsample operations to pass information from deep features to the shallow ones, aiming to enrich the semantic information of the shallow features. To make the network easier to converge, we add a L2 normalization to the bottom detection feature of the feature pyramid to make a norm balance between each pyramid feature. The experimental results on the VEDAI dataset show that the proposed method has obtained impressive progress than the original SSD for the small targets detection.","PeriodicalId":326682,"journal":{"name":"2021 6th International Conference on Multimedia and Image Processing","volume":"98 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"An Improved SSD for small target detection\",\"authors\":\"Xiang Li, Haibo Luo\",\"doi\":\"10.1145/3449388.3449391\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"SSD is one of heuristic one-stage target detection approaches. Although it has got impressive results in general target detection, it still struggles in small-size object detection and precise location. In this paper, we proposed an improved SSD which forces on the small-size target detection. We include a shallow and high resolution feature into the hierarchical detection feature which are used for prediction. Then, we fuse the detection features (including the shallow and high resolution one) as a feature pyramid through some convolution layers and unsample operations to pass information from deep features to the shallow ones, aiming to enrich the semantic information of the shallow features. To make the network easier to converge, we add a L2 normalization to the bottom detection feature of the feature pyramid to make a norm balance between each pyramid feature. The experimental results on the VEDAI dataset show that the proposed method has obtained impressive progress than the original SSD for the small targets detection.\",\"PeriodicalId\":326682,\"journal\":{\"name\":\"2021 6th International Conference on Multimedia and Image Processing\",\"volume\":\"98 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-01-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 6th International Conference on Multimedia and Image Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3449388.3449391\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 6th International Conference on Multimedia and Image Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3449388.3449391","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

SSD是一种启发式的单阶段目标检测方法。虽然它在一般目标检测方面取得了令人瞩目的成绩,但在小尺寸目标检测和精确定位方面仍然存在困难。在本文中,我们提出了一种改进的固态硬盘,用于小尺寸目标的检测。我们在分层检测特征中加入了用于预测的浅分辨率和高分辨率特征。然后,我们通过卷积层和反采样操作将检测特征(包括浅分辨率和高分辨率特征)融合成一个特征金字塔,将深度特征的信息传递给浅分辨率特征,以丰富浅分辨率特征的语义信息。为了使网络更容易收敛,我们在特征金字塔的底部检测特征上增加了L2归一化,使每个金字塔特征之间实现了范数平衡。在VEDAI数据集上的实验结果表明,该方法在小目标检测方面取得了显著的进步。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
An Improved SSD for small target detection
SSD is one of heuristic one-stage target detection approaches. Although it has got impressive results in general target detection, it still struggles in small-size object detection and precise location. In this paper, we proposed an improved SSD which forces on the small-size target detection. We include a shallow and high resolution feature into the hierarchical detection feature which are used for prediction. Then, we fuse the detection features (including the shallow and high resolution one) as a feature pyramid through some convolution layers and unsample operations to pass information from deep features to the shallow ones, aiming to enrich the semantic information of the shallow features. To make the network easier to converge, we add a L2 normalization to the bottom detection feature of the feature pyramid to make a norm balance between each pyramid feature. The experimental results on the VEDAI dataset show that the proposed method has obtained impressive progress than the original SSD for the small targets detection.
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
自引率
0.00%
发文量
0
期刊最新文献
Target Classification Algorithms Based on Multispectral Imaging: A Review Vehicle Flow Detection Based on Improved Deep Structure and Deep Sort Research on Behavior Recognition of Dairy Goat Based on Multi-model Fusion Research on UAV Image Mosaic Based on Improved AKAZE Feature and VFC Algorithm Correlation Filters with Pre-position by Reconstruction Error for Visual Tracking
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1