EmnDash:基于矢量激光投影的m序列虚线标记鲁棒高速空间跟踪

Ryota Nishizono, Tomohiro Sueishi, M. Ishikawa
{"title":"EmnDash:基于矢量激光投影的m序列虚线标记鲁棒高速空间跟踪","authors":"Ryota Nishizono, Tomohiro Sueishi, M. Ishikawa","doi":"10.1109/ISMAR-Adjunct51615.2020.00058","DOIUrl":null,"url":null,"abstract":"Camera pose estimation is commonly used for augmented reality, and it is currently expected to be integrated into sports assistant technologies. However, conventional methods face difficulties in simultaneously achieving fast estimation in milliseconds or less for sports, bright lighting environments of the outdoors, and capturing of large activity areas. In this paper, we propose EmnDash, M-sequence dashed markers on vector-based laser projection for an asynchronous high-speed dynamic camera, which provides both a graphical information display for humans and markers for the wearable high-speed camera with a high S/N ratio from a distance. One of the main notions is drawing a vector projection image with a single stroke using two dashed lines as markers. The other involves embedding the binary M-sequence as the length of each dashed line and its recognition method using locality. The recognition of the M-sequence dashed line requires only a one-shot image, which increases the robustness of tracking both in terms of camera orientation and occlusion. We experimentally confirm an increase in recognizable posture, sufficient tracking accuracy, and low-computational cost in the evaluation of a static camera. We also show good tracking ability and demonstrate immediate recovery from occlusion in the evaluation of a dynamic camera.","PeriodicalId":433361,"journal":{"name":"2020 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"EmnDash: M-sequence Dashed Markers on Vector-based Laser Projection for Robust High-speed Spatial Tracking\",\"authors\":\"Ryota Nishizono, Tomohiro Sueishi, M. Ishikawa\",\"doi\":\"10.1109/ISMAR-Adjunct51615.2020.00058\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Camera pose estimation is commonly used for augmented reality, and it is currently expected to be integrated into sports assistant technologies. However, conventional methods face difficulties in simultaneously achieving fast estimation in milliseconds or less for sports, bright lighting environments of the outdoors, and capturing of large activity areas. In this paper, we propose EmnDash, M-sequence dashed markers on vector-based laser projection for an asynchronous high-speed dynamic camera, which provides both a graphical information display for humans and markers for the wearable high-speed camera with a high S/N ratio from a distance. One of the main notions is drawing a vector projection image with a single stroke using two dashed lines as markers. The other involves embedding the binary M-sequence as the length of each dashed line and its recognition method using locality. The recognition of the M-sequence dashed line requires only a one-shot image, which increases the robustness of tracking both in terms of camera orientation and occlusion. We experimentally confirm an increase in recognizable posture, sufficient tracking accuracy, and low-computational cost in the evaluation of a static camera. We also show good tracking ability and demonstrate immediate recovery from occlusion in the evaluation of a dynamic camera.\",\"PeriodicalId\":433361,\"journal\":{\"name\":\"2020 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISMAR-Adjunct51615.2020.00058\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISMAR-Adjunct51615.2020.00058","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

相机姿态估计通常用于增强现实,目前有望集成到体育辅助技术中。然而,传统方法在同时实现运动、户外明亮照明环境和捕获大型活动区域的毫秒或更短时间内的快速估计方面存在困难。本文针对异步高速动态相机,提出了基于矢量激光投影的m序列虚线标记EmnDash,既为人类提供图形信息显示,又为远距离高信噪比的可穿戴高速相机提供标记。其中一个主要概念是用两条虚线作为标记,用一个笔画一个矢量投影图像。另一种方法是将二值m序列嵌入为每条虚线的长度,并利用局部性进行识别。m序列虚线的识别只需要一张图像,这增加了跟踪在相机方向和遮挡方面的鲁棒性。我们通过实验证实了在静态相机的评估中增加了可识别的姿态,足够的跟踪精度和低计算成本。在动态相机的评估中,我们也展示了良好的跟踪能力和从遮挡中立即恢复的能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
EmnDash: M-sequence Dashed Markers on Vector-based Laser Projection for Robust High-speed Spatial Tracking
Camera pose estimation is commonly used for augmented reality, and it is currently expected to be integrated into sports assistant technologies. However, conventional methods face difficulties in simultaneously achieving fast estimation in milliseconds or less for sports, bright lighting environments of the outdoors, and capturing of large activity areas. In this paper, we propose EmnDash, M-sequence dashed markers on vector-based laser projection for an asynchronous high-speed dynamic camera, which provides both a graphical information display for humans and markers for the wearable high-speed camera with a high S/N ratio from a distance. One of the main notions is drawing a vector projection image with a single stroke using two dashed lines as markers. The other involves embedding the binary M-sequence as the length of each dashed line and its recognition method using locality. The recognition of the M-sequence dashed line requires only a one-shot image, which increases the robustness of tracking both in terms of camera orientation and occlusion. We experimentally confirm an increase in recognizable posture, sufficient tracking accuracy, and low-computational cost in the evaluation of a static camera. We also show good tracking ability and demonstrate immediate recovery from occlusion in the evaluation of a dynamic camera.
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
×
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:604180095
Book学术官方微信