基于运动势能的连体追踪器

Zhao-Qian Tang, Mingyang Liu, Yun Gao
{"title":"基于运动势能的连体追踪器","authors":"Zhao-Qian Tang, Mingyang Liu, Yun Gao","doi":"10.1109/ICSP54964.2022.9778626","DOIUrl":null,"url":null,"abstract":"Siamese trackers have been widely concerned recently. Though many trackers have obtained better performance when the target encounter fast motion or changes the direction of motion, most trackers still utilize the previous frame’s center to generate the center of the search box in the current frame, which may lead to loss of the tracked target. In this paper, we utilize the potential energy to the expended target detection region. Specially, we predict the search area of the current frame by analyzing the potential energy of the object’s historical frame. Abundant experiments show that our tracker with better robustness than most trackers on tracking benchmarks. Especially, the compared results show our tracker has an excellent performance in the fast motion challenge.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Siamese tracker based on motion potential energy\",\"authors\":\"Zhao-Qian Tang, Mingyang Liu, Yun Gao\",\"doi\":\"10.1109/ICSP54964.2022.9778626\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Siamese trackers have been widely concerned recently. Though many trackers have obtained better performance when the target encounter fast motion or changes the direction of motion, most trackers still utilize the previous frame’s center to generate the center of the search box in the current frame, which may lead to loss of the tracked target. In this paper, we utilize the potential energy to the expended target detection region. Specially, we predict the search area of the current frame by analyzing the potential energy of the object’s historical frame. Abundant experiments show that our tracker with better robustness than most trackers on tracking benchmarks. Especially, the compared results show our tracker has an excellent performance in the fast motion challenge.\",\"PeriodicalId\":363766,\"journal\":{\"name\":\"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)\",\"volume\":\"62 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-04-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSP54964.2022.9778626\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSP54964.2022.9778626","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

连体追踪器最近受到了广泛关注。虽然许多跟踪器在目标遇到快速运动或改变运动方向时获得了更好的性能,但大多数跟踪器仍然使用前一帧的中心在当前帧中生成搜索框的中心,这可能导致被跟踪目标的丢失。在本文中,我们将势能用于扩展的目标检测区域。特别地,我们通过分析目标历史框架的势能来预测当前框架的搜索区域。大量的实验表明,我们的跟踪器在跟踪基准上比大多数跟踪器具有更好的鲁棒性。对比结果表明,该跟踪器在快速运动挑战中具有优异的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Siamese tracker based on motion potential energy
Siamese trackers have been widely concerned recently. Though many trackers have obtained better performance when the target encounter fast motion or changes the direction of motion, most trackers still utilize the previous frame’s center to generate the center of the search box in the current frame, which may lead to loss of the tracked target. In this paper, we utilize the potential energy to the expended target detection region. Specially, we predict the search area of the current frame by analyzing the potential energy of the object’s historical frame. Abundant experiments show that our tracker with better robustness than most trackers on tracking benchmarks. Especially, the compared results show our tracker has an excellent performance in the fast motion challenge.
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:481959085
Book学术官方微信