基于ACF和粒子滤波的在线多人检测跟踪方法

T. Kokul, A. Ramanan, U. Pinidiyaarachchi
{"title":"基于ACF和粒子滤波的在线多人检测跟踪方法","authors":"T. Kokul, A. Ramanan, U. Pinidiyaarachchi","doi":"10.1109/INTELCIS.2015.7397272","DOIUrl":null,"url":null,"abstract":"Automatically detecting and tracking multiple persons in videos is one of the main research interest in computer vision based applications. This paper presents a tracking-by-detection approach for tracking people in dynamic backgrounds with frequent occlusions by combining pre-trained generic person detector, online trained person-specific detector and a motion tracker. The popular aggregate channel features (ACF) are used to train the detectors and target specific particle filter is used as motion tracker. In order to learn right appearance of a target person, person-specific detector learns positive samples from prior frames which are detected by both generic person detector and person-specific detector. Data associations among the coincident detections of the detectors and tracker are used to update the person-specific detector and motion tracker. The person-specific detector searches the target person in a reduced region, which is defined by the associate motion tracker. A careful combination of detections of both detectors and tracker are used to locate the correct target person in the video sequence. Experiments have been carried out on Caltech pedestrian benchmark dataset. The proposed method shows better performance against state-of-the-art tracker while maintaining the tracking speed in real-time.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":"55 1","pages":"529-536"},"PeriodicalIF":0.0000,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":"{\"title\":\"Online multi-person tracking-by-detection method using ACF and particle filter\",\"authors\":\"T. Kokul, A. Ramanan, U. Pinidiyaarachchi\",\"doi\":\"10.1109/INTELCIS.2015.7397272\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Automatically detecting and tracking multiple persons in videos is one of the main research interest in computer vision based applications. This paper presents a tracking-by-detection approach for tracking people in dynamic backgrounds with frequent occlusions by combining pre-trained generic person detector, online trained person-specific detector and a motion tracker. The popular aggregate channel features (ACF) are used to train the detectors and target specific particle filter is used as motion tracker. In order to learn right appearance of a target person, person-specific detector learns positive samples from prior frames which are detected by both generic person detector and person-specific detector. Data associations among the coincident detections of the detectors and tracker are used to update the person-specific detector and motion tracker. The person-specific detector searches the target person in a reduced region, which is defined by the associate motion tracker. A careful combination of detections of both detectors and tracker are used to locate the correct target person in the video sequence. Experiments have been carried out on Caltech pedestrian benchmark dataset. The proposed method shows better performance against state-of-the-art tracker while maintaining the tracking speed in real-time.\",\"PeriodicalId\":6478,\"journal\":{\"name\":\"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)\",\"volume\":\"55 1\",\"pages\":\"529-536\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"9\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/INTELCIS.2015.7397272\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INTELCIS.2015.7397272","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9

摘要

自动检测和跟踪视频中的多人是基于计算机视觉应用的主要研究方向之一。本文提出了一种结合预训练的一般人检测器、在线训练的特定人检测器和运动跟踪器的基于检测的跟踪方法,用于在频繁遮挡的动态背景下跟踪人。采用流行的聚合通道特征(ACF)训练检测器,并采用目标特定粒子滤波器作为运动跟踪器。为了学习目标人的正确外观,特定人检测器从之前的帧中学习阳性样本,这些样本由一般人检测器和特定人检测器检测。利用检测器和跟踪器的一致检测之间的数据关联来更新个人专用检测器和运动跟踪器。特定于人的检测器在由关联运动跟踪器定义的缩小区域中搜索目标人。检测器和跟踪器的检测结合使用,以在视频序列中定位正确的目标人。在加州理工学院行人基准数据集上进行了实验。该方法在保持实时跟踪速度的同时,对最先进的跟踪器具有更好的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Online multi-person tracking-by-detection method using ACF and particle filter
Automatically detecting and tracking multiple persons in videos is one of the main research interest in computer vision based applications. This paper presents a tracking-by-detection approach for tracking people in dynamic backgrounds with frequent occlusions by combining pre-trained generic person detector, online trained person-specific detector and a motion tracker. The popular aggregate channel features (ACF) are used to train the detectors and target specific particle filter is used as motion tracker. In order to learn right appearance of a target person, person-specific detector learns positive samples from prior frames which are detected by both generic person detector and person-specific detector. Data associations among the coincident detections of the detectors and tracker are used to update the person-specific detector and motion tracker. The person-specific detector searches the target person in a reduced region, which is defined by the associate motion tracker. A careful combination of detections of both detectors and tracker are used to locate the correct target person in the video sequence. Experiments have been carried out on Caltech pedestrian benchmark dataset. The proposed method shows better performance against state-of-the-art tracker while maintaining the tracking speed in real-time.
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
On the use of probabilistic model-checking for the verification of prognostics applications Prospective, knowledge based clinical risk analysis: The OPT-model Partial deduction in predicate calculus as a tool for artificial intelligence problem complexity decreasing XML summarization: A survey Finding the pin in the haystack: A Bot Traceback service for public clouds
×
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