基于粒子滤波的TLD目标跟踪算法

2018 41st International Conference on Telecommunications and Signal Processing (TSP) Pub Date : 2018-07-01 DOI:10.1109/TSP.2018.8441515

M. A. Zanina, V. Pavlov, S. Zavjalov, S. Volvenko

{"title":"基于粒子滤波的TLD目标跟踪算法","authors":"M. A. Zanina, V. Pavlov, S. Zavjalov, S. Volvenko","doi":"10.1109/TSP.2018.8441515","DOIUrl":null,"url":null,"abstract":"This article describes a modification of the TLD object tracking algorithm. Tracking algorithm based on particle filter used instead of the built-in TLD tracking module for short-term tracking. This method allows achieving the average precision gain 12.6%. The modification was compared with original TLD. TLD with particle filter was tested on videos from VIVID dataset. The results showed how the algorithm works in difficult conditions such as rotation, scale changes and occlusions. Modified algorithm is slower than TLD, but its speed can provide working in real-time.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"TLD Object Tracking Algorithm Improved with Particle Filter\",\"authors\":\"M. A. Zanina, V. Pavlov, S. Zavjalov, S. Volvenko\",\"doi\":\"10.1109/TSP.2018.8441515\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This article describes a modification of the TLD object tracking algorithm. Tracking algorithm based on particle filter used instead of the built-in TLD tracking module for short-term tracking. This method allows achieving the average precision gain 12.6%. The modification was compared with original TLD. TLD with particle filter was tested on videos from VIVID dataset. The results showed how the algorithm works in difficult conditions such as rotation, scale changes and occlusions. Modified algorithm is slower than TLD, but its speed can provide working in real-time.\",\"PeriodicalId\":383018,\"journal\":{\"name\":\"2018 41st International Conference on Telecommunications and Signal Processing (TSP)\",\"volume\":\"100 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 41st International Conference on Telecommunications and Signal Processing (TSP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TSP.2018.8441515\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TSP.2018.8441515","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 8

摘要

本文描述了一种改进的TLD目标跟踪算法。采用基于粒子滤波的跟踪算法代替内置的TLD跟踪模块进行短期跟踪。这种方法可以实现平均精度增益12.6%。将修改后的TLD与原TLD进行了比较。采用粒子滤波方法对VIVID数据集的视频进行了TLD测试。结果显示了该算法在旋转、尺度变化和遮挡等困难条件下的工作原理。改进后的算法比TLD慢，但其速度可以提供实时工作。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

TLD Object Tracking Algorithm Improved with Particle Filter

This article describes a modification of the TLD object tracking algorithm. Tracking algorithm based on particle filter used instead of the built-in TLD tracking module for short-term tracking. This method allows achieving the average precision gain 12.6%. The modification was compared with original TLD. TLD with particle filter was tested on videos from VIVID dataset. The results showed how the algorithm works in difficult conditions such as rotation, scale changes and occlusions. Modified algorithm is slower than TLD, but its speed can provide working 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

2018 41st International Conference on Telecommunications and Signal Processing (TSP)

自引率

0.00%

发文量