基于chebichef矩不变量和时间模板的人体动作识别方法

2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics Pub Date : 2012-08-26 DOI:10.1109/IHMSC.2012.114

Yanan Lu, Yakang Li, Yang Shen, Fang Ding, Xiaofeng Wang, Jicheng Hu, Songtao Ding

{"title":"基于chebichef矩不变量和时间模板的人体动作识别方法","authors":"Yanan Lu, Yakang Li, Yang Shen, Fang Ding, Xiaofeng Wang, Jicheng Hu, Songtao Ding","doi":"10.1109/IHMSC.2012.114","DOIUrl":null,"url":null,"abstract":"In this paper, a new human action recognition method based on Tchebichef moment invariants and temporal templates is presented. We use the motion energy image (MEI) and motion history image (MHI) as the feature representation of the human action at first. Then the Tchebichef moment invariants extract the feature vectors of MEI and MHI. Tchebichef moment invariants perform better than Hu moment invariants and Zernike moment invariants. Finally cluster the actions and use the nearest neighbor algorithm to recognize each human action. The result of these experiments suggests that this method has a high recognition rate in in both noise-free and noisy condition. Therefore, the algorithm has a good robustness.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"19","resultStr":"{\"title\":\"A Human Action Recognition Method Based on Tchebichef Moment Invariants and Temporal Templates\",\"authors\":\"Yanan Lu, Yakang Li, Yang Shen, Fang Ding, Xiaofeng Wang, Jicheng Hu, Songtao Ding\",\"doi\":\"10.1109/IHMSC.2012.114\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, a new human action recognition method based on Tchebichef moment invariants and temporal templates is presented. We use the motion energy image (MEI) and motion history image (MHI) as the feature representation of the human action at first. Then the Tchebichef moment invariants extract the feature vectors of MEI and MHI. Tchebichef moment invariants perform better than Hu moment invariants and Zernike moment invariants. Finally cluster the actions and use the nearest neighbor algorithm to recognize each human action. The result of these experiments suggests that this method has a high recognition rate in in both noise-free and noisy condition. Therefore, the algorithm has a good robustness.\",\"PeriodicalId\":431532,\"journal\":{\"name\":\"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-08-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"19\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IHMSC.2012.114\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IHMSC.2012.114","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 19

摘要

提出了一种基于切比切夫矩不变量和时间模板的人体动作识别新方法。我们首先使用运动能量图像(MEI)和运动历史图像(MHI)作为人体动作的特征表示。然后利用chebichef矩不变量提取MEI和MHI的特征向量。chebichef矩不变量的性能优于Hu矩不变量和Zernike矩不变量。最后对动作进行聚类，并使用最近邻算法对每个人的动作进行识别。实验结果表明，该方法在无噪声和有噪声条件下都具有较高的识别率。因此，该算法具有良好的鲁棒性。

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

A Human Action Recognition Method Based on Tchebichef Moment Invariants and Temporal Templates

In this paper, a new human action recognition method based on Tchebichef moment invariants and temporal templates is presented. We use the motion energy image (MEI) and motion history image (MHI) as the feature representation of the human action at first. Then the Tchebichef moment invariants extract the feature vectors of MEI and MHI. Tchebichef moment invariants perform better than Hu moment invariants and Zernike moment invariants. Finally cluster the actions and use the nearest neighbor algorithm to recognize each human action. The result of these experiments suggests that this method has a high recognition rate in in both noise-free and noisy condition. Therefore, the algorithm has a good robustness.

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

2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics

自引率

0.00%

发文量