基于三维泽尼克矩的人体动作识别

2014 IEEE 11th International Multi-Conference on Systems, Signals & Devices (SSD14) Pub Date : 2014-05-01 DOI:10.1109/SSD.2014.6808758

Okay Arik, A. Bingöl

{"title":"基于三维泽尼克矩的人体动作识别","authors":"Okay Arik, A. Bingöl","doi":"10.1109/SSD.2014.6808758","DOIUrl":null,"url":null,"abstract":"In this work, 3D Zernike moments have been used to classify 7 basic coarse human actions in markerless 3D video sequences. The time trajectories of the Zernike moments of the moving subject have been taken as features. Even though Zernike moment orders of about 15 to 20 are required to characterize and/or reconstruct a general 3D image with reasonable fidelity, it has been found that fewer number of moments are sufficient for satisfactory action classification, due to the accumulative nature of video data. In our work, we have obtained greater than 95% recognition accuracy using as low as 3rd order Zernike moments, over the 7 basic actions considered. Recognition accuracy increased to more than 98% with 5th order moments.","PeriodicalId":168063,"journal":{"name":"2014 IEEE 11th International Multi-Conference on Systems, Signals & Devices (SSD14)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Human action recognition using 3D zernike moments\",\"authors\":\"Okay Arik, A. Bingöl\",\"doi\":\"10.1109/SSD.2014.6808758\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work, 3D Zernike moments have been used to classify 7 basic coarse human actions in markerless 3D video sequences. The time trajectories of the Zernike moments of the moving subject have been taken as features. Even though Zernike moment orders of about 15 to 20 are required to characterize and/or reconstruct a general 3D image with reasonable fidelity, it has been found that fewer number of moments are sufficient for satisfactory action classification, due to the accumulative nature of video data. In our work, we have obtained greater than 95% recognition accuracy using as low as 3rd order Zernike moments, over the 7 basic actions considered. Recognition accuracy increased to more than 98% with 5th order moments.\",\"PeriodicalId\":168063,\"journal\":{\"name\":\"2014 IEEE 11th International Multi-Conference on Systems, Signals & Devices (SSD14)\",\"volume\":\"85 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2014 IEEE 11th International Multi-Conference on Systems, Signals & Devices (SSD14)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SSD.2014.6808758\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 IEEE 11th International Multi-Conference on Systems, Signals & Devices (SSD14)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SSD.2014.6808758","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

在这项工作中，3D泽尼克矩被用来对无标记的3D视频序列中的7种基本的粗糙人类动作进行分类。将运动主体的泽尼克矩的时间轨迹作为特征。尽管要以合理的保真度表征和/或重建一般的3D图像，需要大约15到20个泽尼克矩阶，但由于视频数据的累积性，研究发现较少的矩阶就足以实现令人满意的动作分类。在我们的工作中，在考虑的7个基本动作中，我们使用低至三阶泽尼克矩获得了超过95%的识别准确率。5阶矩的识别准确率提高到98%以上。

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

Human action recognition using 3D zernike moments

In this work, 3D Zernike moments have been used to classify 7 basic coarse human actions in markerless 3D video sequences. The time trajectories of the Zernike moments of the moving subject have been taken as features. Even though Zernike moment orders of about 15 to 20 are required to characterize and/or reconstruct a general 3D image with reasonable fidelity, it has been found that fewer number of moments are sufficient for satisfactory action classification, due to the accumulative nature of video data. In our work, we have obtained greater than 95% recognition accuracy using as low as 3rd order Zernike moments, over the 7 basic actions considered. Recognition accuracy increased to more than 98% with 5th order moments.

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

2014 IEEE 11th International Multi-Conference on Systems, Signals & Devices (SSD14)

自引率

0.00%

发文量