基于HOG特征的列车摄像机人体检测精度提高

2016 IEEE 5th Global Conference on Consumer Electronics Pub Date : 2016-12-27 DOI:10.1109/GCCE.2016.7800373

Shintaro Saika, Saki Takahashi, Masaru Takeuchi, J. Katto

{"title":"基于HOG特征的列车摄像机人体检测精度提高","authors":"Shintaro Saika, Saki Takahashi, Masaru Takeuchi, J. Katto","doi":"10.1109/GCCE.2016.7800373","DOIUrl":null,"url":null,"abstract":"Nowadays, researches on accident prevention using train-mounted cameras had been progressing. Our proposed method considers temporal continuity between frames by using motion vectors in addition to conventional thresholding on similarity values obtained by a human detection method using HOG features. Experiments show the effectiveness of our method as compared with a previous method using only HOG features.","PeriodicalId":416104,"journal":{"name":"2016 IEEE 5th Global Conference on Consumer Electronics","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Accuracy improvement in human detection using HOG features on train-mounted camera\",\"authors\":\"Shintaro Saika, Saki Takahashi, Masaru Takeuchi, J. Katto\",\"doi\":\"10.1109/GCCE.2016.7800373\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Nowadays, researches on accident prevention using train-mounted cameras had been progressing. Our proposed method considers temporal continuity between frames by using motion vectors in addition to conventional thresholding on similarity values obtained by a human detection method using HOG features. Experiments show the effectiveness of our method as compared with a previous method using only HOG features.\",\"PeriodicalId\":416104,\"journal\":{\"name\":\"2016 IEEE 5th Global Conference on Consumer Electronics\",\"volume\":\"10 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-12-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 IEEE 5th Global Conference on Consumer Electronics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/GCCE.2016.7800373\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE 5th Global Conference on Consumer Electronics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/GCCE.2016.7800373","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 6

摘要

目前，利用车载摄像头预防事故的研究已经取得了一定的进展。我们提出的方法考虑帧之间的时间连续性，除了使用HOG特征的人体检测方法获得的相似值的传统阈值之外，还使用运动向量。实验结果表明，与之前仅使用HOG特征的方法相比，我们的方法是有效的。

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

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Accuracy improvement in human detection using HOG features on train-mounted camera

Nowadays, researches on accident prevention using train-mounted cameras had been progressing. Our proposed method considers temporal continuity between frames by using motion vectors in addition to conventional thresholding on similarity values obtained by a human detection method using HOG features. Experiments show the effectiveness of our method as compared with a previous method using only HOG features.

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

2016 IEEE 5th Global Conference on Consumer Electronics

自引率

0.00%

发文量