基于上下文编码器的运动背景建模

2016 Third International Conference on Artificial Intelligence and Pattern Recognition (AIPR) Pub Date : 2016-09-01 DOI:10.1109/ICAIPR.2016.7585207

Zhenshen Qu, Shuanghui Yu, Mengyu Fu

{"title":"基于上下文编码器的运动背景建模","authors":"Zhenshen Qu, Shuanghui Yu, Mengyu Fu","doi":"10.1109/ICAIPR.2016.7585207","DOIUrl":null,"url":null,"abstract":"A background modeling method for motion-based background of a video made by moving camera is proposed in this paper. We utilize the recently proposed context-encoder to model the motion-based background from a dynamic foreground. This method aims to restore the overall scene of a video by removing the moving foreground objects and learning the feature of its context. An advantage of this method is that the performance of background modeling will not be affected when the camera is moving fast.","PeriodicalId":127231,"journal":{"name":"2016 Third International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"Motion background modeling based on context-encoder\",\"authors\":\"Zhenshen Qu, Shuanghui Yu, Mengyu Fu\",\"doi\":\"10.1109/ICAIPR.2016.7585207\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A background modeling method for motion-based background of a video made by moving camera is proposed in this paper. We utilize the recently proposed context-encoder to model the motion-based background from a dynamic foreground. This method aims to restore the overall scene of a video by removing the moving foreground objects and learning the feature of its context. An advantage of this method is that the performance of background modeling will not be affected when the camera is moving fast.\",\"PeriodicalId\":127231,\"journal\":{\"name\":\"2016 Third International Conference on Artificial Intelligence and Pattern Recognition (AIPR)\",\"volume\":\"33 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 Third International Conference on Artificial Intelligence and Pattern Recognition (AIPR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICAIPR.2016.7585207\",\"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 Third International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAIPR.2016.7585207","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 11

摘要

针对运动摄像机拍摄的视频，提出了一种基于运动背景的背景建模方法。我们利用最近提出的上下文编码器从动态前景建模基于运动的背景。该方法旨在通过去除移动的前景物体并学习其上下文的特征来恢复视频的整体场景。这种方法的一个优点是，当相机快速移动时，背景建模的性能不会受到影响。

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

Motion background modeling based on context-encoder

A background modeling method for motion-based background of a video made by moving camera is proposed in this paper. We utilize the recently proposed context-encoder to model the motion-based background from a dynamic foreground. This method aims to restore the overall scene of a video by removing the moving foreground objects and learning the feature of its context. An advantage of this method is that the performance of background modeling will not be affected when the camera is moving fast.

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 Third International Conference on Artificial Intelligence and Pattern Recognition (AIPR)

自引率

0.00%

发文量