首页> 外国专利> How to separate multiple subject areas, programs and equipment

How to separate multiple subject areas, programs and equipment

机译:如何区分多个学科领域,课程和设备

摘要

PROBLEM TO BE SOLVED: To separate a plurality of subjects in which occlusion occurs by using video photographed by one camera without making it necessary to acquire the information of the other cameras in the separation processing of a subject.SOLUTION: A method for separating a plurality of subjects in which occlusion occurs in object video includes: dividing each frame image into a foreground area and a background area; tracking each subject area between frame images; detecting the foreground area in which the occlusion occurs in the frame image as an occlusion area from the foreground area and the tracking result of the subject area; and determining a boundary between the plurality of subject areas tracked by the subject tracking processing in the occlusion area.
机译:解决的问题:通过使用一个摄像机拍摄的视频来分离发生遮挡的多个对象,而无需在对象的分离处理中获取其他摄像机的信息。解决方案:一种分离多个对象的方法在对象视频中发生遮挡的被摄对象包括:将每个帧图像划分为前景区域和背景区域;跟踪帧图像之间的每个主题区域;从前景区域和被摄体区域的跟踪结果中检测出在帧图像中发生遮挡的前景区域作为遮挡区域;确定在遮挡区域中通过对象跟踪处理跟踪的多个对象区域之间的边界。

著录项

  • 公开/公告号JP5838112B2

    专利类型

  • 公开/公告日2015-12-24

    原文格式PDF

  • 申请/专利权人 KDDI株式会社;

    申请/专利号JP20120076102

  • 发明设计人 三功 浩嗣;山田 健太郎;内藤 整;

    申请日2012-03-29

  • 分类号G06T7/20;G06T1/00;H04N5/232;

  • 国家 JP

  • 入库时间 2022-08-21 14:39:45

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号