首页> 外国专利> REAL-TIME OBJECT RE-IDENTIFICATION IN MULTI-CAMERA SYSTEM USING EDGE COMPUTING

REAL-TIME OBJECT RE-IDENTIFICATION IN MULTI-CAMERA SYSTEM USING EDGE COMPUTING

机译:基于边缘计算的多机位系统实时目标识别

摘要

To provide a video surveillance system that uses high quality but inexpensive video cameras that can perform efficient real-time video image analysis based on video images for object re-identification at each site of multiple camera images.SOLUTION: An operator of a monitoring device 20 monitors video images from multiple video cameras 10 and, when a target object is observed, a target image containing the object is transmitted to all video cameras for object re-identification. Each video camera implements an object re-identification algorithm to identify the target in video images captured by that camera in real time. The object re-identification algorithm comprises calculating a frequency domain similarity measure between the target image and test images captured by the camera. The multiple cameras also transmit object re-identification results to each other.SELECTED DRAWING: Figure 1
机译:提供一种视频监视系统,该系统使用高质量但价格便宜的摄像机,该摄像机可以基于视频图像执行高效的实时视频图像分析,以便在多个摄像机图像的每个位置重新识别对象。解决方案:监视设备的操作员20监视来自多个摄像机10的视频图像,并且当观察到目标物体时,包含该物体的目标图像被传输到所有摄像机以重新识别物体。每个摄像机都实现了对象重新识别算法,以实时识别该摄像机捕获的视频图像中的目标。对象重新识别算法包括计算目标图像和由照相机捕获的测试图像之间的频域相似性度量。多台摄像机还相互传输对象重新识别结果。选定的图:图1

著录项

  • 公开/公告号JP2019062527A

    专利类型

  • 公开/公告日2019-04-18

    原文格式PDF

  • 申请/专利权人 KONICAMINOLTA LABORATORY USA INC;

    申请/专利号JP20180153376

  • 发明设计人 RAHMAN KHORSANDI;JUNE AMANO;

    申请日2018-08-17

  • 分类号H04N5/232;H04N7/18;G06T7/262;

  • 国家 JP

  • 入库时间 2022-08-21 12:23:07

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