首页> 外国专利> AUTOMATED SCENARIO RECOGNITION AND REPORTING USING NEURAL NETWORKS

AUTOMATED SCENARIO RECOGNITION AND REPORTING USING NEURAL NETWORKS

机译:使用神经网络自动进行场景识别和报告

摘要

An incident avoidance system includes a plurality of imaging sensors and aneural computing system. The neural networkcomputing system is configured to receive an image feed from at least one ofthe plurality of imaging sensors and analyze the imagefeed to identify a pattern of behavior exhibited by subjects within the imagefeed. The neural computing system is further configuredto determine whether the identified pattern of behavior matches a known typeof behavior and send a command to one or more remotedevices. One or both of a type of the command or the one or more removedevices are selected based on a result of the determinationwhether the identified pattern of behavior matches a known type of behavior.
机译:事故避免系统包括多个成像传感器和一个神经计算系统。神经网络计算系统被配置为从以下至少之一接收图像馈送多个成像传感器并分析图像提要以识别图像中主体显示的行为模式饲料。进一步配置神经计算系统确定所确定的行为模式是否与已知类型匹配行为并发送命令到一个或多个远程设备。一种或两种以上的命令,或者一个或多个删除根据确定结果选择设备所识别的行为模式是否与已知的行为类型匹配。

著录项

  • 公开/公告号CA3071120A1

    专利类型

  • 公开/公告日2019-02-07

    原文格式PDF

  • 申请/专利权人 CUBIC CORPORATION;

    申请/专利号CA20183071120

  • 发明设计人 KAYHANI NIOSHA;REYMANN STEFFEN;

    申请日2018-07-31

  • 分类号G06K9;G06K9/62;

  • 国家 CA

  • 入库时间 2022-08-21 11:58:32

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