首页> 外国专利> SYSTEM AND METHOD FOR PEDESTRIAN-VEHICLE COLLISION WARNING BASED ON PEDESTRIAN STATE

SYSTEM AND METHOD FOR PEDESTRIAN-VEHICLE COLLISION WARNING BASED ON PEDESTRIAN STATE

机译:基于行人状态的行车碰撞预警系统和方法

摘要

Pedestrian condition based pedestrian and vehicle collision warning system according to an embodiment of the present invention, In a pedestrian condition based pedestrian and vehicle collision warning system using a camera mounted on a vehicle, A memory in which a program for performing a collision warning method between vehicles is recorded; And a processor for executing the program, wherein the processor analyzes a driving image input from the camera through an image understanding module of the program, extracts driving environment information including pedestrians and roads, and extracts the driving environment information. Detect pedestrian candidates according to the road area and pedestrian area, the pedestrian distance according to the distance between the vehicle and the pedestrian, the image loss point, the pedestrian direction, and the degree of relevance to the vehicle driving, and detect it through the risk analysis module of the program Pedestrian behavior is recognized on the basis of the identified pedestrian candidates, the pedestrian behavior information, the relative direction information between the pedestrian and the vehicle, and the driving area of the vehicle are analyzed, and then the risk of each pedestrian is evaluated based on the analyzed results.
机译:根据本发明实施例的基于行人状况的行人和车辆碰撞警告系统,在使用安装在车辆上的照相机的基于行人状况的行人和车辆碰撞警告系统中,在其中执行碰撞警告方法的程序的存储器之间。车辆被记录;以及一种用于执行程序的处理器,其中,处理器通过程序的图像理解模块来分析从相机输入的驾驶图像,提取包括行人和道路的驾驶环境信息,并提取驾驶环境信息。根据道路区域和行人区域,根据车辆与行人之间的距离,图像丢失点,行人方向以及与车辆行驶的相关程度来确定行人距离,并通过根据识别出的行人候选者,行人行为信息,行人与车辆之间的相对方向信息以及车辆的行驶区域,识别出程序行人行为的风险分析模块,然后分析根据分析结果对每个行人进行评估。

著录项

  • 公开/公告号KR102099265B1

    专利类型

  • 公开/公告日2020-05-15

    原文格式PDF

  • 申请/专利权人 고려대학교 산학협력단;

    申请/专利号KR20180135033

  • 发明设计人 이성환;곽인엽;김성수;

    申请日2018-11-06

  • 分类号B60W30/08;B60R21;B60W50/14;G06K9;

  • 国家 KR

  • 入库时间 2022-08-21 11:04:53

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