VEHICLE COLLISION WARNING SYSTEM AND METHOD THEREFOR
    2.
    发明申请
    VEHICLE COLLISION WARNING SYSTEM AND METHOD THEREFOR 审中-公开
    车辆碰撞警告系统及其方法

    公开(公告)号:WO2012011715A3

    公开(公告)日:2012-05-10

    申请号:PCT/KR2011005292

    申请日:2011-07-19

    CPC classification number: B60W30/0956 B60W50/14

    Abstract: The present invention relates to a vehicle collision warning system and a method therefor. The method of the present invention comprises: a step for preprocessing the image obtained from a camera module attached to a user's automobile into an integral image; a step for detecting a vehicle candidate region by applying the AdaBoost algorithm to the integral image while adjusting the size of a vehicle detection window within a predetermined range; a step for verifying whether the detected vehicle candidate region is a valid vehicle region; a step for determining a vehicle region corresponding to the vehicle in front by clustering the verified valid vehicle regions; a step for finding the distance from the vehicle in front and the user's automobile by using the determined vehicle region; a step for deciding vehicle collision warning conditions when the distance between the vehicle in front and the vehicle of a user is below the predetermined standards; and a step for generating a vehicle collision warning when the vehicle collision warning conditions are met.

    Abstract translation: 车辆碰撞预警系统及其方法技术领域本发明涉及一种车辆碰撞预警系统及其方法。 本发明的方法包括:将从安装在用户汽车上的照相机模块获得的图像预处理成整体图像的步骤; 通过将AdaBoost算法应用于整体图像同时将车辆检测窗口的尺寸调整到预定范围内来检测车辆候补区域的步骤; 用于验证检测到的车辆候选区域是否是有效车辆区域的步骤; 通过将验证的有效车辆区域聚集来确定与前方车辆相对应的车辆区域的步骤; 通过使用确定的车辆区域来找到从前方的车辆和用户的汽车的距离的步骤; 当用户的车辆与车辆之间的距离低于预定标准时,确定车辆碰撞警告条件的步骤; 以及当满足车辆碰撞警告条件时产生车辆碰撞警告的步骤。

    SYSTEM AND METHOD FOR TRAFFIC LANE RECOGNITION
    4.
    发明申请
    SYSTEM AND METHOD FOR TRAFFIC LANE RECOGNITION 审中-公开
    用于交通车道识别的系统和方法

    公开(公告)号:WO2012011713A2

    公开(公告)日:2012-01-26

    申请号:PCT/KR2011005290

    申请日:2011-07-19

    CPC classification number: G06K9/00798

    Abstract: The present invention relates to a system and a method for traffic lane recognition and comprises: a step for preprocessing a vehicle front image obtained from a camera module attached to a vehicle into an integral image; a step for extracting a traffic lane candidate point by convoluting the integral image and a traffic lane candidate point template when a previous traffic lane equation does not exist; a step for finding a primary traffic lane equation of a traffic lane candidate cluster, which is obtained by converting the coordinates of the extracted traffic lane candidate points into the coordinates of an actual distance coordination system and clustering thereafter; and a step for selecting from the found traffic lane potential clusters a traffic lane candidate cluster pair that satisfies the predetermined conditions as the initially detected traffic lane pair.

    Abstract translation: 用于车道识别的系统和方法技术领域本发明涉及用于车道识别的系统和方法,并且包括:用于将从附接到车辆的相机模块获得的车辆前方图像预处理为整体图像的步骤; 当不存在先前的交通车道方程时,通过对积分图像和交通车道候选点模板进行卷积来提取交通车道候选点的步骤; 寻找通过将所提取的车道候选点的坐标转换为实际距离协调系统的坐标并随后聚类而获得的车道候选集群的主要车道方程的步骤; 以及从所找到的行车道可能集群中选择满足预定条件的行车道候选集群对作为初始检测到的行车道对。

Patent Agency Ranking