SYSTEM AND METHOD FOR DETECTING AN OCCUPANT AND HEAD POSE USING STEREO DETECTORS
    2.
    发明公开
    SYSTEM AND METHOD FOR DETECTING AN OCCUPANT AND HEAD POSE USING STEREO DETECTORS 有权
    系统和方法检测在乘客和头部位置,通过采用立体探测器

    公开(公告)号:EP1687754A2

    公开(公告)日:2006-08-09

    申请号:EP04811824.4

    申请日:2004-11-22

    IPC分类号: G06K9/00 G06K9/62

    摘要: A system and method for detecting an occupant and head pose using stereo detectors is disclosed. In the training stage, pairs of images taken simultaneously from a pair of stereo cameras are received and components in each pair of images are identified. Features are associated with each component and a value is associated with each feature. Among them, a subset of features with best discriminative capabilities is selected and forms a strong classifier for a given component in a pair of images. In the detection stage, the strong classifiers are used in the incoming image pairs to detect components. Identified components are used to detect occupants and head pose of the occupants. Stereo detection is combined with stereo matching in a systematic way to improve occupant detection and localization.

    摘要翻译: 一种用于乘员和头部检测系统和方法,姿态使用立体检测器被游离缺失盘。 在锻炼阶段,对从一对立体摄像机同时拍摄的图像被接收并在每对图像的部件被识别。 特征与每个部件相关联和的值与每个特征相关联。 其中,与最好的判别能力特征的子集被选择并在一对图像形成用于给定的部件的强分类器。 在检测阶段中,强分类器在输入图像对用于检测组件。 标识的组件被用来检测居住者和头部姿势乘员。 立体声检测是在以提高乘员检测和定位系统的方式与立体匹配相结合。

    REAL-TIME OBSTACLE DETECTION WITH A CALIBRATED CAMERA AND KNOWN EGO-MOTION
    4.
    发明授权
    REAL-TIME OBSTACLE DETECTION WITH A CALIBRATED CAMERA AND KNOWN EGO-MOTION 有权
    ECHTZEIT-HINDERNISERKENNUNG MIT EINER KALIBRITEN KAMERA UND BEKANNTER EGO-BEWEGUNG

    公开(公告)号:EP1590771B1

    公开(公告)日:2008-04-09

    申请号:EP04707795.3

    申请日:2004-02-03

    IPC分类号: G06T7/20 G06K9/00 G05D1/02

    摘要: A method and system of real-time obstacle detection from a moving vehicle is provided. An image capturing device is calibrated (205). One or more images is captured (210) by the image capturing device. One or more real-world points is selected (215) using a tractability criterion. An image motion flow of the real-world point is determined (220). A true motion flow of the real-world point is determined (225). By comparing the image motion flow and the true motion flow, it can be determined (230) whether the real-world point is an obstacle point. Any mismatch between the image motion flows and the true motion flows are verified over time to achieve robust obstacle detection

    摘要翻译: 提供了一种来自移动车辆的实时障碍物检测方法和系统。 该方法和系统使用校准的图像捕获装置。 该方法和系统使用运动估计技术来拾取具有可靠图像运动流的点,并且在图像运动流和从图像捕获装置的自身运动计算的真实运动流之间执行非常快的稀疏匹配。 图像运动流和真实运动流之间的任何不匹配随时间被验证,以实现鲁棒的障碍物检测。

    REAL-TIME OBSTACLE DETECTION WITH A CALIBRATED CAMERA AND KNOWN EGO-MOTION
    5.
    发明公开
    REAL-TIME OBSTACLE DETECTION WITH A CALIBRATED CAMERA AND KNOWN EGO-MOTION 有权
    使用校准相机或已知EGO-MOTION实时避检测

    公开(公告)号:EP1590771A1

    公开(公告)日:2005-11-02

    申请号:EP04707795.3

    申请日:2004-02-03

    IPC分类号: G06T7/20 G06K9/00 G05D1/02

    摘要: A method and system of real-time obstacle detection from a moving vehicle is provided. An image capturing device is calibrated (205). One or more images is captured (210) by the image capturing device. One or more real-world points is selected (215) using a tractability criterion. An image motion flow of the real-world point is determined (220). A true motion flow of the real-world point is determined (225). By comparing the image motion flow and the true motion flow, it can be determined (230) whether the real-world point is an obstacle point. Any mismatch between the image motion flows and the true motion flows are verified over time to achieve robust obstacle detection