Method and apparatus for self-diagnostics of a vision system
    1.
    发明授权
    Method and apparatus for self-diagnostics of a vision system 有权
    视觉系统自我诊断的方法和装置

    公开(公告)号:US07003384B2

    公开(公告)日:2006-02-21

    申请号:US10692949

    申请日:2003-10-24

    IPC分类号: G05D1/00 G06F7/00

    CPC分类号: B60R21/01538 G06T7/73

    摘要: A method and apparatus (20) for recognizing and determining a location of an object (40) in an area of interest (31) comprises an imaging device (61) for obtaining an image of the area of interest. At least three identifying marks (104) are located at predetermined positions in the area of interest (31). The apparatus (20) also comprises a memory (78) in which the predetermined positions of the at least three identifying marks (104) are stored. A controller (80) determines whether the imaging device (61) is calibrated properly by analyzing the image obtained by the imaging device to determine whether positions of the at least three identifying marks (104) in the obtained image correspond to the predetermined positions stored in the memory (78). The controller (80) is also adapted to determine whether a view of the area of interest (31) from the imaging device (61) is obstructed.

    摘要翻译: 一种用于识别和确定感兴趣区域(31)中的物体(40)的位置的方法和装置(20)包括用于获得感兴趣区域的图像的成像装置(61)。 至少三个识别标记(104)位于感兴趣区域(31)中的预定位置处。 装置(20)还包括其中存储有至少三个识别标记(104)的预定位置的存储器(78)。 控制器(80)通过分析由成像装置获得的图像来确定成像装置(61)是否被正确地校准,以确定所获得的图像中的至少三个识别标记(104)的位置是否对应于存储在 存储器(78)。 控制器(80)还适于确定来自成像装置(61)的感兴趣区域(31)的视图是否被阻挡。

    Method and apparatus for determining an occupant's head location in an actuatable occupant restraining system
    2.
    发明授权
    Method and apparatus for determining an occupant's head location in an actuatable occupant restraining system 失效
    用于确定在可起动的乘员约束系统中乘客的头部位置的方法和装置

    公开(公告)号:US07379559B2

    公开(公告)日:2008-05-27

    申请号:US10447248

    申请日:2003-05-28

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00248 G06T7/73

    摘要: An apparatus (20) for determining a location of a person's head (90) includes stereo vision system (60) for imaging an area of interest such as the interior of a vehicle (26). The vision system provides an image signal of the area of interest. An analyzer (80) analyzes the image signal to identify head candidates (90′, 210, 212, 214, 216) in the area of interest and provides data regarding any identified head candidates in the area of interest. A processor (80) processes the provided data regarding identified head candidates to locate the person's head. In an air bag restraining system (22), a controller (50) monitors the location of the person's head and controls an air bag (34) in response to a sensed crash condition (52) and the location of the person's head.

    摘要翻译: 用于确定人的头部(90)的位置的装置(20)包括用于对诸如车辆内部(26)的感兴趣区域成像的立体视觉系统(60)。 视觉系统提供感兴趣区域的图像信号。 分析器(80)分析图像信号以识别感兴趣区域中的首选候选(90',210,212,214,216),并且提供关于感兴趣区域中关于任何识别的首选候选的数据。 处理器(80)处理所提供的关于所识别的头部候选者的数据以定位该人的头部。 在气囊限制系统(22)中,控制器(50)根据感测到的碰撞状况(52)和人的头部的位置来监视人的头部的位置并控制气囊(34)。

    Method and apparatus for arbitrating outputs from multiple pattern recognition classifiers
    4.
    发明授权
    Method and apparatus for arbitrating outputs from multiple pattern recognition classifiers 失效
    用于仲裁来自多个模式识别分类器的输出的方法和装置

    公开(公告)号:US07471832B2

    公开(公告)日:2008-12-30

    申请号:US10785278

    申请日:2004-02-24

    IPC分类号: G06K9/62

    摘要: A system (400) for classifying an input image into one of a plurality of output classes includes a plurality of pattern recognition classifiers (420, 422, 424). Each of the plurality of pattern recognition classifiers determines a candidate output class and at least one rejected output class for the input image from an associated subset of the plurality of output classes. Each classifier generates a confidence value associated with the classifier based on the determination. An arbitrator (430) selects a classifier having the best associated confidence value and eliminates the at least one rejected class determined at the selected classifier from consideration as the associated class for the input image.

    摘要翻译: 用于将输入图像分类成多个输出类别中的一个的系统(400)包括多个模式识别分类器(420,422,424)。 多个模式识别分类器中的每一个从多个输出类别的相关联的子集确定输入图像的候选输出类别和至少一个被拒绝的输出类别。 每个分类器基于确定产生与分类器相关联的置信度值。 仲裁器(430)选择具有最佳关联置信度值的分类器,并且将从所考虑的所选分类器确定的至少一个被拒绝类别排除为用于输入图像的关联类别。

    Method and apparatus for controlling classification and classification switching in a vision system
    5.
    发明授权
    Method and apparatus for controlling classification and classification switching in a vision system 有权
    用于控制视觉系统中的分类和分类切换的方法和装置

    公开(公告)号:US07636479B2

    公开(公告)日:2009-12-22

    申请号:US10785920

    申请日:2004-02-24

    IPC分类号: G06K9/62

    摘要: A system for classifying image data includes a vision system (58) for continuously imaging an area (42) of interest and providing an image signals. A classifier (84) determines an image class corresponding to each image signal, determines a confidence level for each determined image class, determines a time period for the confidence level, and establishes an image classification in response thereto. Switching between image classifications is in response to the confidence level and time period of the confidence level. When used in a vehicle restraining system (20), other monitor vehicle parameters (54) can be used to adjust the confidence levels and time periods needed to switch between image classifications.

    摘要翻译: 用于对图像数据进行分类的系统包括用于对感兴趣的区域(42)连续成像并提供图像信号的视觉系统(58)。 分类器(84)确定对应于每个图像信号的图像类别,确定每个确定的图像类别的置信水平,确定置信水平的时间段,并响应于此建立图像分类。 图像分类之间的切换是响应置信水平的置信水平和时间段。 当在车辆限制系统(20)中使用时,可以使用其他监视器车辆参数(54)来调整在图像分类之间切换所需的置信水平和时间段。

    Apparatus and method for determining vehicle occupant characteristic utilizing imaging with provided light
    6.
    发明授权
    Apparatus and method for determining vehicle occupant characteristic utilizing imaging with provided light 失效
    利用所提供的光利用成像确定车辆乘员特性的装置和方法

    公开(公告)号:US06947575B2

    公开(公告)日:2005-09-20

    申请号:US09865154

    申请日:2001-05-24

    CPC分类号: B60R21/01538 G06T7/254

    摘要: An apparatus (30) and associated method determine a vehicle occupant characteristic. An imager (32) collects a first image of an occupant location while the occupant location is subject to a first lighting condition. A light source (38) provides light onto the occupant location. The imager (32) collects a second image of the occupant location while the occupant location is subject to the first lighting condition and the provided light. A subtractor device (50) generates a third image of the occupant location indicative of the difference between the first and second images. An image processing device (52) processes the third image to determine the vehicle occupant characteristic.

    摘要翻译: 装置(30)和相关方法确定车辆乘员特性。 成像器(32)收集乘员位置的第一图像,同时乘客位置经受第一照明条件。 光源(38)向乘员位置提供光。 成像器(32)收集乘员位置的第二图像,同时乘客位置经受第一照明条件和所提供的光。 减法器装置(50)生成表示第一和第二图像之间的差异的乘员位置的第三图像。 图像处理装置(52)处理第三图像以确定车辆乘员特性。

    Intrusion detection system using linear imaging
    7.
    发明授权
    Intrusion detection system using linear imaging 失效
    入侵检测系统采用线性成像

    公开(公告)号:US06914526B2

    公开(公告)日:2005-07-05

    申请号:US10104173

    申请日:2002-03-22

    IPC分类号: B60R25/10 G08B13/00

    CPC分类号: B60R25/305 B60R25/1004

    摘要: A vehicle intrusion detection system (10) for detecting an intrusion condition of a vehicle (12) having an occupant compartment (14) partially defined by an outer structure (30) of the vehicle, comprises an actuatable illuminator (40) mounted in the vehicle and having a limited field of illumination (52) extending within the vehicle occupant compartment adjacent the vehicle outer structure. A linear imager (60) mounted in the vehicle (12) has a field of view (62) that substantially coincides with the field of illumination (52) of the illuminator (40). A controller (70) compares a first image taken by the imager (60) when the illuminator (40) is actuated and a second image taken by the imager when the illuminator is unactuated to help determine the existence of an intrusion condition of the vehicle.

    摘要翻译: 一种车辆入侵检测系统(10),用于检测具有由车辆的外部结构(30)部分地限定的乘员室(14)的车辆(12)的入侵状况,包括安装在车辆中的致动照明器(40) 并且具有在邻近车辆外部结构的车辆乘员舱内延伸的有限的照明领域(52)。 安装在车辆(12)中的线性成像器(60)具有与照明器(40)的照明场(52)大致重合的视场(62)。 当照明器(40)被致动时,控制器(70)比较由成像器(60)拍摄的第一图像和当照明器未致动时由成像器拍摄的第二图像,以帮助确定车辆的入侵状况的存在。

    Enhancement of vehicle interior digital images
    9.
    发明授权
    Enhancement of vehicle interior digital images 有权
    增强车内数字图像

    公开(公告)号:US07123747B2

    公开(公告)日:2006-10-17

    申请号:US10156592

    申请日:2002-05-28

    IPC分类号: G06K9/00

    摘要: A method for helping to control a vehicle occupant protection device (22) includes taking an image of the vehicle interior with a digital imager (50) having an array of pixels (53). A contiguous portion of the image less than the entire image is selected. At least one image enhancement technique is applied to the selected image portion. The enhanced image portion is combined with the other portions of the image to make an enhanced image. The enhanced image is analyzed to detect at least one of features and characteristics of the enhanced image. Alternatively, a selected non-contiguous group of the pixels (53) of the imager (50) are read out, as representative of the entire image, to estimate the illumination levels across the entire array of pixels. In one aspect, the imager shutter (56) speed may be controlled to enhance the image.

    摘要翻译: 用于帮助控制车辆乘员保护装置(22)的方法包括利用具有像素阵列(53)的数字成像器(50)拍摄车辆内部的图像。 选择小于整个图像的图像的连续部分。 至少一个图像增强技术被应用于所选择的图像部分。 增强图像部分与图像的其他部分组合以形成增强图像。 分析增强图像以检测增强图像的特征和特征中的至少一个。 或者,作为整个图像的代表,读出成像器(50)的像素(53)的选定的非连续组,以估计整个像素阵列上的照明水平。 在一个方面,可以控制成像器快门(56)的速度以增强图像。

    Occupant sensing system and method via imaging
    10.
    发明授权
    Occupant sensing system and method via imaging 失效
    乘员感应系统及其成像方法

    公开(公告)号:US06810133B2

    公开(公告)日:2004-10-26

    申请号:US09872527

    申请日:2001-06-01

    IPC分类号: G06K900

    CPC分类号: B60R21/01538 G06T7/254

    摘要: An occupant sensing system (12) and an associated method provide for the sensing of an occupant (14). An illuminating element (46) of the system (12)selectively illuminates the interior of a vehicle (8). An image sensor (50) acquires a first image of the interior of the vehicle (8) when the interior of the vehicle is illuminated by ambient sources only and acquires a second image of the interior of the vehicle when the interior of the vehicle is illuminated by ambient sources and the illuminating element (46). A controller (34) removes the effect of ambient sources by comparing the first and second images to produce a third image of the interior of the vehicle (8) as illuminated by the illuminating element (46) only. The controller (34) determines the presence of an occupant (14) by comparing the third image to a produced map of the interior of the vehicle (8).

    摘要翻译: 乘客感测系统(12)和相关联的方法提供对乘员(14)的感测。 系统(12)的照明元件(46)选择性地照亮车辆(8)的内部。 当车辆的内部仅被环境源照明时,图像传感器(50)获取车辆内部的第一图像,并且当车辆的内部被照亮时获取车辆内部的第二图像 通过环境源和照明元件(46)。 控制器(34)通过比较第一和第二图像以产生仅由照明元件(46)照明的车辆(8)的内部的第三图像来消除环境源的影响。 控制器(34)通过将第三图像与生成的车辆内部(8)的地图进行比较来确定乘员(14)的存在。