Method and apparatus for self-diagnostics of a vision system
    1.
    发明申请
    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:US20050090957A1

    公开(公告)日:2005-04-28

    申请号:US10692949

    申请日:2003-10-24

    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 selectively extracting training data for a pattern recognition classifier using grid generation
    2.
    发明申请
    Method and apparatus for selectively extracting training data for a pattern recognition classifier using grid generation 审中-公开
    用于使用网格生成来选择性地提取用于模式识别分类器的训练数据的方法和装置

    公开(公告)号:US20050175235A1

    公开(公告)日:2005-08-11

    申请号:US10772655

    申请日:2004-02-05

    IPC分类号: G06K9/46 G06K9/62

    CPC分类号: G06K9/6256

    摘要: A system (600) for selectively generating training data for a pattern recognition classifier includes an image synthesizer (606) that combines a plurality of training images from an output class into a class composite image. A grid generator (608) generates a grid pattern representing the output class from the class composite image. A feature extractor (610) extracts feature data from the plurality of training images according to the generated grid pattern.

    摘要翻译: 用于选择性地生成用于模式识别分类器的训练数据的系统(600)包括将来自输出类的多个训练图像组合成类合成图像的图像合成器(606)。 网格生成器(608)从类合成图像生成表示输出类的网格图案。 特征提取器(610)根据生成的网格图案从多个训练图像中提取特征数据。

    Method and apparatus for controlling classification and classification switching in a vision system
    3.
    发明申请
    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:US20050185846A1

    公开(公告)日:2005-08-25

    申请号:US10785920

    申请日:2004-02-24

    IPC分类号: G06K9/00 G06K9/72 G06K9/46

    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。

    Method and apparatus for classifying image data using classifier grid models
    4.
    发明申请
    Method and apparatus for classifying image data using classifier grid models 审中-公开
    使用分类器网格模型对图像数据进行分类的方法和装置

    公开(公告)号:US20050175243A1

    公开(公告)日:2005-08-11

    申请号:US10772664

    申请日:2004-02-05

    IPC分类号: G06K9/00 G06K9/62 G06K9/68

    CPC分类号: G06K9/6292 G06K9/00362

    摘要: A system (600) for classifying an input image into one of a plurality of output classes includes a plurality of pattern recognition classifiers (620, 622, 624). Each pattern recognition classifier is operative to process feature data associated with the input image to determine an associated output class of the input image. The system further includes a plurality of feature extractors (610, 612, 614). Each feature extractor extracts feature data from the input image for an associated one of the plurality of pattern recognition classifiers according to a classifier grid model representing the associated classifier.

    摘要翻译: 用于将输入图像分类为多个输出类别中的一个的系统(600)包括多个模式识别分类器(620,622,624)。 每个模式识别分类器用于处理与输入图像相关联的特征数据,以确定输入图像的相关联的输出类别。 该系统还包括多个特征提取器(610,612,614)。 每个特征提取器根据表示相关分类器的分类器网格模型,从多个模式识别分类器中相关联的一个模型识别分类器的输入图像中提取特征数据。

    Method and apparatus for arbitrating outputs from multiple pattern recognition classifiers
    5.
    发明申请
    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:US20050185845A1

    公开(公告)日:2005-08-25

    申请号:US10785278

    申请日:2004-02-24

    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 tracking head candidate locations in an actuatable occupant restraining system
    6.
    发明申请
    Method and apparatus for tracking head candidate locations in an actuatable occupant restraining system 审中-公开
    用于跟踪可起动乘员约束系统中的头候选位置的方法和装置

    公开(公告)号:US20050196015A1

    公开(公告)日:2005-09-08

    申请号:US10791258

    申请日:2004-03-02

    IPC分类号: G06K9/00 G06K9/46 G06K9/66

    CPC分类号: G06K9/00234

    摘要: An apparatus (100) for tracking at least one head candidate comprises an image analyzer (104) for analyzing an image signal to identify at least one of a possible plurality of new head candidates within an area of interest. The image analyzer (104) provides data regarding the identified head candidates. A tracking system (108) stores location information for at least one tracked head candidate. A candidate matcher (106) predicts the current position of a given tracked head candidate and selects a subset of the at least one of a plurality of new head candidates according to their distance from the predicted position. The similarity of each member of the selected subset to the tracked candidate is evaluated to determine if a member of the selected subset represents a current position of the tracked candidate.

    摘要翻译: 用于跟踪至少一个头候选的装置(100)包括图像分析器(104),用于分析图像信号以识别感兴趣区域内的可能的多个新的头候选者中的至少一个。 图像分析器(104)提供关于所识别的头候选的数据。 跟踪系统(108)存储至少一个被跟踪头部候选的位置信息。 候选匹配器(106)预测给定的跟踪头候选者的当前位置,并且根据与预测位置的距离来选择多个新头候选中的至少一个的子集。 评估所选择的子集的每个成员与跟踪的候选者的相似度,以确定所选择的子集的成员是否表示所追踪候选的当前位置。

    Method and apparatus for locating an object of interest within an image
    7.
    发明申请
    Method and apparatus for locating an object of interest within an image 失效
    用于在图像内定位感兴趣对象的方法和装置

    公开(公告)号:US20060155442A1

    公开(公告)日:2006-07-13

    申请号:US11035146

    申请日:2005-01-13

    申请人: Yun Luo Jon Wallace

    发明人: Yun Luo Jon Wallace

    IPC分类号: B60R21/32

    摘要: Systems and methods are provided for identifying a position of a head of a vehicle occupant from a plurality of images of a vehicle interior. Image data is translated from the plurality of images to produce a virtual side view image of the vehicle interior. A largest grouping of pixels in the side view image having values within a desired range is identified. The grouping includes a plurality of pixel columns. A contour comprising uppermost pixels of each pixel column is produced and peaks are located within the contour. The contour peaks are analyzed according to a heuristic voting algorithm to identify a peak location associated with the head of the vehicle occupant.

    摘要翻译: 提供了用于从车辆内部的多个图像中识别车辆乘员的头部的位置的系统和方法。 从多个图像翻译图像数据,以产生车辆内部的虚拟侧视图。 识别具有期望范围内的值的侧视图中最大的像素分组。 分组包括多个像素列。 产生包括每个像素列的最上面的像素的轮廓,并且峰位于轮廓内。 根据启发式投票算法分析轮廓峰值,以识别与车辆乘客头部相关联的峰值位置。

    Method and apparatus for locating an object of interest within an image
    8.
    发明申请
    Method and apparatus for locating an object of interest within an image 失效
    用于在图像内定位感兴趣对象的方法和装置

    公开(公告)号:US20080004776A1

    公开(公告)日:2008-01-03

    申请号:US11899257

    申请日:2007-09-04

    申请人: Yun Luo Jon Wallace

    发明人: Yun Luo Jon Wallace

    IPC分类号: B60R21/00 G06K9/46

    摘要: Systems and methods are provided for identifying a position of a head of a vehicle occupant from a plurality of images of a vehicle interior. Image data is translated from the plurality of images to produce a virtual side view image of the vehicle interior. A largest grouping of pixels in the side view image having values within a desired range is identified. The grouping includes a plurality of pixel columns. A contour comprising uppermost pixels of each pixel column is produced and peaks are located within the contour. The contour peaks are analyzed according to a heuristic voting algorithm to identify a peak location associated with the head of the vehicle occupant.

    摘要翻译: 提供了用于从车辆内部的多个图像中识别车辆乘员的头部的位置的系统和方法。 从多个图像翻译图像数据,以产生车辆内部的虚拟侧视图。 识别具有期望范围内的值的侧视图中最大的像素分组。 分组包括多个像素列。 产生包括每个像素列的最上面的像素的轮廓,并且峰位于轮廓内。 根据启发式投票算法分析轮廓峰值,以识别与车辆乘员头部相关联的峰值位置。

    Method and apparatus for producing classifier training images
    9.
    发明申请
    Method and apparatus for producing classifier training images 失效
    生产分类器训练图像的方法和装置

    公开(公告)号:US20050196035A1

    公开(公告)日:2005-09-08

    申请号:US10792445

    申请日:2004-03-03

    申请人: Yun Luo Jon Wallace

    发明人: Yun Luo Jon Wallace

    IPC分类号: G06K9/00 G06K9/62

    摘要: A system (400) for generating training images for a pattern recognition classifier (54) from three-dimensional image data representing an output class comprises a model constructor (404) that constructs an image model in a standard coordinate domain from the three-dimensional image data. A model transformer (406) manipulates the image model in the standard coordinate domain to produce at least one manipulated image model. An image restorer (408) maps the at least one manipulated image model from the standard coordinate domain to a coordinate domain associated with an image source utilized during the run-time operation of the pattern recognition classifier.

    摘要翻译: 用于从表示输出类的三维图像数据生成用于模式识别分类器(54)的训练图像的系统(400)包括:模型构造器(404),其从三维图像构建标准坐标域中的图像模型 数据。 模型变换器(406)操纵标准坐标域中的图像模型以产生至少一个操纵图像模型。 图像恢复器(408)将至少一个被操纵的图像模型从标准坐标域映射到与在图案识别分类器的运行时操作期间使用的图像源相关联的坐标域。

    Method and apparatus for enhancing the dynamic range of stereo vision system
    10.
    发明申请
    Method and apparatus for enhancing the dynamic range of stereo vision system 失效
    提高立体视觉系统动态范围的方法和装置

    公开(公告)号:US20060140510A1

    公开(公告)日:2006-06-29

    申请号:US11022723

    申请日:2004-12-27

    申请人: Jon Wallace Yun Luo

    发明人: Jon Wallace Yun Luo

    IPC分类号: G06K9/36 G06K9/32

    摘要: Systems and methods are provided for producing a stereo disparity map representing an imaged subject. A plurality of sensors (102 and 104) are operative to produce a plurality of images. Each image has an associated exposure according to an exposure level of an associated sensor. A system control (106) determines exposure levels for the plurality of sensors according to an exposure selection algorithm. A disparity processing component (112) is operative to generate a stereo disparity map from a plurality of images. An image merger (110) is operative to merge a plurality of images to produce a composite image having an increased dynamic range.

    摘要翻译: 提供了用于产生代表成像对象的立体视差图的系统和方法。 多个传感器(102和104)可操作以产生多个图像。 每个图像根据相关传感器的曝光水平具有相关联的曝光。 系统控制(106)根据曝光选择算法确定多个传感器的曝光水平。 视差处理部件(112)用于从多个图像生成立体视差图。 图像合并(110)用于合并多个图像以产生具有增加的动态范围的合成图像。