SYSTEMS AND METHODS FOR MULTI-DIMENSIONAL OBJECT DETECTION
    1.
    发明申请
    SYSTEMS AND METHODS FOR MULTI-DIMENSIONAL OBJECT DETECTION 有权
    用于多维对象检测的系统和方法

    公开(公告)号:US20140029852A1

    公开(公告)日:2014-01-30

    申请号:US13945830

    申请日:2013-07-18

    CPC classification number: G06T7/13 G06K9/00798 G06K9/00805 G06K9/18

    Abstract: Systems and methods for multi-dimensional object detection are described. Embodiments disclose receiving image frames, extracting image components in the image frame, identifying line segments in the extracted components, grouping the line segments into groups, based at least in part on one or more similarities between the slope associated with a line segment and the spatial proximity between the line segments, and merging each of the one or more identified line segments in a selected group into a single line segment. Embodiments additionally disclose detecting the position of one or more objects in the image frame by identifying objects in the image frame, producing a second version of the image frame, applying at least one image classifier to the image frame and the second version of the image frame, and identifying coordinates associated with at least one target object. Some embodiments additionally couple lane and object detection with alert generation.

    Abstract translation: 描述了用于多维对象检测的系统和方法。 实施例公开了接收图像帧,提取图像帧中的图像分量,识别所提取的分量中的线段,至少部分地基于与线段相关联的斜率与空间中的一个或多个相似度,将线段分组成组 线段之间的接近度,并将所选组中的一个或多个识别的线段中的每一个合并成单个线段。 实施例另外公开了通过识别图像帧中的对象来检测图像帧中的一个或多个对象的位置,产生图像帧的第二版本,将至少一个图像分类器应用于图像帧和图像帧的第二版本 以及识别与至少一个目标对象相关联的坐标。 一些实施例另外将通道和物体检测与报警生成相结合。

    METHODS FOR ASSESSING TRANSITION VALUE AND DEVICES THEREOF
    2.
    发明申请
    METHODS FOR ASSESSING TRANSITION VALUE AND DEVICES THEREOF 审中-公开
    评估过渡值的方法及其装置

    公开(公告)号:US20130317889A1

    公开(公告)日:2013-11-28

    申请号:US13891884

    申请日:2013-05-10

    CPC classification number: G06Q10/06375

    Abstract: A method, non-transitory computer readable medium, and apparatus that generates a transition enabler overall score for each of a plurality of transition enablers based on at least one weight values and at least one score associated with each transition enabler. A hierarchical statistical model is generated based at least on the transition enabler overall scores and at least one of transition metric values, transition impact values, a transition context index value, or domain expert information. At least one transition impact value is determined for one or more transition impacts based on the hierarchical statistical model. The at least one transition impact value is output.

    Abstract translation: 一种方法,非暂时性计算机可读介质和装置,其基于至少一个权重值和与每个转换使能器相关联的至少一个得分来生成多个转换使能器中的每一者的转换使能整体得分。 至少基于转换启动器整体得分和转换度量值,转换影响值,转换上下文索引值或域专家信息中的至少一个生成分级统计模型。 基于分层统计模型,确定一个或多个过渡影响的至少一个过渡冲击值。 输出至少一个过渡冲击值。

    Systems and methods for multi-dimensional object detection

    公开(公告)号:US09633436B2

    公开(公告)日:2017-04-25

    申请号:US13945830

    申请日:2013-07-18

    CPC classification number: G06T7/13 G06K9/00798 G06K9/00805 G06K9/18

    Abstract: Systems and methods for multi-dimensional object detection are described. Embodiments disclose receiving image frames, extracting image components in the image frame, identifying line segments in the extracted components, grouping the line segments into groups, based at least in part on one or more similarities between the slope associated with a line segment and the spatial proximity between the line segments, and merging each of the one or more identified line segments in a selected group into a single line segment. Embodiments additionally disclose detecting the position of one or more objects in the image frame by identifying objects in the image frame, producing a second version of the image frame, applying at least one image classifier to the image frame and the second version of the image frame, and identifying coordinates associated with at least one target object. Some embodiments additionally couple lane and object detection with alert generation.

Patent Agency Ranking