OBJECT DETECTION METHOD AND SYSTEM
    1.
    发明申请
    OBJECT DETECTION METHOD AND SYSTEM 有权
    对象检测方法与系统

    公开(公告)号:US20110116682A1

    公开(公告)日:2011-05-19

    申请号:US12700706

    申请日:2010-02-04

    Abstract: An object detection method and an object detection system, suitable for detecting moving object information of a video stream having a plurality of images, are provided. The method performs a moving object foreground detection on each of the images, so as to obtain a first foreground detection image comprising a plurality of moving objects. The method also performs a texture object foreground detection on each of the images, so as to obtain a second foreground detection image comprising a plurality of texture objects. The moving objects in the first foreground detection image and the texture objects in the second foreground detection image are selected and filtered, and then the remaining moving objects or texture objects after the filtering are output as real moving object information.

    Abstract translation: 提供了一种适用于检测具有多个图像的视频流的移动物体信息的物体检测方法和物体检测系统。 该方法对每个图像执行移动物体前景检测,以便获得包括多个移动物体的第一前景检测图像。 该方法还对每个图像执行纹理对象前景检测,以便获得包括多个纹理对象的第二前景检测图像。 选择并过滤第一前景检测图像中的移动对象和第二前景检测图像中的纹理对象,然后将滤波后的剩余移动对象或纹理对象作为实际移动对象信息输出。

    MULTI-STATE TARGET TRACKING MEHTOD AND SYSTEM
    2.
    发明申请
    MULTI-STATE TARGET TRACKING MEHTOD AND SYSTEM 审中-公开
    多状态目标跟踪和系统

    公开(公告)号:US20110115920A1

    公开(公告)日:2011-05-19

    申请号:US12703207

    申请日:2010-02-10

    Abstract: A multi-state target tracking method and a multi-state target tracking system are provided. The method detects a crowd density of a plurality of images in a video stream and compares the detected crowd density with a threshold when receiving the video stream, so as to determine a tracking mode used for detecting the targets in the images. When the detected crowd density is less than the threshold, a background model is used to track the targets in the images. When the detected crowd density is greater than or equal to the threshold, a none-background model is used to track the targets in the images.

    Abstract translation: 提供了多状态目标跟踪方法和多状态目标跟踪系统。 该方法检测视频流中的多个图像的人群密度,并且当接收到视频流时将检测到的人群密度与阈值进行比较,以便确定用于检测图像中的目标的跟踪模式。 当检测到的人群密度小于阈值时,使用背景模型来跟踪图像中的目标。 当检测到的人群密度大于或等于阈值时,无背景模型用于跟踪图像中的目标。

    Ultraviolet Lamp
    5.
    发明申请
    Ultraviolet Lamp 失效
    紫外灯

    公开(公告)号:US20070069654A1

    公开(公告)日:2007-03-29

    申请号:US11535952

    申请日:2006-09-27

    CPC classification number: H01J61/0672 A61L2/10 H01J61/35

    Abstract: The present invention relates to an ultraviolet lamp comprising a glass shell and an electrode fixed on one or more ends of the lamp, where each electrode is a coiled wire with a hollow conical shape. The hollowed conical structure of the electrode reduces the thermal capacity of the electrode as compared with other types of electrodes of the same mass, makes the lamp start quicker, and decreases the emission loss of the electrode when the glow discharge is transformed to an arc discharge. The lamp of the present invention has a wide electrode surface area, such that the loads on each point of the emissive surface are equally distributed, thus decreasing the electron scattering and dispersion, and allowing the lamp to resist the impact from positive ions. Due to the shape and structure of the electrode, the lamp of the present invention has increased efficiency and emitting ability, and allows for a longer lasting lamp.

    Abstract translation: 本发明涉及一种紫外灯,其包括玻璃壳和固定在灯的一个或多个端部上的电极,其中每个电极是具有中空圆锥形状的线圈。 电极的中空圆锥形结构与其他类型的相同质量的电极相比,降低了电极的热容量,使得灯起动更快,并且当辉光放电转变为电弧放电时,电极的发射损耗降低 。 本发明的灯具有宽的电极表面积,使得发射表面的每个点上的负载均匀分布,从而减少电子散射和分散,并允许灯抵抗来自正离子的冲击。 由于电极的形状和结构,本发明的灯具具有提高的效率和发射能力,并允许更持久的灯。

    Ultraviolet lamp
    6.
    发明授权
    Ultraviolet lamp 失效
    紫外线灯

    公开(公告)号:US07635951B2

    公开(公告)日:2009-12-22

    申请号:US11535952

    申请日:2006-09-27

    CPC classification number: H01J61/0672 A61L2/10 H01J61/35

    Abstract: The present invention relates to an ultraviolet lamp comprising a glass shell and an electrode fixed on one or more ends of the lamp, where each electrode is a coiled wire with a hollow conical shape. The hollowed conical structure of the electrode reduces the thermal capacity of the electrode as compared with other types of electrodes of the same mass, makes the lamp start quicker, and decreases the emission loss of the electrode when the glow discharge is transformed to an arc discharge. The lamp of the present invention has a wide electrode surface area, such that the loads on each point of the emissive surface are equally distributed, thus decreasing the electron scattering and dispersion, and allowing the lamp to resist the impact from positive ions. Due to the shape and structure of the electrode, the lamp of the present invention has increased efficiency and emitting ability, and allows for a longer lasting lamp.

    Abstract translation: 本发明涉及一种紫外灯,其包括玻璃壳和固定在灯的一个或多个端部上的电极,其中每个电极是具有中空圆锥形状的线圈。 电极的中空圆锥形结构与其他类型的相同质量的电极相比,降低了电极的热容量,使得灯起动更快,并且当辉光放电转变为电弧放电时,电极的发射损耗降低 。 本发明的灯具有宽的电极表面积,使得发射表面的每个点上的负载均匀分布,从而减少电子散射和分散,并允许灯抵抗来自正离子的冲击。 由于电极的形状和结构,本发明的灯具具有提高的效率和发射能力,并允许更持久的灯。

    Moving object detection detection within a video stream using object texture
    9.
    发明授权
    Moving object detection detection within a video stream using object texture 有权
    使用对象纹理在视频流内移动物体检测检测

    公开(公告)号:US08559670B2

    公开(公告)日:2013-10-15

    申请号:US12700706

    申请日:2010-02-04

    Abstract: An object detection method and an object detection system, suitable for detecting moving object information of a video stream having a plurality of images, are provided. The method performs a moving object foreground detection on each of the images, so as to obtain a first foreground detection image comprising a plurality of moving objects. The method also performs a texture object foreground detection on each of the images, so as to obtain a second foreground detection image comprising a plurality of texture objects. The moving objects in the first foreground detection image and the texture objects in the second foreground detection image are selected and filtered, and then the remaining moving objects or texture objects after the filtering are output as real moving object information.

    Abstract translation: 提供了一种适用于检测具有多个图像的视频流的移动物体信息的物体检测方法和物体检测系统。 该方法对每个图像执行移动物体前景检测,以便获得包括多个移动物体的第一前景检测图像。 该方法还对每个图像执行纹理对象前景检测,以便获得包括多个纹理对象的第二前景检测图像。 选择并过滤第一前景检测图像中的移动对象和第二前景检测图像中的纹理对象,然后将滤波后的剩余移动对象或纹理对象作为实际移动对象信息输出。

Patent Agency Ranking