Non-contact apparatus and method for measuring surface profile
    2.
    发明授权
    Non-contact apparatus and method for measuring surface profile 有权
    用于测量表面轮廓的非接触式装置和方法

    公开(公告)号:US07382471B2

    公开(公告)日:2008-06-03

    申请号:US11313671

    申请日:2005-12-22

    IPC分类号: G01B11/24

    摘要: Embodiments of the invention provide a non-contact method for measuring the surface profile of an object that can include generating a point-type optical signal and projecting it on a rotatable precision optical grating, generating a rotating pattern of light and dark lines onto the object, recording a series of images of the rotating pattern moving across the object with an image receiving device and calculating the surface profile of the object. Other embodiments can include a method to calibrate the system and a non-contact apparatus that generally includes a point-type light source, a rotatably mounted optical grating being configured to project a moving grating image on the object, a processor in communication with the image capturing device and configured to receive image input from the image capturing device and generate a surface profile representation of the object therefrom.

    摘要翻译: 本发明的实施例提供了一种用于测量物体的表面轮廓的非接触方法,其可以包括产生点型光信号并将其投射在可旋转的精密光栅上,在对象上产生光线和暗线的旋转图案 记录利用图像接收装置在物体上移动的旋转图案的一系列图像,并计算物体的表面轮廓。 其他实施例可以包括校准系统的方法和通常包括点式光源的非接触式设备,可旋转地安装的光栅被配置为将物体上的移动光栅图像投影到与图像通信的处理器 捕获装置,并且被配置为从所述图像捕获装置接收图像输入并从其生成所述对象的表面轮廓表示。

    Model-based incident detection system with motion classification
    3.
    发明授权
    Model-based incident detection system with motion classification 有权
    基于模型的事件检测系统,具有运动分类

    公开(公告)号:US06985172B1

    公开(公告)日:2006-01-10

    申请号:US10056665

    申请日:2002-01-25

    IPC分类号: H04N7/18 H04N5/225

    摘要: Surveillance apparatus and methods effective for detecting incidents are based upon improved image processing techniques applied to infrared and visible light spectrum images in a time sequence. A reference image is generated by removing motion objects from an image of a region of interest. The reference image is compared to an image to be analyzed to detect motion. Detected motion is analyzed and classified as motion objects. The motion objects are then compared to a motion model, which classifies the objects as being anticipated or unanticipated.

    摘要翻译: 用于检测事件的监视装置和方法基于在时间序列中应用于红外和可见光谱图像的改进的图像处理技术。 通过从感兴趣区域的图像中移除运动对象来生成参考图像。 将参考图像与要分析的图像进行比较以检测运动。 检测到的运动被分析和分类为运动对象。 然后将运动对象与运动模型进行比较,运动模型将对象分类为预期的或意料之外的。