利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

38 条记录 (耗时 0.027 秒)

    CONTENT AWARE FORENSIC DETECTION OF IMAGE MANIPULATIONS
    1.
    发明申请
    CONTENT AWARE FORENSIC DETECTION OF IMAGE MANIPULATIONS 审中-公开

    公开(公告)号：US20200005078A1

    公开(公告)日：2020-01-02

    申请号：US16400542

    申请日：2019-05-01

    申请人： Honeywell International Inc.

    发明人： Asongu Tambo ,  Michael Albright ,  Scott McCloskey

    IPC分类号： G06K9/62 ,  G06K9/46

    摘要： A process identifies features in a probe image and a donor image. A similarity measure matches the features in the probe image with features in the donor image, and forms pairs of matched features. The process then forms clusters of the pairs based on the pairs occupying a similar location in the probe image, and verifies that the clusters in the probe image are good fits for corresponding features in the donor image. Locations of the clusters and locations of the corresponding features are marked, and the extent to which the clusters and the corresponding features represent the same semantic class. The process calculates a score based on clusters having the good fit and the clusters in the first digital image having a similar semantic interpretation as the corresponding cluster in the second digital image.

    Athentication of device users by gaze
    3.
    发明授权
    Athentication of device users by gaze 有权
    通过注视认证设备用户

    公开(公告)号：US09424411B2

    公开(公告)日：2016-08-23

    申请号：US14247922

    申请日：2014-04-08

    申请人： Honeywell International Inc.

    发明人： Scott McCloskey

    IPC分类号： G06F21/32 ,  G06F21/31

    CPC分类号： G06F21/316 ,  G06F3/013 ,  G06F21/32 ,  G06F2221/2105 ,  G06F2221/2141 ,  G06F2221/2147

    摘要： A method includes obtaining a gaze feature of a user of a device, wherein the device has already been unlocked using a second feature, the gaze feature being based on images of a pupil relative to a display screen of the device, comparing the obtained gaze feature to known gaze features of an authorized user of the device, and determining whether or not the user is authorized to use the device based on the comparison.

    摘要翻译： 一种方法包括获得设备的用户的凝视特征，其中所述设备已经使用第二特征被解锁，所述注视特征基于相对于所述设备的显示屏幕的瞳孔的图像，将获得的凝视特征 到设备的授权用户的已知凝视特征，以及基于该比较来确定用户是否被授权使用该设备。

    POINT SPREAD FUNCTION ESTIMATION FOR MOTION INVARIANT IMAGES
    4.
    发明申请
    POINT SPREAD FUNCTION ESTIMATION FOR MOTION INVARIANT IMAGES 有权
    用于运动不变图像的点扩展函数估计

    公开(公告)号：US20160171666A1

    公开(公告)日：2016-06-16

    申请号：US14218595

    申请日：2014-03-18

    申请人： Honeywell International Inc.

    发明人： Scott McCloskey

    IPC分类号： G06T5/00 ,  G06T7/20 ,  G06T5/50 ,  G06T7/00

    CPC分类号： G06T5/003 ,  G06T5/50 ,  G06T7/13 ,  G06T7/20 ,  G06T2207/20201

    摘要： A method that includes using a point spread function to de-blur an original motion invariant image to create a modified motion invariant image; using an edge detector to find edges in the modified motion invariant image; determining the distances between the edges and corresponding artifacts in the modified motion invariant image; using the distances between the edges and the corresponding artifacts to estimate a velocity of an object in the modified motion invariant image; generating a corrected point spread function corresponding to the estimated velocity of the object; and using the corrected point spread function to de-blur the original motion invariant image and create a resulting image.

    摘要翻译： 一种方法，包括使用点扩散函数去模糊原始运动不变图像以创建经修改的运动不变图像; 使用边缘检测器在修改的运动不变图像中找到边缘; 确定修改的运动不变图像中边缘之间的距离和对应的伪像; 使用边缘和对应的伪影之间的距离来估计修改的运动不变图像中的对象的速度; 产生对应于物体的估计速度的校正点扩散函数; 并且使用校正的点扩散函数来去模糊原始运动不变图像并创建所得到的图像。

    Score fusion and training data recycling for video classification
    5.
    发明授权
    Score fusion and training data recycling for video classification 有权
    分数融合和训练数据回收用于视频分类

    公开(公告)号：US09147129B2

    公开(公告)日：2015-09-29

    申请号：US13622328

    申请日：2012-09-18

    申请人： Honeywell International Inc.

    发明人： Jingchen Liu ,  Scott McCloskey

    IPC分类号： G06F15/18 ,  G06K9/62 ,  G06N99/00 ,  G06K9/00

    CPC分类号： G06K9/6256 ,  G06K9/00718 ,  G06K9/6264 ,  G06K9/6292 ,  G06N99/005

    摘要： Multiple classifiers can be applied independently to evaluate images or video. Where there are heavily imbalanced class distributions, a local expert forest model for meta-level score fusion for event detection can be used. Performance variations of classifiers in different regions of a score space can be adapted. Multiple pairs of experts based on different partitions, or “trees,” can form a “forest,” balancing local adaptivity and over-fitting. Among ensemble learning methods, stacking with a meta-level classifier can be used to fuse an output of multiple base-level classifiers to generate a final score. A knowledge-transfer framework can reutilize the base-training data for learning the meta-level classifier. By recycling the knowledge obtained during a base-classifier-training stage, efficient use can be made of all available information, such as can be used to achieve better fusion and better overall performance.

    摘要翻译： 可以独立应用多个分类器来评估图像或视频。 如果类别分布严重不平衡，可以使用用于事件检测的元级分数融合的本地专家森林模型。 可以调整分数空间不同区域的分类器的性能变化。 基于不同分区或“树”的多对专家可以形成“森林”，平衡局部适应性和过度配合。 在综合学习方法中，使用元级分类器的堆叠可以用于融合多个基本级分类器的输出以产生最终分数。 知识转移框架可以重新利用基础训练数据来学习元级分类器。 通过回收在基础分类器训练阶段获得的知识，可以有效利用所有可用的信息，例如可用于实现更好的融合和更好的整体性能。

    MOTION DEBLURRING
    6.
    发明申请
    MOTION DEBLURRING 有权
    动作消失

    公开(公告)号：US20150042829A1

    公开(公告)日：2015-02-12

    申请号：US14176984

    申请日：2014-02-10

    申请人： Honeywell International Inc.

    发明人： Scott McCloskey ,  Kelly Muldoon ,  Sharath Venkatesha

    IPC分类号： H04N5/232 ,  G06T5/00

    CPC分类号： G06T5/003 ,  G06T2200/21 ,  H04N5/23258 ,  H04N5/23267

    摘要： Motion de-blurring systems and methods are described herein. One motion de-blurring system includes an image sensing element, one or more motion sensors in an imaging device, a lens element that undergoes motion during a capture of an image by the sensing element, and a de-blurring element to de-blur the image captured by the sensing element via de-convolving a Point Spread Function (PSF).

    摘要翻译： 本文描述了运动去模糊系统和方法。 一种运动去模糊系统包括图像感测元件，成像装置中的一个或多个运动传感器，在感测元件捕获图像期间经历运动的透镜元件，以及去模糊元件 由传感元件通过去卷积点扩展函数（PSF）捕获的图像。

    CARGO SENSING
    7.
    发明申请
    CARGO SENSING 审中-公开
    货物感觉

    公开(公告)号：US20140036072A1

    公开(公告)日：2014-02-06

    申请号：US13923259

    申请日：2013-06-20

    申请人： Honeywell International Inc.

    发明人： Ronald Lyall ,  Pedro Davalos ,  Sharath Venkatesha ,  Donald Anderson ,  Ynjiun P. Wang ,  Scott McCloskey ,  John Hatherall ,  Steve Howe

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00771 ,  H04N7/18

    摘要： Cargo presence detection devices, systems, and methods are described herein. One cargo presence detection system includes one or more sensors positioned in an interior space of a container, and arranged to collect background image data about at least a portion of the interior space of the container and updated image data about the portion of the interior space of the container and a detection component that receives the image data from the one or more sensors and identifies if one or more cargo items are present in the interior space of the container based on analysis of the background and updated image data.

    摘要翻译： 本文描述了货物存在检测装置，系统和方法。 一个货物存在检测系统包括位于容器的内部空间中的一个或多个传感器，并被布置成收集关于容器的内部空间的至少一部分的背景图像数据，以及关于内部空间的部分的更新的图像数据 所述容器和检测部件，其接收来自所述一个或多个传感器的图像数据，并且基于对所述背景和更新的图像数据的分析来识别所述容器的内部空间中是否存在一个或多个货物物品。