会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明申请
    • IMAGE STABILIZER, SYSTEM HAVING THE SAME AND METHOD OF STABILIZING AN IMAGE
    • 图像稳定器,具有该图像的系统和稳定图像的方法
    • US20070248167A1
    • 2007-10-25
    • US11678929
    • 2007-02-26
    • Jun-Hyun ParkMing Zhao
    • Jun-Hyun ParkMing Zhao
    • H04N7/12
    • H04N19/527H04N5/145H04N5/23248
    • An image stabilizer includes a motion estimation unit, a motion vector selection unit, a motion compensation vector calculation unit and an image compensation unit. A plurality of divided areas of a picture is projected onto a plurality of windows. The motion estimation unit extracts motion vectors from the plurality of windows. The motion vector selection unit selects an optimal motion vector among the plurality of motion vectors. The motion compensation vector calculation unit calculates a motion compensation vector using the optimal motion vector. The image compensation unit compensates an image of the picture using the motion compensation vector. Accordingly a sudden shift effect may be reduced when stabilizing the image.
    • 图像稳定器包括运动估计单元,运动矢量选择单元,运动补偿矢量计算单元和图像补偿单元。 图像的多个分割区域被投影到多个窗口上。 运动估计单元从多个窗口提取运动矢量。 运动矢量选择单元选择多个运动矢量中的最佳运动矢量。 运动补偿矢量计算单元使用最佳运动矢量来计算运动补偿矢量。 图像补偿单元使用运动补偿矢量补偿图像的图像。 因此,当稳定图像时可能会降低突然的移位效果。
    • 8. 发明授权
    • Automatic large scale video object recognition
    • 自动大规模视频对象识别
    • US08792732B1
    • 2014-07-29
    • US13559420
    • 2012-07-26
    • Ming ZhaoJay Yagnik
    • Ming ZhaoJay Yagnik
    • G06K9/46H04N5/14
    • G06K9/6232G06K9/6215
    • An object recognition system performs a number of rounds of dimensionality reduction and consistency learning on visual content items such as videos and still images, resulting in a set of feature vectors that accurately predict the presence of a visual object represented by a given object name within an visual content item. The feature vectors are stored in association with the object name which they represent and with an indication of the number of rounds of dimensionality reduction and consistency learning that produced them. The feature vectors and the indication can be used for various purposes, such as quickly determining a visual content item containing a visual representation of a given object name.
    • 对象识别系统对诸如视频和静止图像的视觉内容项目执行多次维数降低和一致性学习,导致一组特征向量,其精确地预测由一个对象名称表示的视觉对象的存在 视觉内容项目。 特征向量与它们所代表的对象名称相关联地存储,并且显示产生它们的维度降低和一致性学习的轮次数。 特征向量和指示可以用于各种目的,诸如快速确定包含给定对象名称的视觉表示的视觉内容项。