中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.017 seconds)

    Object detection based on a feature map of a convolutional neural network
    2.
    发明授权
    Object detection based on a feature map of a convolutional neural network 有权

    公开(公告)号：US11551027B2

    公开(公告)日：2023-01-10

    申请号：US16641609

    申请日：2018-06-21

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

    Inventor： Jingjing Fu ,  Yao Zhai ,  Yan Lu

    IPC: G06K9/62

    Abstract: Implementations of the subject matter described herein relate to object detection based on deep neural network. With a given input image, it is desired to determine a class and a boundary of one or more objects within the input image. Specifically, a plurality of channel groups is generated from a feature map of an image, the image including at least a region corresponding to a first grid. A target feature map is extracted from at least one of the plurality of channel groups associated with a cell of the first grid. Information related to an object within the region is determined based on the target feature map. The information related to the object may be a class and/or a boundary of the object.

    DEPTH DATA PROCESSING AND COMPRESSION
    4.
    发明申请
    DEPTH DATA PROCESSING AND COMPRESSION 有权
    深度数据处理和压缩

    公开(公告)号：US20170064305A1

    公开(公告)日：2017-03-02

    申请号：US15347098

    申请日：2016-11-09

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Jingjing Fu ,  Yan Lu ,  Shipeng Li

    IPC: H04N19/136 ,  G06T7/40 ,  H04N19/426 ,  G06T7/00

    CPC classification number: H04N19/136 ,  G06T5/005 ,  G06T7/13 ,  G06T7/40 ,  G06T7/50 ,  G06T7/70 ,  G06T2207/10028 ,  G06T2207/20192 ,  H04N13/128 ,  H04N13/271 ,  H04N19/426

    Abstract: Techniques for setting depth values for invalid measurement regions of depth images are described herein. A computing device may set the depth values based on evaluations of depth values of neighboring pixels and of corresponding pixels from time-adjacent depth images. Alternately or additionally, the computing device may utilize a texture image corresponding to the depth image to identify objects and may set depth values for pixels based on depth values of other pixels belonging to the same object. After setting the depth values, the computing device may normalize the depth values of the pixels. Further, the computing device may generate reduced representations of the depth images based on a depth reference model or a depth error model and may provide the reduced representations to an encoder.

    Abstract translation: 本文描述了用于设置深度图像的无效测量区域的深度值的技术。 计算设备可以基于来自相邻深度图像的相邻像素和对应像素的深度值的评估来设置深度值。 或者或另外，计算设备可以利用与深度图像相对应的纹理图像来识别对象，并且可以基于属于同一对象的其他像素的深度值来设置像素的深度值。 在设置深度值之后，计算设备可以对像素的深度值进行归一化。 此外，计算设备可以基于深度参考模型或深度误差模型生成深度图像的缩小表示，并且可以将缩小的表示提供给编码器。

    Representation and compression of depth data
    5.
    发明授权
    Representation and compression of depth data 有权
    深度数据的表示和压缩

    公开(公告)号：US09467681B2

    公开(公告)日：2016-10-11

    申请号：US13850173

    申请日：2013-03-25

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Jingjing Fu ,  Dan Miao ,  Yan Lu ,  Shipeng Li

    IPC: H04N13/02 ,  H04N13/00 ,  H04N19/597 ,  H04N19/85 ,  H04N19/36

    CPC classification number: H04N13/271 ,  H04N13/128 ,  H04N13/161 ,  H04N19/36 ,  H04N19/597 ,  H04N19/85

    Abstract: The techniques and arrangements described herein provide for layered compression of depth image data. In some examples, an encoder may partition depth image data into a most significant bit (MSB) layer and a least significant bit (LSB) layer. The encoder may quantize the MSB layer and generate quantization difference data based at least in part on the quantization of the MSB layer. The encoder may apply the quantization difference data to the LSB layer to generate an adjusted LSB layer.

    Abstract translation: 本文描述的技术和布置提供了深度图像数据的分层压缩。 在一些示例中，编码器可以将深度图像数据分割成最高有效位（MSB）层和最低有效位（LSB）层。 编码器可以至少部分地基于MSB层的量化来量化MSB层并生成量化差异数据。 编码器可以将量化差值数据应用于LSB层以产生经调整的LSB层。

Patent Agency Ranking