Systems and methods for image processing in a deep convolution network
    1.
    发明授权
    Systems and methods for image processing in a deep convolution network 有权
    深卷积网络中图像处理的系统和方法

    公开(公告)号:US09582726B2

    公开(公告)日:2017-02-28

    申请号:US14749387

    申请日:2015-06-24

    Abstract: A method performed by an electronic device is described. The method includes interleaving multiple input image channels to produce an interleaved multi-channel input. The method also includes loading the interleaved multi-channel input to a single-instruction multiple data (SIMD) processor. The method further includes convolving the interleaved multi-channel input with a multi-channel filter.

    Abstract translation: 描述由电子设备执行的方法。 该方法包括交织多个输入图像通道以产生交织的多通道输入。 该方法还包括将交织的多通道输入加载到单指令多数据(SIMD)处理器。 该方法还包括用交错多通道输入与多通道滤波器进行卷积。

    Methods and apparatus for video background subtraction

    公开(公告)号:US10269123B2

    公开(公告)日:2019-04-23

    申请号:US15402103

    申请日:2017-01-09

    Abstract: Methods and an apparatus for background subtraction are described. According to some implementations, the temporal history of a pixel location can be used to classify whether a current input pixel of a current input video frame is a background pixel or a foreground pixel. The classification can be made based on the number of matching pixels in corresponding pixel locations in background history planes. One of the background history planes can be updated according to the classified background pixels and persistent classified foreground pixels.

    Methods and apparatus for codeword boundary detection for generating depth maps

    公开(公告)号:US10192311B2

    公开(公告)日:2019-01-29

    申请号:US15230211

    申请日:2016-08-05

    Abstract: A structured light active sensing systems may be configured to transmit and received codewords to generate a depth map by analyzing disparities between the locations of the transmitted and received codewords. To determine the locations of received codewords, an image of the projected codewords is identified, from which one or more codeword boundaries are detected. The codeword boundaries may be detected based upon a particular codeword bit of each codeword. Each detected codeword boundary may be constrained from overlapping with other detected codeword boundaries, such that no pixel of the received image is associated with more than one codeword boundary.

    SYSTEMS AND METHODS FOR IMAGE PROCESSING IN A DEEP CONVOLUTION NETWORK
    6.
    发明申请
    SYSTEMS AND METHODS FOR IMAGE PROCESSING IN A DEEP CONVOLUTION NETWORK 有权
    深层调解网络中图像处理的系统和方法

    公开(公告)号:US20160379073A1

    公开(公告)日:2016-12-29

    申请号:US14749387

    申请日:2015-06-24

    Abstract: A method performed by an electronic device is described. The method includes interleaving multiple input image channels to produce an interleaved multi-channel input. The method also includes loading the interleaved multi-channel input to a single-instruction multiple data (SIMD) processor. The method further includes convolving the interleaved multi-channel input with a multi-channel filter.

    Abstract translation: 描述由电子设备执行的方法。 该方法包括交织多个输入图像通道以产生交织的多通道输入。 该方法还包括将交织的多通道输入加载到单指令多数据(SIMD)处理器。 该方法还包括用交错多通道输入与多通道滤波器进行卷积。

    METHODS AND APPARATUS FOR CODEWORD BOUNDARY DETECTION FOR GENERATING DEPTH MAPS

    公开(公告)号:US20180040130A1

    公开(公告)日:2018-02-08

    申请号:US15230211

    申请日:2016-08-05

    CPC classification number: G06T7/0057 G06T7/11 G06T7/13 G06T7/521

    Abstract: A structured light active sensing systems may be configured to transmit and received codewords to generate a depth map by analyzing disparities between the locations of the transmitted and received codewords. To determine the locations of received codewords, an image of the projected codewords is identified, from which one or more codeword boundaries are detected. The codeword boundaries may be detected based upon a particular codeword bit of each codeword. Each detected codeword boundary may be constrained from overlapping with other detected codeword boundaries, such that no pixel of the received image is associated with more than one codeword boundary.

Patent Agency Ranking