SUPER RESOLUTION USING CONVOLUTIONAL NEURAL NETWORK

    公开(公告)号:US20230052483A1

    公开(公告)日:2023-02-16

    申请号:US17793341

    申请日:2020-02-17

    Abstract: An apparatus for super resolution imaging includes a convolutional neural network (104) to receive a low resolution frame (102) and generate a high resolution illuminance component frame. The apparatus also includes a hardware scaler (106) to receive the low resolution frame (102) and generate a second high resolution chrominance component frame. The apparatus further includes a combiner (108) to combine the high resolution illuminance component frame and the high resolution chrominance component frame to generate a high resolution frame (110).

    Trajectory planning for video stabilization

    公开(公告)号:US10158802B2

    公开(公告)日:2018-12-18

    申请号:US15502990

    申请日:2014-09-19

    Abstract: Trajectory planning is described for video stabilization. In one example, a sequence of video frames is received and low-pass filtered. If a subset of the low-pass filtered frames are determined to be zero-motion frames, then a smooth trajectory is estimated for the for the zero-motion frames. Jitter is removed from the zero-motion frames using the smooth trajectory and frame warping is applied to the zero-motion frames with jitter removed.

    Adaptive motion instability detection in video
    9.
    发明授权
    Adaptive motion instability detection in video 有权
    视频中的自适应运动不稳定检测

    公开(公告)号:US09336460B2

    公开(公告)日:2016-05-10

    申请号:US14218457

    申请日:2014-03-18

    CPC classification number: G06K9/6298 H04N5/23267

    Abstract: One or more apparatus and method for adaptively detecting motion instability in video. In embodiments, video stabilization is predicated on adaptive detection of motion instability. Adaptive motion instability detection may entail determining an initial motion instability state associated with a plurality of video frames. Subsequent transitions of the instability state may be detected by comparing a first level of instability associated with a first plurality of the frames to a second level of instability associated with a second plurality of the frames. Image stabilization of received video frames may be toggled first based on the initial instability state, and thereafter based on detected changes in the instability state. Output video frames, which may be stabilized or non-stabilized, may then be stored to a memory. In certain embodiments, video motion instability is scored based on a probability distribution of video frame motion jitter values.

    Abstract translation: 一种或多种用于自适应地检测视频中的运动不稳定性的装置和方法。 在实施例中,视频稳定基于运动不稳定性的自适应检测。 自适应运动不稳定性检测可能需要确定与多个视频帧相关联的初始运动不稳定状态。 可以通过将与第一多个帧相关联的不稳定性的第一级别与与第二多个帧相关联的第二级不稳定性进行比较来检测不稳定状态的后续转换。 首先可以基于初始不稳定状态来切换所接收的视频帧的图像稳定性,然后基于检测到的不稳定状态的变化。 然后可以将稳定或不稳定的输出视频帧存储到存储器中。 在某些实施例中,基于视频帧运动抖动值的概率分布对视频运动不稳定性进行评分。

Patent Agency Ranking