Method for Detecting Foreground
    1.
    发明申请
    Method for Detecting Foreground 有权
    检测前景的方法

    公开(公告)号:US20150294179A1

    公开(公告)日:2015-10-15

    申请号:US14248364

    申请日:2014-04-09

    申请人: MEDIATEK INC.

    IPC分类号: G06K9/46 G06K9/62 G06K9/00

    摘要: A method and apparatus for foreground detection by designating one of two non-occlusion areas as the foreground area according to results of position matching using two given motion vectors. The detection is performed by matching the position of the current occlusion area in the current frame with one or more positions of a previous occlusion area in a previous frame. The matching operation is based on motion vectors determined for the neighboring areas adjacent to the current occlusion area. The determination of the motion vectors are based on two neighboring frames temporally located before and after the current frame. If the position of the current occlusion area is matched with the previous occlusion area by using one of the motion vectors, the neighboring area corresponding to the motion vector is designated as a foreground area.

    摘要翻译: 根据使用两个给定运动矢量的位置匹配结果,通过将两个非遮挡区域中的一个指定为前景区域来进行前景检测的方法和装置。 通过将当前帧中的当前遮挡区域的位置与先前帧中的先前遮挡区域的一个或多个位置进行匹配来执行检测。 匹配操作基于为邻近当前遮挡区域的相邻区域确定的运动矢量。 运动矢量的确定基于时间上位于当前帧之前和之后的两个相邻帧。 如果通过使用运动矢量之一将当前遮挡区域的位置与先前的遮挡区域相匹配,则将与运动矢量对应的相邻区域指定为前景区域。

    DATA BUFFERING APPARATUS CAPABLE OF ALTERNATELY TRANSMITTING STORED PARTIAL DATA OF INPUT IMAGES MERGED IN ONE MERGED IMAGE TO IMAGE/VIDEO PROCESSING DEVICE AND RELATED DATA BUFFERING METHOD
    2.
    发明申请
    DATA BUFFERING APPARATUS CAPABLE OF ALTERNATELY TRANSMITTING STORED PARTIAL DATA OF INPUT IMAGES MERGED IN ONE MERGED IMAGE TO IMAGE/VIDEO PROCESSING DEVICE AND RELATED DATA BUFFERING METHOD 审中-公开
    数据缓冲装置,能够将一个合并图像中的输入图像存储在图像/视频处理装置中的存储部分数据和相关数据缓冲方法

    公开(公告)号:US20130222422A1

    公开(公告)日:2013-08-29

    申请号:US13772336

    申请日:2013-02-21

    申请人: MEDIATEK INC.

    发明人: Hung-Chi Fang

    IPC分类号: G06T5/50

    摘要: A data buffering apparatus includes a plurality of storage devices and a storage controller. Each of the storage devices is arranged for only storing a partial data of one of a plurality of input images merged in a merged image when data of the merged image is received at a data input port of the data buffering apparatus. The storage controller is coupled to the storage devices, and arranged for alternately controlling stored partial data of the input images to be transmitted to an image/video processing device when the data of the merged image is received at the data input port.

    摘要翻译: 数据缓冲装置包括多个存储装置和存储控制器。 每个存储装置被布置为仅在存储在数据缓冲装置的数据输入端口处接收合并图像的数据时,存储合并在合并图像中的多个输入图像之一的部分数据。 存储控制器耦合到存储装置,并且被布置为当在数据输入端口处接收到合并图像的数据时,交替地控制要发送到图像/视频处理装置的输入图像的存储部分数据。

    Method for detecting occlusion areas

    公开(公告)号:US09917988B2

    公开(公告)日:2018-03-13

    申请号:US14248361

    申请日:2014-04-09

    申请人: MEDIATEK INC.

    摘要: A method and apparatus for occlusion area detection based on block difference associated with a motion vector and a predicted block difference are disclosed. For each current block of a frame, motion estimation is performed based on a temporally previous frame and a temporally subsequent frame. Based on the motion vector derived, two reference blocks of the current block are located in the temporally neighboring frames. The block difference between these two reference blocks is calculated for the current block. By comparing the block difference with a predicted block difference of the current block, the current block is determined to be an occlusion block or not accordingly. The predicted block difference is updated by averaging the block difference of neighboring blocks in a non-motion boundary area.

    Method for detecting foreground
    4.
    发明授权
    Method for detecting foreground 有权
    检测前景的方法

    公开(公告)号:US09563960B2

    公开(公告)日:2017-02-07

    申请号:US14248364

    申请日:2014-04-09

    申请人: MEDIATEK INC.

    摘要: A method and apparatus for foreground detection by designating one of two non-occlusion areas as the foreground area according to results of position matching using two given motion vectors. The detection is performed by matching the position of the current occlusion area in the current frame with one or more positions of a previous occlusion area in a previous frame. The matching operation is based on motion vectors determined for the neighboring areas adjacent to the current occlusion area. The determination of the motion vectors are based on two neighboring frames temporally located before and after the current frame. If the position of the current occlusion area is matched with the previous occlusion area by using one of the motion vectors, the neighboring area corresponding to the motion vector is designated as a foreground area.

    摘要翻译: 根据使用两个给定运动矢量的位置匹配结果,通过将两个非遮挡区域中的一个指定为前景区域来进行前景检测的方法和装置。 通过将当前帧中的当前遮挡区域的位置与先前帧中的先前遮挡区域的一个或多个位置进行匹配来执行检测。 匹配操作基于为邻近当前遮挡区域的相邻区域确定的运动矢量。 运动矢量的确定基于时间上位于当前帧之前和之后的两个相邻帧。 如果通过使用运动矢量之一将当前遮挡区域的位置与先前的遮挡区域相匹配,则将与运动矢量对应的相邻区域指定为前景区域。

    Method for Detecting Occlusion Areas
    5.
    发明申请
    Method for Detecting Occlusion Areas 有权
    检测闭塞区域的方法

    公开(公告)号:US20150296102A1

    公开(公告)日:2015-10-15

    申请号:US14248361

    申请日:2014-04-09

    申请人: MEDIATEK INC.

    IPC分类号: H04N5/14 H04N5/455

    摘要: A method and apparatus for occlusion area detection based on block difference associated with a motion vector and a predicted block difference are disclosed. For each current block of a frame, motion estimation is performed based on a temporally previous frame and a temporally subsequent frame. Based on the motion vector derived, two reference blocks of the current block are located in the temporally neighboring frames. The block difference between these two reference blocks is calculated for the current block. By comparing the block difference with a predicted block difference of the current block, the current block is determined to be an occlusion block or not accordingly. The predicted block difference is updated by averaging the block difference of neighboring blocks in a non-motion boundary area.

    摘要翻译: 公开了一种基于与运动矢量相关联的块差异和预测块差异的遮挡区域检测的方法和装置。 对于帧的每个当前块,基于时间上先前的帧和时间上的后续帧来执行运动估计。 基于导出的运动矢量,当前块的两个参考块位于时间上相邻的帧中。 针对当前块计算这两个参考块之间的块差。 通过将块差与当前块的预测块差进行比较,当前块被确定为闭塞块,或者不相应地确定。 通过对非运动边界区域中的相邻块的块差进行平均来更新预测块差。