公开(公告)号：US20140204227A1

公开(公告)日：2014-07-24

申请号：US14163090

申请日：2014-01-24

Applicant: STMicroelectronics S.r.l.

Inventor： Giuseppe SPAMPINATO ,  Arcangelo Ranieri BRUNA

IPC: H04N5/232

CPC classification number: H04N5/23254 ,  G06T7/246 ,  H04N5/23261 ,  H04N5/23267 ,  H04N5/23277

Abstract: According to an embodiment, a sequence of video frames as produced in a video-capture apparatus such as a video camera is stabilized against hand shaking or vibration by:—subjecting a pair of frames in the sequence to feature extraction and matching to produce a set of matched features;—subjecting the set of matched features to an outlier removal step; and—generating stabilized frames via motion-model estimation based on features resulting from outlier removal. Motion-model estimation is performed based on matched features having passed a zone-of-interest test confirmative that the matched features passing the test are distributed over a plurality of zones across the frames.

Abstract translation: 根据实施例，在诸如摄像机的视频捕获设备中产生的视频帧序列通过以下方式稳定，以防止手抖动或振动： - 在序列中插入一对帧以特征提取和匹配以产生一组 的匹配特征; - 将匹配的特征集合发布到异常值去除步骤; 并基于异常值去除产生的特征，通过运动模型估计产生稳定帧。 基于已经通过感兴趣区域测试的匹配特征来执行运动模型估计，证实通过测试的匹配特征分布在跨越帧的多个区域上。

公开(公告)号：US20170169311A1

公开(公告)日：2017-06-15

申请号：US15169232

申请日：2016-05-31

Applicant: STMicroelectronics S.r.l.

Inventor： Giuseppe SPAMPINATO ,  Arcangelo Ranieri BRUNA ,  Viviana D'ALTO

IPC: G06K9/62 ,  G06T7/20 ,  G06K9/48

CPC classification number: G06K9/6218 ,  G06K9/481 ,  G06K9/6202 ,  G06K9/623 ,  G06T7/2033 ,  G06T7/215 ,  G06T7/246 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/20024

Abstract: Image processing circuitry processes image frames in a sequence of image frames, for example, to identify objects of interest. The processing includes filtering motion vectors associated with a current image frame, grouping the filtered motion vectors associated with the current image frame into a set of clusters associated with the current image frame, and selectively merging clusters in the set of clusters associated with the current image frame. At least one of the filtering, the grouping and the merging may be based on one or more clusters associated with one or more previous image frames in the sequence of image frames. Motion vectors included in merged clusters associated with a previous frame may be added to filtered motion vectors before grouping the motion vectors in the current frame.

公开(公告)号：US20130336590A1

公开(公告)日：2013-12-19

申请号：US13875541

申请日：2013-05-02

Applicant: STMicroelectronics S.r.l.

Inventor： Alexandro SENTINELLI ,  Luca CELETTO ,  Arcangelo Ranieri BRUNA ,  Giuseppe SPAMPINATO ,  Claudio Domenico MARCHISIO

IPC: G06K9/62

CPC classification number: G06K9/6201 ,  G06F16/739 ,  H04N5/772

Abstract: An embodiment includes a method and an apparatus for the generation of a visual story board in real time in an image-capturing device including a photo sensor and a buffer, wherein the method includes the consecutively performed steps: starting the recording of a video, receiving information on an image frame of the video, comparing the information on the received image frame with information on at least one of a plurality of image frames wherein the information on the plurality of image frames has previously been stored in the buffer, storing the information on the received image frame in the buffer depending on the result of the comparison, and finishing the recording of the video.

Abstract translation: 一个实施例包括一种用于在包括光传感器和缓冲器的图像捕获设备中实时生成视觉故事板的方法和装置，其中该方法包括连续执行的步骤：开始录像，接收 关于视频的图像帧的信息，将关于接收到的图像帧的信息与关于多个图像帧的信息先前已经存储在缓冲器中的多个图像帧中的至少一个的信息进行比较，将该信息存储在 根据比较结果在缓冲器中接收的图像帧，并完成视频的记录。