公开(公告)号：US20160140724A1

公开(公告)日：2016-05-19

申请号：US14941475

申请日：2015-11-13

Applicant: Huawei Technologies Co., Ltd.

Inventor： Mengqi JI ,  Shan GAO ,  Haiyan YANG

IPC: G06T7/00

CPC classification number: G06T7/11 ,  G06K9/38 ,  G06K9/62 ,  G06K9/6277 ,  G06T7/136 ,  G06T7/143 ,  G06T7/194 ,  G06T2207/10024

Abstract: Embodiments of the present invention provide an image processing method and apparatus, where the method includes: determining a Gaussian mixture model of a first area in a first image, where the first area belongs to a background area of the first image, and the first image is a first frame of image in a video; determining a distance from a first pixel in a second image to the Gaussian mixture model; and when the distance from the first pixel to the Gaussian mixture model is less than or equal to a first preset threshold, determining that the first pixel belongs to a background area of the second image. In the embodiments of the present invention, an area to which a pixel belongs can be directly determined according to a distance from the pixel to a Gaussian mixture model, so that image foreground segmentation can be completed efficiently.

Abstract translation: 本发明的实施例提供了一种图像处理方法和装置，其中所述方法包括：确定第一图像中的第一区域的高斯混合模型，其中第一区域属于第一图像的背景区域，第一图像 是视频中第一帧图像; 确定从第二图像中的第一像素到高斯混合模型的距离; 并且当从第一像素到高斯混合模型的距离小于或等于第一预设阈值时，确定第一像素属于第二图像的背景区域。 在本发明的实施例中，可以根据从像素到高斯混合模型的距离直接确定像素所属的区域，从而可以有效地完成图像前景分割。