公开(公告)号：US09262691B2

公开(公告)日：2016-02-16

申请号：US14262636

申请日：2014-04-25

Applicant: CATHOLIC UNIVERSITY INDUSTRY ACADEMIC COOPERATION FOUNDATION

Inventor： Hang-Bong Kang ,  Sang-Hyun Cho

IPC: G06K9/00 ,  G06K9/34 ,  G06T15/00 ,  G06K9/46 ,  G06K9/62 ,  G06T7/00

CPC classification number: G06K9/4676 ,  G06K9/6202 ,  G06T7/11 ,  G06T2207/10012 ,  G06T2207/10024

Abstract: The method for extracting salient object from stereoscopic video includes: dividing regions based on the similarity of color and the distance between pixels in a left-eye image and a right-eye image which are used for an input stereoscopic image; creating a disparity map based on a disparity obtained from a pixel difference of the left-eye image and the right-eye image; calculating a contrast-based saliency by comparing the divided regions and the divided regions of the disparity map; calculating a prior-knowledge-based saliency based on a prior-knowledge for the divided regions and the divided regions of the disparity map; and extracting salient regions of the image based on the contrast-based saliency and the prior-knowledge-based saliency.

Abstract translation: 用于从立体视频中提取突出物体的方法包括：基于颜色的相似度和用于输入立体图像的左眼图像和右眼图像中的像素之间的距离来划分区域; 基于从左眼图像和右眼图像的像素差获得的视差来创建视差图; 通过比较视差图的分割区域和分割区域来计算基于对比度的显着性; 基于视差图的分割区域和分割区域的先验知识计算基于知识的先验显着性; 并基于基于对比度的显着性和先验知识的显着性来提取图像的突出区域。