| 本文已被：浏览 4642次 下载 6915次 |
码上扫一扫！ |
|
|
| 立体视频编码中的目标分割与立体匹配算法 |
|
朱仲杰1,2, 郁梅2,3, 蒋刚毅2,3, 吴训威1,2
|
|
1.浙江大学,信息与电子工程系,浙江,杭州,310027;2.宁波大学,电路与系统研究所,浙江,宁波,315211;3.西安电子科技大学ISN国家重点实验室,陕西,西安,710071
|
|
| 摘要: |
| 视频目标分割与立体匹配是目标基立体视频编码中的核心技术.首先在单通道视频目标分割的基础上提出一种轮廓跟踪匹配算法,以提取立体视频目标对,然后提出一种基于目标的视差估计算法.它以具有特征信息的像素为匹配基元,结合视差匹配约束进行视差估计,克服了传统块匹配算法视差场不连续、视差精度差的缺点,可以获得较为精确和平滑的视差场. |
| 关键词: 立体视频编码 视频目标分割 视差匹配 |
| DOI： |
| 分类号: |
| 基金项目:Supported by the Project-Sponsored by SRF for ROCS, SEM under Grant No.2001331 (教育部留学归国人员科研基金); the Natural Science Foundation of Zhejiang Province of China under Grant Nos.RC01057, 601017 (浙江省自然科学基金); the Open Project Foundation of National Key Laboratory of ISN of Xidian of China under Grant No.H02025 (西安电子科技大学ISN国家重点实验室开放基金); the Key Doctor Foundation of Ningbo of China under Grant No.01J20300-05 (宁波市重点博士基金) |
|
| New Algorithms for Object Segmentation and Stereo Correspondence in Stereo Video Coding |
|
ZHU Zhong-Jie,YU Mei,JIANG Gang-Yi,WU Xun-Wei
|
| Abstract: |
| Video object segmentation and stereo correspondence is a key technology in object-based stereo video coding. In this paper, based on an algorithm for extracting video object in one view-channel, a new contour tracking and correspondence algorithm is first proposed for extracting stereo video object pairs. Then, a disparity estimation algorithm based on video objects is proposed. It takes a characteristic pixel as a correspondence primitive and the disparity estimation is implemented with disparity constraints. The disadvantages of discontinuous and imprecise disparities with the traditional block-based algorithms can be improved and a precise and smooth disparity field can be finally acquired. |
| Key words: stereo video coding video object segmentation disparity correspondence |
