|本期目录/Table of Contents|

[1]冯杰,马汉杰.基于视频压缩域的深度图推理算法研究[J].浙江理工大学学报,2016,35-36(自科3):421-426.
 FENG Jie,MA Hanjie.Depth Map Inference Algorithm Based on Video Compression Domain[J].Journal of Zhejiang Sci-Tech University,2016,35-36(自科3):421-426.
点击复制

基于视频压缩域的深度图推理算法研究()
分享到:

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第35-36卷
期数:
2016年自科3期
页码:
421-426
栏目:
出版日期:
2016-05-10

文章信息/Info

Title:
Depth Map Inference Algorithm Based on Video Compression Domain
文章编号:
1673-3851 (2016) 03-0421-06
作者:
冯杰马汉杰
浙江理工大学信息学院,杭州 310018
Author(s):
FENG Jie MA Hanjie
School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
关键词:
2D到3D视频转换深度图运动矢量压缩域
分类号:
TP37
文献标志码:
A
摘要:
对2D到3D视频转换过程中的深度图推理算法进行了研究。该研究以视频压缩域中的宏块为单位进行深度图推理,根据不同的宏块类型选择不同的推理策略。首先,采用基于邻块的运动估计算法对帧内宏块的运动矢量进行计算;然后,针对帧间宏块,对直接提取出的运动矢量进行滤波处理以提升其鲁棒性;最后,采用运动补偿和上采样双边滤波技术获得深度图。实验结果表明该方法可以获得平滑而可靠的深度图像,并且具有更好的深度图像质量。

参考文献/References:

[1] 黄晓军,王梁昊.2D视频转换3D视频技术概览[J].影视制作,2011,17(2):34-36.
[2] VAREKAMP B, BARENBRUG C. Improved depth propagation for 2D to 3D video conversion using keyframes[C]// 4th European Conference on Visual Media Production. London: IET, 2007: 1-7.
[3] WU C, ER G, XIE X, LI T, et al. A novel method for semiautomatic 2D to 3D video conversion[C]// 3DTV Conference: the True Vision   Capture, Transmission and Display of 3D Video. Istanbul: IEEE. 2008: 65-68.
[4] LIE W N, CHEN C Y, CHEN W C. 2D to 3D video conversion with keyframe depth propagation and trilateral filtering[J]. Electronics Letters, 2011, 47(5): 319-321.
[5] VOSTERS  L, DE HAAN G. Efficient and Stable SparsetoDense Conversion for Automatic 2D to 3D Conversion[J]. Circuits and Systems for Video Technology, IEEE Transactions on, 2013, 23(3): 373-386.
[6] PHAN R, ANDROUTSOS D. Robust semiautomatic depth map generation in unconstrained images and video sequences for 2d to stereoscopic 3d conversion[J]. Multimedia, IEEE Transactions on, 2014, 16(1): 122-136.[7] FENG J, CHEN Y, TIAN X. Moving object segmentation algorithm based on cellular neural networks in the H. 264 compressed domain[J]. Optical Engineering, 2009, 48(7): 077001-077001-7.
[8] RIEMENS A K, GANGWAL O P, BARENBRUG B, et al. Multistep joint bilateral depth upsampling [C]// IS&T/SPIE Electronic Imaging. International Society for Optics and Photonics, 2009: 72570M 72570M 12.

相似文献/References:

[1]任瀚实,周志宇,孙树森.基于通道注意力机制的室内场景深度图补全[J].浙江理工大学学报,2023,49-50(自科三):344.
 REN Hanshi,ZHOU Zhiyu,SUN Shusen.Depth map completion for indoor scenes based on the channel attention mechanism[J].Journal of Zhejiang Sci-Tech University,2023,49-50(自科3):344.

备注/Memo

备注/Memo:
收稿日期: 2016-01-16
基金项目: 国家自然科学基金项目(61501402)
作者简介: 冯杰(1980-),男,辽宁锦州人,讲师,主要从事视频处理方面的研究
更新日期/Last Update: 2016-06-06