[1]汪永宝[],杨红雨[][],兰时勇[][]. 基于置信度传播和色度分割算法的深度估计[J].计算机技术与发展,2015,25(09):6-11.
　WANG Yong-bao[] YANG Hong-yu[][],LAN Shi-yong[][]. Depth Estimation of Algorithm Based on Belief Propagation and Color Segmentation [J].,2015,25(09):6-11.
点击复制

 基于置信度传播和色度分割算法的深度估计()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
25
期数:
2015年09期
页码:
6-11
栏目:
智能、算法、系统工程
出版日期:
2015-09-10

文章信息/Info

Title:
 Depth Estimation of Algorithm Based on Belief Propagation and Color Segmentation 
文章编号:
1673-629X（2015)09-0006-06
作者:
 汪永宝[1] ; 杨红雨[1][2] ; 兰时勇[1][2]
 1.四川大学 计算机学院；2.视觉合成图形图像技术国家重点学科实验室
Author(s):
 WANG Yong-bao[1] YANG Hong-yu[1][2]; LAN Shi-yong[1][2]
关键词:
 ; 置信度传播; 多视图几何; 色度分割; 对极几何; 深度估计
Keywords:
 ; belief propagation; multiple view geometry; color segmentation; epipolar geometry; depth estimation
分类号:
TP391.4
文献标志码:
A
摘要:
 为了提高图像序列深度估计的质量，提出了一种基于置信度传播和色度分割的全局匹配算法。首先，构造了包含匹配误差项和平滑性假设的能量函数，通过置信度传播算法来求取初始视差图序列。然后用均值漂移算法对每一帧进行色度分割，对每个色度分割区域分别进行全局匹配，得到新的视差图。最后，构造包含对极几何约束的新能量函数，使用置信度传播算法进行全局匹配和迭代优化，获取最终视差图序列。实验结果表明，文中算法可以得到高质量的深度图，能够改善图像噪声、弱纹理和物体遮挡等问题。
Abstract:
 In order to improve the quality of the depth estimation of the image sequence,a global matching algorithm based on belief prop-agation and color segmentation is proposed. First,the algorithm constructs a matching energy function that contains the matching error term and smoothness assumptions. Estimate the initial disparity map sequences through using the belief propagation algorithm. Then,the each frame is segmented into several color areas by employing the mean shift algorithm. For each of the divided color segmentation re-gions,respectively processing the global matching to obtain the new disparity maps. Finally,create a new energy function that contains a epipolar geometric constraints,to obtain the final disparity map sequences via belief propagation algorithm using global matching and iter-ative optimization. Experimental results demonstrate that the algorithm can get high-quality depth maps and improve image noise,texture-less and occlusions problems.

相似文献/References:

[1]沈剑 路林吉.MRF随机场在文本图像清晰化算法中的应用[J].计算机技术与发展,2011,(06):9.
　SHEN Jian,LU Lin-ji.Enhancement of Document Text Images Using MRF Approach[J].,2011,(09):9.
[2]张志宏,吴庆波,邵立松,等.基于飞腾平台TOE协议栈的设计与实现[J].计算机技术与发展,2014,24(07):1.
　ZHANG Zhi-hong,WU Qing-bo,SHAO Li-song,et al. Design and Implementation of TCP/IP Offload Engine Protocol Stack Based on FT Platform[J].,2014,24(09):1.
[3]梁文快,李毅. 改进的基因表达算法对航班优化排序问题研究[J].计算机技术与发展,2014,24(07):5.
　LIANG Wen-kuai,LI Yi. Research on Optimization of Flight Scheduling Problem Based on Improved Gene Expression Algorithm[J].,2014,24(09):5.
[4]黄静,王枫,谢志新,等. EAST文档管理系统的设计与实现[J].计算机技术与发展,2014,24(07):13.
　HUANG Jing,WANG Feng,XIE Zhi-xin,et al. Design and Implementation of EAST Document Management System[J].,2014,24(09):13.
[5]侯善江[],张代远[][][]. 基于样条权函数神经网络P2P流量识别方法[J].计算机技术与发展,2014,24(07):21.
　HOU Shan-jiang[],ZHANG Dai-yuan[][][]. P2P Traffic Identification Based on Spline Weight Function Neural Network[J].,2014,24(09):21.
[6]李璨,耿国华,李康,等. 一种基于三维模型的文物碎片线图生成方法[J].计算机技术与发展,2014,24(07):25.
　LI Can,GENG Guo-hua,LI Kang,et al. A Method of Obtaining Cultural Debris’ s Line Chart Based on Three-dimensional Model[J].,2014,24(09):25.
[7]翁鹤,皮德常. 混沌RBF神经网络异常检测算法[J].计算机技术与发展,2014,24(07):29.
　WENG He,PI De-chang. Chaotic RBF Neural Network Anomaly Detection Algorithm[J].,2014,24(09):29.
[8]刘茜[],荆晓远[],李文倩[],等. 基于流形学习的正交稀疏保留投影[J].计算机技术与发展,2014,24(07):34.
　LIU Qian[],JING Xiao-yuan[,LI Wen-qian[],et al. Orthogonal Sparsity Preserving Projections Based on Manifold Learning[J].,2014,24(09):34.
[9]尚福华,李想,巩淼. 基于模糊框架-产生式知识表示及推理研究[J].计算机技术与发展,2014,24(07):38.
　SHANG Fu-hua,LI Xiang,GONG Miao. Research on Knowledge Representation and Inference Based on Fuzzy Framework-production[J].,2014,24(09):38.
[10]叶偲,李良福,肖樟树. 一种去除运动目标重影的图像镶嵌方法研究[J].计算机技术与发展,2014,24(07):43.
　YE Si,LI Liang-fu,XIAO Zhang-shu. Research of an Image Mosaic Method for Removing Ghost of Moving Targets[J].,2014,24(09):43.

更新日期/Last Update: 2015-10-16