基于频率敏感三维自组织映射的立体视频视差估计算法

doi:10.19678/j.issn.1000-3428.0046947

计算机工程 ›› 2018, Vol. 44 ›› Issue (5): 252-255. doi: 10.19678/j.issn.1000-3428.0046947

基于频率敏感三维自组织映射的立体视频视差估计算法

任云,程福林,黎洪松

桂林电子科技大学信息与通信学院,广西桂林 541004

收稿日期:2017-04-25 出版日期:2018-05-15 发布日期:2018-05-15
作者简介:任云(1992—),女,硕士研究生,主研方向为视频通信、神经网络算法;程福林,硕士研究生;黎洪松,教授、博士。
基金资助:
国家自然科学基金(61261035)。

Stereo Video Parallax Estimation Algorithm Based on Frequency Sensitive Three-dimensional Self-organizing Mapping

REN Yun,CHENG Fulin,LI Hongsong

School of Information and Communication,Guilin University of Electronic Technology,Guilin,Guangxi 541004,China

Received:2017-04-25 Online:2018-05-15 Published:2018-05-15

摘要/Abstract

摘要： 传统基于块的立体视频视差估计算法计算复杂、效率较低,难于以硬件实现。为此,提出一种基于三维自组织映射的视差模式识别算法。根据图像块均值的大小,为视差序列建立高、底亮度模式库,输入块根据均值大小在不同的库中匹配模式块,从而实现视差估计。在模式库训练时引入频率敏感方法,以提高矢量利用率,减少死神经元,降低获胜矢量响应频率。实验结果表明,与基于块的视差估计算法相比,该算法的视差预测图像的平均峰值信噪比提高了1.78 dB。

关键词: 视差估计, 自组织映射算法, 聚类算法, 视差模式识别, 立体视频编码

Abstract: Traditional stereo video parallax estimation algorithm based on blocks is difficult to be implemented in hardware,because of its complexity and low efficiency.To solve this problem,parallax pattern recognition algorithm based on three-dimensional self-organizing mapping is proposed.According to the mean values of image blocks,establish pattern library with high brightness and pattern library with low brightness for the parallax sequence.Input blocks can search their matching pattern blocks in different libraries according to mean values.In the library training,the frequency sensitive method is introduced to improve the utilization of vectors,reduce the dead neurons,and decrease the response frequency of the winning vectors.In the experiments,the average Peak Signal-to-Noise Ratio(PSNR) of the algorithm is 1.78 dB,and that results are higher than the traditional parallax estimation algorithm.

Key words: parallax estimation, self-organizing mapping algorithm, clustering algorithm, parallax pattern recognition, stereo video coding

中图分类号:

TN919.8

任云,程福林,黎洪松. 基于频率敏感三维自组织映射的立体视频视差估计算法[J]. 计算机工程, 2018, 44(5): 252-255.

REN Yun,CHENG Fulin,LI Hongsong. Stereo Video Parallax Estimation Algorithm Based on Frequency Sensitive Three-dimensional Self-organizing Mapping[J]. Computer Engineering, 2018, 44(5): 252-255.

http://www.ecice06.com/CN/Y2018/V44/I5/252

参考文献

［1］POLLEFEYS M,VAN G L,VERGAUWEN M,et al.Visual modeling with a hand-held camera［J］.International Journal of Computer Vision,2004,59(3):207-232.
［2］BROWN M Z,BURSCHKA D,HAGER G D.Advances in computational stereo［J］.IEEE Transactions on Pattern Analysis & Machine Intelligence,2003,25(8):993-1008.
［3］SCHARSTEIN D,SZELISKI R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms［J］.International Journal of Computer Vision,2002,47(1):7-42.
［4］YOON K J,KWEON I S.Adaptive support-weight approach for correspondence search［J］.IEEE Transactions on Pattern Analysis & Machine Intelligence,2006,28(4):650-656.
［5］HOSNI A,BLEYER M,GELAUTZ M,et al.Local stereo matching using geodesic support weights［C］//Proceedings of IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2010:2093-2096.
［6］WEI Y,QUAN L.Region-based progressive stereo matching［C］//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2004:106-113.
［7］HONG L,CHEN G.Segment-based stereo matching using graph cuts［C］//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2004:74-81.
［8］SUN J,SHUM H Y,ZHENG N N.Stereo matching using belief propagation［C］//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer-Verlag,2002:510-524.
［9］HAUBLEIN K,REICHENBACH M,FEY D.Fast and generic hardware architecture for stereo block matching applications on embedded systems［C］//Proceedings of International Conference on Reconfigurable Computing and FPGAs.Washington D.C.,USA:IEEE Press,2014:1-6.
［10］SAHLBACH H,ERNST R,WONNEBERGER S,et al.Exploration of FPGA-based dense block matching for motion estimation and stereo vision on a single chip［C］//Proceedings of IEEE Intelligent Vehicles Symposium.Washington D.C.,USA:IEEE Press,2013:823-828.
［11］WANG Y C,TUNG C P,CHUNG P C.Efficient disparity estimation using hierarchical bilateral disparity structure based graph cut algorithm with a foreground boundary refinement mechanism［J］.IEEE Transactions on Circuits & Systems for Video Technology,2013,23(5):784-801.
［12］赵戈,蔺蘭,唐延东,等.一种基于曲率与置信度传播的视差估计方法［J］.模式识别与人工智能,2013(12):1154-1160.
［13］刘欣.基于立体视觉的公交客流统计方法与实现［D］.秦皇岛:燕山大学,2013.
［14］PODDAR S,SAHU H,BANGALE M R,et al.Feature based dense disparity estimation［C］//Proceedings of IEEE International Conference on Industrial Instrumentation and Control.Washington D.C.,USA:IEEE Press,2015:950-955.
［15］KAMENCAY P,BREZNAN M,JELSOVKA D,et al.Sparse disparity map computation from stereo-view images using segment based algorithm［C］//Proceedings of the 22nd International Conference Radioelektronika.Washington D.C.,USA:IEEE Press,2012:1-4.
［16］RAMAN S,KANOJIA G,KANOJIA G,et al.Facial stereo:facial depth estimation from a stereo pair［C］//Proceedings of International Conference on Computer Vision Theory and Applications.Washington D.C.,USA:IEEE Press,2014:686-691.
［17］KOHONEN T.Essentials of the self-organizing map［J］.Neural Networks,2013,37:52-65.
［18］LI N,CHENG X,ZHANG S,et al.Realistic human-action recognition by fast HOG3D and self-organization feature map［J］.Machine Vision and Applications,2014,25(7):1793-1812.
［19］KAMAL S,MUJEEB A,SUPRIYA M H.Novel class detection of underwater targets using self-organizing neural networks［C］//Proceedings of Underwater Technology (UT),2015 IEEE.Washington D.C.,USA:IEEE Press,2015:1-5.
［20］PARK S,RYU S,CHOI Y,et al.A framework for baseline load estimation in demand response:data mining approach［C］//Proceedings of IEEE International Conference on Smart Grid Communications.Washington D.C.,USA:IEEE Press,2014:638-643.
［21］MCLOUGHLIN F,DUFFY A,CONLON M.A clustering approach to domestic electricity load profile characterisation using smart metering data［J］.Applied Energy,2015,141:190-199.

[1]	王芙银, 张德生, 肖燕婷. 基于加权共享近邻与累加序列的密度峰值算法[J]. 计算机工程, 2022, 48(4): 61-69.
[2]	王治和, 王淑艳, 杜辉. 基于密度敏感距离的改进模糊C均值聚类算法[J]. 计算机工程, 2021, 47(5): 88-96,103.
[3]	周伟枭, 蓝雯飞. 融合文本分类的多任务学习摘要模型[J]. 计算机工程, 2021, 47(4): 48-55.
[4]	刘宇航, 马慧芳, 刘海姣, 余丽. 一种可重叠子空间K-Means聚类算法[J]. 计算机工程, 2020, 46(8): 58-63,71.
[5]	陆慎涛, 葛洪伟. 一种抗噪的移动时间势能聚类算法[J]. 计算机工程, 2020, 46(5): 144-149.
[6]	张强, 张勇, 刘芝国, 周文军, 刘佳慧. 基于改进YOLOv3的手势实时识别方法[J]. 计算机工程, 2020, 46(3): 237-245,253.
[7]	唐鸿成, 文畅, 冯文祥, 谢凯, 方文青. 基于智能聚类模型的海量数据快速显示方法[J]. 计算机工程, 2019, 45(8): 53-59.
[8]	钱雪忠,姚琳燕. 面向稀疏高维大数据的扩展增量模糊聚类算法[J]. 计算机工程, 2019, 45(6): 75-81.
[9]	牛壮,李凤莲,张雪英,樊宇宙,魏鑫. 改进欠抽样方法及其在非平衡数据集分类中的应用[J]. 计算机工程, 2019, 45(6): 218-224.
[10]	王卫华,应时,贾向阳,王冰明,程国力. 一种基于日志聚类的多类型故障预测方法[J]. 计算机工程, 2018, 44(7): 67-73.
[11]	谢永华,朱延刚,赵贤国. 基于Zernike矩与BoF-SURF特征融合的花粉图像分类识别[J]. 计算机工程, 2018, 44(7): 259-263,270.
[12]	陈建,王子磊,奚宏生. 基于情境感知的广播电视群组发现策略[J]. 计算机工程, 2018, 44(5): 140-145.
[13]	赵英,韩春昊. 马尔科夫模型在网络流量分类中的应用与研究[J]. 计算机工程, 2018, 44(5): 291-295.
[14]	宁可,孙同晶,徐洁洁. 面向海量数据的改进最近邻优先吸收聚类算法[J]. 计算机工程, 2018, 44(4): 35-40.
[15]	曾碧,黄文. 一种融合多特征聚类集成的室内点云分割方法[J]. 计算机工程, 2018, 44(3): 281-286.

选择文件类型/文献管理软件名称

选择包含的内容

基于频率敏感三维自组织映射的立体视频视差估计算法

Stereo Video Parallax Estimation Algorithm Based on Frequency Sensitive Three-dimensional Self-organizing Mapping

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于频率敏感三维自组织映射的立体视频视差估计算法

Stereo Video Parallax Estimation Algorithm Based on Frequency Sensitive Three-dimensional Self-organizing Mapping

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价