加权支持域硬件友好型立体匹配技术

侯作勋; 朱睿; 陈秋伯; 吕敏杰

doi:10.3788/OPE.20142210.2861

您当前的位置：

首页 >

文章列表页 >

加权支持域硬件友好型立体匹配技术

信息科学 | 更新时间：2020-08-13

- 加权支持域硬件友好型立体匹配技术
- Hardware friendly stereo matching by employing weighted support region
- 光学精密工程 2014年22卷第10期页码：2861-2869
- 作者机构：
  
  西安交通大学人工智能与机器人研究所,陕西西安,710049
- 作者简介：
- 基金信息：
  
  国家科技"核高基"重大专项资助项目(No.2013ZX01033001-001-002)()
- DOI：10.3788/OPE.20142210.2861
  中图分类号： TN47;TP391.4
- 收稿日期：2014-04-20，
  
  修回日期：2014-06-05，
  
  纸质出版日期：2014-10-25
- 稿件说明：
移动端阅览
侯作勋, 朱睿, 陈秋伯等. 加权支持域硬件友好型立体匹配技术[J]. 光学精密工程, 2014,22(10): 2861-2869

HOU Zuo-xun, ZHU Rui, CHEN Qiu-bo etc. Hardware friendly stereo matching by employing weighted support region[J]. Editorial Office of Optics and Precision Engineering, 2014,22(10): 2861-2869
侯作勋, 朱睿, 陈秋伯等. 加权支持域硬件友好型立体匹配技术[J]. 光学精密工程, 2014,22(10): 2861-2869 DOI： 10.3788/OPE.20142210.2861.

HOU Zuo-xun, ZHU Rui, CHEN Qiu-bo etc. Hardware friendly stereo matching by employing weighted support region[J]. Editorial Office of Optics and Precision Engineering, 2014,22(10): 2861-2869 DOI： 10.3788/OPE.20142210.2861.

摘要

为了准确获取实际场景中的深度信息

本文通过引入空间距离权重

提出了同时考虑局部区域相似度和接近度的加权支持域立体匹配方法.首先

对输入图像进行滤波

去除图像中的噪声

并通过Mini-Census变换求取Hamming距离.然后

建立加权支持域

求取代价累积;进而通过winner-take-all方法求取最小匹配代价和原始视差图.最后

对原始视差图进行细化处理

得到优化的视差图

并反演出空间的深度分布.实验结果表明

利用该算法在不同光照、不同场景下均能够正确地产生视差图;对标准数据库图片进行处理时

平均错误率仅为6.77%.该算法有效地降低了计算复杂度

具有计算精度高、适应性强、鲁棒性好、便于硬件实现等特点

可为高精度实时立体匹配专用处理硬件的设计和实现提供基础.

Abstract

A hardware friendly stereo matching algorithm by employing a weighted support region was proposed with considering the local similarity and proximity of the local region to acquire the depth information in the real scenes accurately. Firstly

the input image were filtered to remove the noise and the results of the Mini-Census transform were used to calculate the Hamming distance. Then

the weighted support region was built to finish the cost aggregation and furthermore to find the minimal matching cost and generate a raw disparity map by the winner-take-all method. Finally

the raw disparity map was refined to generate the optimal disparity map and to deduce its depth distribution in the real scenes. The experimental result shows that the algorithm produces the disparity map accurately in different illumination conditions and different scenes

and its processing average bad pixel rate is only 6.77% when the images of the standard database are processed by the proposed algorithm. The proposed algorithm reduces computational complexity and is characterized by higher accuracy

good adaptability and fine robustness. It provides a basis for design and implementation of specific hardware for high accuracy stereo matching.

关键词

Keywords

references

王欣,袁坤,于晓,等. 基于运动恢复的双目视觉三维重建系统设计[J]. 光学精密工程,2014,22(5): 1379-1387. WANG X, YUAN K, YU X,et al.. Design of binocular vision 3D reconstruction system based on motion recovery[J]. Opt. Precision Eng., 2014,22(5): 1379-1387. (in Chinese)

吴迪,王奎民,赵玉新,等. 分段正则化正交匹配追踪算法[J]. 光学精密工程,2014,22(5): 1395-1402. WU D, WANG K M, ZHAO Y X,et al.. Stagewise regularized orthogonal matching pursuit algorithm[J]. Opt. Precision Eng., 2014,22(5): 1395-1402. (in Chinese)

全燕鸣,黎淑梅,麦青群. 基于双目视觉的工件尺寸在机三维测量[J]. 光学精密工程,2013,21(4): 1054-1061. QUAN Y M, LI S M, MAI Q Q. On-machine 3D measurement of workpiece dimensions based on binocular vision [J]. Opt. Precision Eng., 2013, 21(4): 1054-1061. (in Chinese)

张来刚,魏仲慧,何昕,等. 面向低纹理图像的快速立体匹配[J]. 液晶与显示,2013,28(3): 450-458. ZHANG L G, WEI ZH H, HE X, et al.. New stereo matching method based edge extraction [J]. Chinese Journal of Liquid Crystals and Displays, 2013,28(3): 450-458. (in Chinese)

王嘉辉,邓玉桃,苏剑邦,等. 全高清裸眼3D显示效果的评价与测量[J]. 液晶与显示,2013,28(5): 805-809. WANG J H, DENG Y T, SU J B, et al.. Evaluation and measurement of display effect in full high resolution autostereoscopic display [J].Chinese Journal of Liquid Crystals and Displays, 2013,28(5):805-809. (in Chinese)

CHANG N C, TSAI T H, HSU B H, et al.. Algorithm and architecture of disparity estimation with Mini-Census adaptive support weight [J]. IEEE Transactions on Circuits and Systems for Video Technolog, 2010, 20(6):792-805.

ZHANG K, LU J, LAFRUIT G. Cross-based local stereo matching using orthogonal integral images [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2009, 19 (7):1073-1079.

ZHANG L, ZHANG K, CHANG TS, et al.. Real-time high-definition stereo matching on FPGA[C]. ACM/SIGDA International Symposium on Field Programmable Gate Arrays, 2011:55-64.

HOU Z, MA Y, ZHU H, et al.. Real-time very large-scale integration recognition system with an on-chip adaptive k-means learning algorithm [J]. Japanese Journal of Applied Physics, 2013, 52 (4):04CE11.

SCHARSTEIN D, SZELISKI R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms [J]. International Journal of Computer Vision, 2002, 47 (1-3): 7-42.

YOON K, KWEON IS. Adaptive support-weight approach for correspondence search [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28 (4): 650-656.

HUMENBERGER M, ZINNER C, WEBER M, et al.. A fast stereo matching algorithm suitable for embedded real-time systems [J]. Computer Vision and Image Understanding, 2010, 114 (11):1180-1202.

JIN S, CHO J, DAI P X, et al.. FPGA design and implementation of a real-time stereo vision system [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2010, 20 (1): 15-26.

浏览量

404

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

强环境噪声下的双目视觉受电弓轨旁异常检测

空洞卷积和双边格网的立体匹配网络

基于光线散射衰减模型的低照度图像增强

基于城市遥感卫星影像对的立体匹配

利用平面约束的月球车立体匹配方法