Stereo matching algorithm based on Census transformation  and guided filter

ZHOU Zhe; SHEN Jianxin; HAN Peng; JIANG Junjia

doi:10.5768/JAO202041.0102003

Journal of Applied Optics > 2020 > 41(1): 79-85. > DOI: 10.5768/JAO202041.0102003

ZHOU Zhe, SHEN Jianxin, HAN Peng, JIANG Junjia. Stereo matching algorithm based on Census transformation and guided filter[J]. Journal of Applied Optics, 2020, 41(1): 79-85. DOI: 10.5768/JAO202041.0102003

Citation:

PDF (1108 KB)

Stereo matching algorithm based on Census transformation and guided filter

College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

More Information

Received Date: May 12, 2019
Revised Date: June 03, 2019
Available Online: March 30, 2020

Graphical Abstract

Abstract

Abstract

Stereo matching is one of the key steps in binocular stereo vision system, and its accuracy has a significant impact on the subsequent research. The Census algorithm is widely used because of its advantages of simplicity and clarity, good running effect and strong real-time performance. However, the Census stereo matching algorithm also has some disadvantages, such as the center point of transform window is easily disturbed by the external conditions and the accuracy of the depth discontinuous region is low. Therefore, a new stereo matching algorithm based on Census transformation and guided filter was proposed. In the stage of Census transformation, the impact of the external interference was reduced by calculating the pixel average around the transform window. And at the same time, in the stage of cost aggregation, the guided filter with tipping characteristics and its computational complexity was independent of the size for filter nuclear was introduced as the adaptive weight. The experimental results show that the average mistake matching error of the proposed algorithm is 6.03% on the Middlebury test platform. Compared with the current average mistake matching rate of 16.2% for Census stereo matching algorithm, the matching effect is obviously improved, and the algorithm has high efficiency and good radiation invariance.
- binocular stereo vision,
- stereo matching,
- Census transform,
- adaptive weight,
- guided filtering

FullText(HTML)

References (18)

References

[1]	张琦, 胡广地, 李雨生, 等. 改进Fast-RCNN的双目视觉车辆检测方法[J]. 应用光学,2018,39(6):832-838. ZHANG Qi, HU Guangdi, LI Yusheng, et al. Binocular vision vehicle detection method based on improved Fast-RCNN[J]. Journal of Applied Optics,2018,39(6):832-838.
[2]	苏赫. 微创手术机器人图像系统设计方法与空间映射策略研究[D]. 天津: 天津大学, 2016. SU He. Design method and space mapping of minimally invasive surgical robot image system[D]. Tianjin: Tianjin University, 2016.
[3]	ZHANG Z. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334. doi: 10.1109/34.888718
[4]	林俊义, 黄常标, 刘斌, 等. 双目立体视觉摄像机标定及精度分析[J]. 华侨大学学报(自然科学版),2011,32(4):364-367. LIN Junyi, HUANG Changbiao, LIU Bin, et al. Camera calibration and accuracy analysis of stereo vision[J]. Journal of Huaqiao University(Natural Science),2011,32(4):364-367.
[5]	龚文彪, 顾国华, 钱惟贤, 等. 基于图像分割和自适应支撑权重的立体匹配算法[J]. 光学学报,2015,35(s2):s210002. GONG Wenzhen, GU Guohua, QIAN Weixian, et al. Stereo matching algorithm based on image segmentation and adaptive support weights[J]. Acta Optica Sinica,2015,35(s2):s210002.
[6]	韩慧妍. 基于双目立体视觉的三维模型重建方法研究[D]. 太原: 中北大学, 2014. HAN Huiyan. Research on 3D model reconstruction based on binocular stereo vision[J].Taiyuan: North University of China, 2014.
[7]	HSIAO S, WANG W L, WU P S. VLSI implementations of stereo matching using dynamic programming: Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, Hsinchu, Taiwan, China, April 28-30, 2014[C]. USA: IEEE, 2014.
[8]	YANG Y Y, WANG X R, LIANG Q. Belief propagation stereo matching algorithm based on ground control points and spatiotemporal consistency: 2014 7th International Congress on Image and Signal Processing, Dalian, China, October 14-16, 2014[C]. USA: IEEE, 2014.
[9]	BESSE F, ROTHER C, FITZGIBBON A, et al. PMBP: PatchMatch belief propagation for correspondence field estimation[J]. International Journal of Computer Vision,2014,110(1):2-13. doi: 10.1007/s11263-013-0653-9
[10]	SCHARSTEIN D, SZELISKI R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. Computer Vision,2002,47:7-42. doi: 10.1023/A:1014573219977
[11]	MENANT J, GAUTIER G, PRESSIGOUT M, et al. An automatized method to parameterize embedded stereo matching algorithms[J]. Journal of Systems Architecture,2017,80:92-103. doi: 10.1016/j.sysarc.2017.09.002
[12]	ZABIH R, WOODFILL J. Non-parametric local transforms for computing visual correspondence[C]//Computer Vision — ECCV '94. Berlin, Heidelberg: Springer Berlin Heidelberg, 1994: 151-158.
[13]	YOON K, KWEON I S. Adaptive support-weight approach for correspondence search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):650-656. doi: 10.1109/TPAMI.2006.70
[14]	闫利, 王芮, 刘华, 等. 基于改进代价计算和自适应引导滤波的立体匹配[J]. 光学学报,2018,38(11):257-267. YAN Li, WANG Rui, LIU Hua, et al. Stereo matching method based on improved cost computation and adaptive guided filter[J]. Acta Optica Sinica,2018,38(11):257-267.
[15]	MEI X, SUN X, ZHOU M C, et a1. On building an accurate stereo matching system on graphics hardware[C]//Proc. IEEE International Conference on Computer Vision Workshops. Barcelona: IEEE Press, 2011: 467-474.
[16]	RHEMANN C, HOSNI A, BLEYER M, et al. Fast cost-volume filtering for visual correspondence and beyond: CVPR 2011, Colorado Springs, June 20-25, 2011[C]. USA: IEEE, 2011.
[17]	HOSNI A, BLEYER M, RHEMANN C, et al. Real-time local stereo matching using guided image filtering: 2011 IEEE International Conference on Multimedia and Expo, Barcelona, Spain, July 11-15, 2011[C]. USA: IEEE, 2011.
[18]	YANG Q, WANG L, YANG R, et al. Stereo matching with colorweighted, correlation hierarchical belief propagation and occlusion handling[J]. IEEE TPAMI,2009,31(3):492-504. doi: 10.1109/TPAMI.2008.99

[1]	XIANG Wanfeng, CHEN Jie, GUO Yuqing, WANG Xiaoyu, WANG Juanfen. Experimental and simulation study of dual-wavelength fiber laser based on intracavity filtering effect[J]. Journal of Applied Optics, 2024, 45(5): 1079-1084. DOI: 10.5768/JAO202445.0508001
[2]	ZHAO Ming, WANG Tianshu. Switchable soliton molecules and noise-like pulses in hybrid mode-locking fiber laser[J]. Journal of Applied Optics, 2023, 44(2): 456-461. DOI: 10.5768/JAO202344.0208001
[3]	QU Jiahui, ZHANG Haiyang, FAN Yu, WANG Lin, WANG Heying, ZHAO Changming. Mechanism of multi-wavelength laser detection of micro-camera[J]. Journal of Applied Optics, 2022, 43(4): 809-818. DOI: 10.5768/JAO202243.0407004
[4]	ZHAO Ming, WANG Tianshu. High SNR multi-wavelength 2 μm actively mode-locked fiber laser[J]. Journal of Applied Optics, 2021, 42(1): 194-199. DOI: 10.5768/JAO202142.0108001
[5]	WANG Furen, WANG Tianshu, MA Wanzhuo, JIA Qingsong, ZHAO Desheng, LIU Runmin. Multi-wavelength noise-like pulsed erbium-doped fiber laser[J]. Journal of Applied Optics, 2019, 40(4): 710-716. DOI: 10.5768/JAO201940.0408003
[6]	Jia Qingsong, Wang Tianshu, Wang Zhen, Chen Bowen, Bo Baoxue, Jiang Huilin. Temperature sensing characteristics based on multi-wavelength Brillouin fiber laser[J]. Journal of Applied Optics, 2018, 39(4): 585-589. DOI: 10.5768/JAO201839.0408001
[7]	Xu Yu-meng, Wang Guo-zheng, Peng Ling-ling, Liu Xin-nan, Kou Yan-qiang, Wu Ke-xin. Dual-wavelength fiber laser for generating interval-adjustable microwave[J]. Journal of Applied Optics, 2014, 35(4): 729-732.
[8]	LU Xue-feng, BAI Qing-lan. Optimal design for Sagnac interferometer of imaging spectrometer[J]. Journal of Applied Optics, 2012, 33(4): 666-669.
[9]	GAO Jiao-bo, LI Jian-jun, SUN Zhi-jia, WANG Jun, ZHENG Ya-wei, WANG Ji-long. Simulation of multi-wavelength laser composite point target motion[J]. Journal of Applied Optics, 2011, 32(3): 562-567.
[10]	ZHONG Yu-guang, ZHANG Zu-xing. AHigh birefringence coherent fiber filter with selectable wavelengths[J]. Journal of Applied Optics, 2011, 32(1): 96-100.

Cited By

Cited by

Periodical cited type(1)

刘宵婵，陈琛，单宏，刘红军，高松，宋涛，李维善，张禹. 基于4k分辨率小型投影机的鱼眼镜头设计. 应用光学. 2020(05): 1060-1066 .

本站查看

Other cited types(5)

Get Citation

PDF

XML

Article views (1222) PDF downloads (47) Cited by(6)

Turn off MathJax

Article Contents

Abstract

References

Stereo matching algorithm based on Census transformation and guided filter