• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

一种带有局部特征匹配和立体匹配的微型双目内窥镜，用于三维测量和三维重建。

A Miniature Binocular Endoscope with Local Feature Matching and Stereo Matching for 3D Measurement and 3D Reconstruction.

机构信息

Department of Instrument Science and Engineering, SEIEE, Shanghai Jiao Tong University, Shanghai 200240, China.

Shanghai Engineering Research Center for Intelligent Diagnosis and Treatment Instrument, Shanghai 200240, China.

出版信息

Sensors (Basel). 2018 Jul 12;18(7):2243. doi: 10.3390/s18072243.

DOI:10.3390/s18072243
PMID:30002288
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC6069142/
Abstract

As the traditional single camera endoscope can only provide clear images without 3D measurement and 3D reconstruction, a miniature binocular endoscope based on the principle of binocular stereoscopic vision to implement 3D measurement and 3D reconstruction in tight and restricted spaces is presented. In order to realize the exact matching of points of interest in the left and right images, a novel construction method of the weighted orthogonal-symmetric local binary pattern (WOS-LBP) descriptor is presented. Then a stereo matching algorithm based on Gaussian-weighted AD-Census transform and improved cross-based adaptive regions is studied to realize 3D reconstruction for real scenes. In the algorithm, we adjust determination criterions of adaptive regions for edge and discontinuous areas in particular and as well extract mismatched pixels caused by occlusion through image entropy and region-growing algorithm. This paper develops a binocular endoscope with an external diameter of 3.17 mm and the above algorithms are applied in it. The endoscope contains two CMOS cameras and four fiber optics for illumination. Three conclusions are drawn from experiments: (1) the proposed descriptor has good rotation invariance, distinctiveness and robustness to light change as well as noises; (2) the proposed stereo matching algorithm has a mean relative error of 8.48% for Middlebury standard pairs of images and compared with several classical stereo matching algorithms, our algorithm performs better in edge and discontinuous areas; (3) the mean relative error of length measurement is 3.22%, and the endoscope can be utilized to measure and reconstruct real scenes effectively.

摘要

由于传统的单目内窥镜只能提供清晰的图像，而无法进行 3D 测量和 3D 重建，因此提出了一种基于双目立体视觉原理的微型双目内窥镜，以在紧凑和受限的空间中实现 3D 测量和 3D 重建。为了实现左右图像中兴趣点的精确匹配，提出了一种新颖的加权正交对称局部二值模式（WOS-LBP）描述符的构建方法。然后研究了一种基于高斯加权 AD-Census 变换和改进的基于交叉的自适应区域的立体匹配算法，以实现真实场景的 3D 重建。在该算法中，我们特别调整了边缘和不连续区域的自适应区域确定准则，并通过图像熵和区域生长算法提取由于遮挡而导致的不匹配像素。本文开发了一种外径为 3.17mm 的双目内窥镜，并将上述算法应用于其中。内窥镜包含两个 CMOS 相机和四个用于照明的光纤。实验得出了三个结论：（1）所提出的描述符具有良好的旋转不变性、对光照变化和噪声的区分性和鲁棒性；（2）所提出的立体匹配算法对于 Middlebury 标准图像对的平均相对误差为 8.48%，与几种经典的立体匹配算法相比，我们的算法在边缘和不连续区域表现更好；（3）长度测量的平均相对误差为 3.22%，内窥镜可以有效地用于测量和重建真实场景。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/d65357c12406/sensors-18-02243-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/c54f92b22071/sensors-18-02243-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/a28f884fb37c/sensors-18-02243-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/4668a7bdc0c5/sensors-18-02243-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/961c377f8c2d/sensors-18-02243-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/2dabab1042b9/sensors-18-02243-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/c969fe9b6b21/sensors-18-02243-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/1d6b07400449/sensors-18-02243-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/9a47817d7c20/sensors-18-02243-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/11dddd756b8b/sensors-18-02243-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/a99a3494a565/sensors-18-02243-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/64975edfbdd3/sensors-18-02243-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/19120cd70c7b/sensors-18-02243-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/bfcd522855e4/sensors-18-02243-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/35e2708979da/sensors-18-02243-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/814d6ec8851a/sensors-18-02243-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/e2919d9a1681/sensors-18-02243-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/fb1df07c9a8d/sensors-18-02243-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/c23ae7af2fc4/sensors-18-02243-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/d65357c12406/sensors-18-02243-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/c54f92b22071/sensors-18-02243-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/a28f884fb37c/sensors-18-02243-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/4668a7bdc0c5/sensors-18-02243-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/961c377f8c2d/sensors-18-02243-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/2dabab1042b9/sensors-18-02243-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/c969fe9b6b21/sensors-18-02243-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/1d6b07400449/sensors-18-02243-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/9a47817d7c20/sensors-18-02243-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/11dddd756b8b/sensors-18-02243-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/a99a3494a565/sensors-18-02243-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/64975edfbdd3/sensors-18-02243-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/19120cd70c7b/sensors-18-02243-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/bfcd522855e4/sensors-18-02243-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/35e2708979da/sensors-18-02243-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/814d6ec8851a/sensors-18-02243-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/e2919d9a1681/sensors-18-02243-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/fb1df07c9a8d/sensors-18-02243-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/c23ae7af2fc4/sensors-18-02243-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7b4f/6069142/d65357c12406/sensors-18-02243-g019.jpg

相似文献

1
A Miniature Binocular Endoscope with Local Feature Matching and Stereo Matching for 3D Measurement and 3D Reconstruction.一种带有局部特征匹配和立体匹配的微型双目内窥镜，用于三维测量和三维重建。
Sensors (Basel). 2018 Jul 12;18(7):2243. doi: 10.3390/s18072243.
2
A Method for Broccoli Seedling Recognition in Natural Environment Based on Binocular Stereo Vision and Gaussian Mixture Model.基于双目立体视觉和高斯混合模型的自然环境下西兰花幼苗识别方法。
Sensors (Basel). 2019 Mar 6;19(5):1132. doi: 10.3390/s19051132.
3
Stereoscopic visualization of laparoscope image using depth information from 3D model.利用 3D 模型的深度信息实现腹腔镜图像的立体可视化。
Comput Methods Programs Biomed. 2014 Mar;113(3):862-8. doi: 10.1016/j.cmpb.2013.12.013. Epub 2014 Jan 3.
4
An application of stereo matching algorithm based on transfer learning on robots in multiple scenes.基于迁移学习的立体匹配算法在多场景机器人中的应用。
Sci Rep. 2023 Aug 6;13(1):12739. doi: 10.1038/s41598-023-39964-z.
5
Research on 3D Reconstruction of Binocular Vision Based on Thermal Infrared.基于热红外的双目视觉三维重建研究
Sensors (Basel). 2023 Aug 24;23(17):7372. doi: 10.3390/s23177372.
6
Hybrid constraint optimization for 3D subcutaneous vein reconstruction by near-infrared images.基于近红外图像的三维皮下静脉重建的混合约束优化。
Comput Methods Programs Biomed. 2018 Sep;163:123-133. doi: 10.1016/j.cmpb.2018.06.008. Epub 2018 Jun 15.
7
Fuzzy zoning for feature matching technique in 3D reconstruction of nasal endoscopic images.鼻内镜图像三维重建中用于特征匹配技术的模糊分区
Comput Biol Med. 2015 Dec 1;67:83-94. doi: 10.1016/j.compbiomed.2015.09.021. Epub 2015 Oct 9.
8
Binocular stereo matching algorithm based on MST cost aggregation.基于 MST 代价聚合的双目立体匹配算法。
Math Biosci Eng. 2021 Apr 7;18(4):3215-3226. doi: 10.3934/mbe.2021160.
9
Comparative study on surface reconstruction accuracy of stereo imaging devices for microsurgery.用于显微外科手术的立体成像设备表面重建精度的比较研究。
Int J Comput Assist Radiol Surg. 2016 Jan;11(1):145-56. doi: 10.1007/s11548-015-1240-z. Epub 2015 Jun 24.
10
Perceptual full-reference quality assessment of stereoscopic images by considering binocular visual characteristics.考虑双眼视觉特性的立体图像感知全参考质量评估。
IEEE Trans Image Process. 2013 May;22(5):1940-53. doi: 10.1109/TIP.2013.2240003. Epub 2013 Jan 14.

引用本文的文献

1
Optical Measurement of Ligament Strain: Opportunities and Limitations for Intraoperative Application.光学测量韧带应变：术中应用的机遇与限制。
Sensors (Basel). 2023 Aug 28;23(17):7487. doi: 10.3390/s23177487.
2
Novel and Automatic Rice Thickness Extraction Based on Photogrammetry Using Rice Edge Features.基于稻米边缘特征的新型自动稻米厚度提取的摄影测量法。
Sensors (Basel). 2019 Dec 16;19(24):5561. doi: 10.3390/s19245561.
3
A Robust Method for Automatic Panoramic UAV Image Mosaic.一种用于无人机全景图像自动拼接的稳健方法。

本文引用的文献

1
3D endoscope system using DOE projector.使用衍射光学元件投影仪的3D内窥镜系统。
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:2091-2094. doi: 10.1109/EMBC.2016.7591140.
2
Evaluation of stereo matching costs on images with radiometric differences.具有辐射差异的图像上立体匹配成本的评估。
IEEE Trans Pattern Anal Mach Intell. 2009 Sep;31(9):1582-99. doi: 10.1109/TPAMI.2008.221.
Sensors (Basel). 2019 Apr 22;19(8):1898. doi: 10.3390/s19081898.