不连续相位跳变点的三维深度分割

邓吉; 李健; 封皓; 曾周末

doi:10.3788/OPE.20192711.2459

您当前的位置：

首页 >

文章列表页 >

不连续相位跳变点的三维深度分割

信息科学 | 更新时间：2020-08-13

- 不连续相位跳变点的三维深度分割
- Three-dimensional depth segmentation technique utilizing discontinuities of wrapped phase sequence
- 光学精密工程 2019年27卷第11期页码：2459-2466
- 作者机构：
  
  天津大学精密测试技术及仪器国家重点实验室，天津 300072
- 作者简介：
  
  [ "邓吉(1993-)，男，博士，2017年于合肥工业大学获得硕士学位，现为天津大学精密仪器与光电子工程学院博士生，主要研究方向为结构光三维投影测量技术。E-mail：dengji@tju.edu.cn" ]
  [ "李健(1974-)，男，山东人，教授，博士生导师，分别于1994年、1997年和2000年在天津大学获得学士学位、硕士学位和博士学位。主要从事管道泄漏检测、管道安全预警和新型管道内检测器。E-mail：tjupipe@tju.edu.cn" ]
- 基金信息：
  
  国家重点研发计划“重大科学仪器设备开发”专项资助(2016YFF0101802)
- DOI：10.3788/OPE.20192711.2459
  中图分类号： TP391; TH741
- 收稿日期：2018-12-03，
  
  录用日期：2019-2-2，
  
  纸质出版日期：2019-11-15
- 稿件说明：
移动端阅览
邓吉, 李健, 封皓, 等. 不连续相位跳变点的三维深度分割[J]. 光学精密工程, 2019,27(11):2459-2466.

Ji DENG, Jian LI, Hao FENG, et al. Three-dimensional depth segmentation technique utilizing discontinuities of wrapped phase sequence[J]. Optics and precision engineering, 2019, 27(11): 2459-2466.
邓吉, 李健, 封皓, 等. 不连续相位跳变点的三维深度分割[J]. 光学精密工程, 2019,27(11):2459-2466. DOI： 10.3788/OPE.20192711.2459.

Ji DENG, Jian LI, Hao FENG, et al. Three-dimensional depth segmentation technique utilizing discontinuities of wrapped phase sequence[J]. Optics and precision engineering, 2019, 27(11): 2459-2466. DOI： 10.3788/OPE.20192711.2459.

摘要

本文提出了一种简易的三维深度分割技术，该技术能够对存在突变表面的物体的不同深度区域进行分割。为实现该项技术，首先需要搭建由投影仪、相机和物体组成的深度分割平台。由投影仪向被分割物体投射一系列相移数字光栅；数字光栅经物体表面调制，被相机采集并存入计算机中待后续处理。将所采集的序列数字光栅进行顺序置换操作，依次获得三种序列的数字光栅组，通过最小二乘法对不同序列光栅组进行解相位并因此得到包裹相位组。包裹相位组经差分与相交运算后，可获得相交边缘；对相交边缘进行图像增强操作后即可对不同三维深度的不连续区域进行分割。仿真结果表明，对于900 pixel×900 pixel范围的复杂面型，该算法的分割偏移误差仅为2 pixel。实验结果表明：该技术能够对多个不同深度的相似颜色物体进行精确的分割。因此，本方法具备低消耗，高精度三维深度分割的能力。

Abstract

To segment objects with abrupt change surface positioned at different depth

this paper presented a flexible technique for 3D depth segmentation. The system consisted of one projector

one camera

and the objects for segmentation. The first step was to establish the system for segmentation. The second step was to cast the phase-shifted gratings onto the object surface. The gratings

which were modulated by the 3D information of the objects

were then captured by the camera and sent to the computer for further processing. The wrapped phase sequence could then be calculated by changing the sequence of the phase-shifted patterns and using the least squares algorithm. By applying the neighbor pixel difference algorithm to the wrapped phase maps

the edges for segmentation could be retrieved further. Finally

these edges could be optimized and sent for segmentation. The simulation result shows that the method can effectively segment the complex objects with size 900 × 900 pixels

with the corresponding error reaching only two pixels. The experimental result shows that the approach can segment objects with similar color precisely. The proposed method has the advantages of low cost

high precision

and can perform the task of 3D depth segmentation.

关键词

Keywords

references

王宇, 王宝山, 王田, 等.面向遥感图像水域分割的图像熵主动轮廓模型[J].光学精密工程, 2018 26(3): 698-707.

WANG Y, WANG B SH, WANG T, et al .. Image entropy active contour models towards water area segmentation in remote sensing image[J]. Opt. Precision Eng. , 2018, 26(3): 698-707.(in Chinese)

温广瑞, 徐斌, 张志芬, 等.基于差商的油液监测铁谱图像自适应分割[J].光学精密工程, 2017 25(5):1322-1330.

WEN G R, XU B, ZHANG ZH F, et al .. Self-adaptive segmentation of oil monitoring ferrographic image based on difference quotient[J]. Opt. Precision Eng. , 2017, 25(5):1322-1330.(in Chinese)

邓吉, 李健, 封皓, 等.编码条纹投影技术的阶次校正算法[J].仪器仪表学报, 2018, 39(8): 250-258.

DENG J, LI J, FENG H, et al .. Fringe order correction algorithm for code-based fringe projection profilometry[J]. Chinese Journal of Scientific Instrument , 2018, 39(8): 250-258.(in Chinese)

肖启阳, 李健, 吴思进, 等.基于能量的DSPI相位图正余弦降噪[J].光学精密工程, 2018, 26(4):936-943.

XIAO Q Y, LI J, WU S J, et al .. Denoising of DSPI phase map using sine-cosine filtering and signal energy[J]. Opt. Precision Eng. , 2018, 26(4):936-943.(in Chinese)

YANG X, ZENG C N, LUO J, et al .. Absolute phase retrieval using one coded pattern and geometric constraints of fringe projection system[J]. Applied Sciences , 2018, 8(12): 2673.

JEON B K, JUNG Y B, HONG K S. Image segmentation by unsupervised sparse clustering[C]. Application of Computer Vision , Wacv / motions 051 Seventh IEEE Workshops on . IEEE , 2005.

CHERIET M, SAID J N, SUEN C Y. A recursive thresholding technique for image segmentation[J]. IEEE Transactions on Image Processing , 1998, 7(6): 918-921.

尹诗白, 孔垂涵, 王一斌.非监督层次化模糊相关的人体红外图像分割[J].光学精密工程, 2018, 26(6): 1542-1550.

YIN S B, KONG C H, WANG Y B. Unsupervised hierarchical human target infrared image segmentation through fuzzy correlation[J]. Opt. Precision Eng. , 2018, 26(6): 1542-1550.(in Chinese)

FELZENSZWALB P F, HUTTENLOCHER D P. Efficient graph-based image segmentation[J]. International Journal of Computer Vision , 2004, 59(2): 167-181.

SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017, 39(4): 640-651.

DOSOVITSKIY A, FISCHER P, ILG E, et al .. FlowNet: learning optical flow with convolutional networks[C]. 2015 IEEE International Conference on Computer Vision ( ICCV ), December 7-13, 2015. Santiago . New York , USA : IEEE , 2015.

FU H Z, XU D, LIN S, et al .. Object-based RGBD image co-segmentation with mutex constraint[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), June 7-12, 2015. Boston , MA , USA . New York , USA : IEEE , 2015.

BLEIWEISS A, WERMAN M. Fusing Time-of-Flight Depth and Color for Real-Time Segmentation and Tracking [M]. Dynamic 3D Imaging. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009: 58-69.

RAO D, LE Q V, PHOKA T, et al .. Grasping novel objects with depth segmentation[C]. 2010 IEEE / RSJ International Conference on Intelligent Robots and Systems , October 18-22, 2010. Taipei . New York , USA : IEEE , 2010.

DENG H X, DENG J, MA M C, et al .. 3D information detection with novel five composite fringe patterns[J]. Modern Physics Letters B , 2017, 31(19/20/21): 1740088.

MA M C, YAO P C, DENG J, et al .. A morphology phase unwrapping method with one code grating[J]. Review of Scientific Instruments , 2018, 89(7): 073112.

MERNER L, WANG Y, ZHANG S. Accurate calibration for 3D shape measurement system using a binary defocusing technique[J]. Optics & Lasers in Engineering , 2013, 51(5):514-519.

CHEN X C, WANG Y W, WANG Y J, et al .. Quantized phase coding and connected region labeling for absolute phase retrieval[J]. Optics Express , 2016, 24(25): 28613.

WANG Y J, ZHANG S. Optimal fringe angle selection for digital fringe projection technique[J]. Applied Optics , 2013, 52(29): 7094.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

不连续相位跳变点的三维深度分割技术

融合条形注意力机制的电芯极片计算机断层图像分割

面向干涉包裹相位的多等级噪声抑制网络

增强型金枪鱼群优化指数熵的砂粒显微图像分割

语义流引导采样结合注意力机制的脑肿瘤图像分割