第一人称视角地形轮廓草图的真实空间重建

曾升; 耿国华; 邹林波; 周明全

doi:10.3788/OPE.20202808.1861

您当前的位置：

首页 >

文章列表页 >

第一人称视角地形轮廓草图的真实空间重建

信息科学 | 更新时间：2020-08-14

- 第一人称视角地形轮廓草图的真实空间重建
- Real spatial terrain reconstruction of first person point-of-view sketches
- 光学精密工程 2020年28卷第8期页码：1861-1871
- 作者机构：
  
  西北大学信息科学与技术学院, 陕西西安 710127
- 作者简介：
  
  [ "曾升(1986-), 男, 宁夏银川人, 博士研究生, 2008, 2011年于中南大学分别获得学士、硕士学位, 主要从事虚拟现实及计算机视觉方面的研究。E-mail:shengzeng@stumail.nwu.edu.cn" ]
  [ "周明全(1954-), 男, 陕西西安人, 教授, 博士生导师, 1976, 1988年于西北大学分别获得学士、硕士学位, 主要从事虚拟现实、可视化技术、智能信息处理等领域的理论及应用工程创新研究。E-mail:mqzhou@bnu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金资助项目(61672103);国家自然科学基金资助项目(61731015);国家自然科学基金资助项目(61673319);科技部重点研发计划资助项目(2017YFB1402100);陕西省重点产业链资助项目(2019ZDLSF07-02);陕西省重点产业链资助项目(2019ZDLGY10-01);陕西省重点产业创新链资助项目(2017ZDCXL-GY-03-01-01)
- DOI：10.3788/OPE.20202808.1861
  中图分类号： TP394.1;TH691.9
- 收稿日期：2020-03-23，
  
  修回日期：2020-05-29，
  
  录用日期：2020-5-29，
  
  纸质出版日期：2020-08-25
- 稿件说明：
移动端阅览
曾升, 耿国华, 邹林波, 等. 第一人称视角地形轮廓草图的真实空间重建[J]. 光学精密工程, 2020,28(8):1861-1871.

Sheng ZENG, Guo-hua GENG, Lin-bo ZOU, et al. Real spatial terrain reconstruction of first person point-of-view sketches[J]. Optics and precision engineering, 2020, 28(8): 1861-1871.
曾升, 耿国华, 邹林波, 等. 第一人称视角地形轮廓草图的真实空间重建[J]. 光学精密工程, 2020,28(8):1861-1871. DOI： 10.3788/OPE.20202808.1861.

Sheng ZENG, Guo-hua GENG, Lin-bo ZOU, et al. Real spatial terrain reconstruction of first person point-of-view sketches[J]. Optics and precision engineering, 2020, 28(8): 1861-1871. DOI： 10.3788/OPE.20202808.1861.

摘要

第一人称2D地形草图重建三维模型是具有挑战性的研究，由于缺失一维信息，多数研究都侧重于研究自由设计地形及提高真实感的地面纹理映射方法，却并未涉及更符合普通用户手绘的目的并遵循摄影几何规律的真实空间位置重建，本文提出手绘草图直接生成符合真实空间位置的三维模型生成方法。首先，遵循二维草图既定的形状规律、视觉遮挡关系，根据小孔成像规律构建相对深度关系；然后，通过采样不同深度层的轮廓数据点进行椭圆扩展来建立等高线图，周向采样点的分形插值来计算地形单元；接着通过旋转映射来实现空间地形单元的非刚性变形，从而实现第一人称视角下同一轮廓不同三维模型的构建；最后，加入柏林噪声以添加三维地形细节展示的随机效果。实验结果表明：在相同的二维草图透视下，可以构建具有不同真实空间位置的三维地形模型，与三种草图地形建模方法相比，解决了真实空间位置重建的问题。本文提出的方法更符合用户的设计目的，实现任意同一投影草图轮廓的三维地形真实空间重建，得到多层遮挡地形草图的多种真实空间位置布局，并能满足地形特征的展示，弥合了艺术意图与数字建模之间的鸿沟。

Abstract

It is challenging to reconstruct 3D terrain modelsbased on sketches drawn in the first-person pointofview. Owing to the lack of one-dimensional information

most studies focus on terrain-independent design and texture mapping methods to improve the realism; however

the spatial location is not considered in such methods.To address this limitation

we propose a methodto generate 3D modelsthat conform tothe real space position. First

based on the established shape rules and visual occlusion relation

the relative depth relationship is determined according to the geometric rules derived from photographs; then

a contour map is established by sampling the contour data points of different depth layers for ellipse expansion.Furthermore

the fractal interpolation of circumferential sampling points is performed to calculate terrain units

and the non-rigid deformation of spatial terrain elements is realized via rotation mapping. Finally

Berlin noise is added to improve the random effect of the 3D terrain display. Experimental results show that for the same 2D sketch perspective

3D terrain models corresponding todifferent real spatial locations can be constructed; in this regard

the proposed method is different from the other three methods.Furthermore

it solves the problem of real space location reconstruction. Our method is more suitable for expressing the intended design purpose of users.It realizes the 3D terrain real space reconstruction of any 2D sketch; moreover

it obtains a variety of real space layouts of multi-layer occlusion terrainsin addition to displayingthe terrain features

which bridges the gap between artistic intent and the actual result.

关键词

Keywords

references

CHOY C.B, XU D, GWAK J, et al . 3D-R2N2: A unified approach for single and multi-view 3D object reconstruction[C]. European Conference on Computer Vision , 2016.

A SAXENA , M SUN , A Y NG . Make3D:Learning 3D scene structure from a single still image . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2009 . 31 ( 5 ): 824 - 840 . DOI: 10.1109/TPAMI.2008.132 http://doi.org/10.1109/TPAMI.2008.132 .

NIU C, LI J, XU K. Im2Struct: Recovering 3D shape structure from a single RGB image[C]. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 4521-4529.

WU J, ZHANG C, ZHANG X, et al . Learning shape priors for single-view 3D completion and reconstruction[C]. Computer Vision-ECCV , 2018: 673-691.

P S WANG , C Y SUN , Y LIU , 等 . Adaptive O-CNN:A patch-based deep representation of 3D shapes . ACM Trans. Graph. , 2018 . 37 ( 6 ): 1 - 11 . http://cn.bing.com/academic/profile?id=14bc592a435bfa692d130a3a90cb9775&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=14bc592a435bfa692d130a3a90cb9775&encoded=0&v=paper_preview&mkt=zh-cn .

LIU C, YANG J, CEYLAN D, et al . PlaneNet: Piece-wise planar reconstruction from a single RGB image[C]. CVPR , 2018.

C LI , H PAN , Y LIU , 等 . BendSketch:Modeling freeform surfaces through 2D sketching . Acm Transactions on Graphics , 2017 . 36 ( 4 ): 125 http://cn.bing.com/academic/profile?id=a1bbfd67bc37689379579dac9840525a&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=a1bbfd67bc37689379579dac9840525a&encoded=0&v=paper_preview&mkt=zh-cn .

杨洪波 . CAD建模中的草图约束处理 . 光学精密工程 , 1995 . 3 ( 6 ): 18 - 22 . http://ope.lightpublishing.cn/thesisDetails?columnId=1714600&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1714600&Fpath=&index=-1&l=zh .

H B YANG . Sketch constraint processing in CAD modeling . Opt. Precision Eng. , 1995 . 3 ( 6 ): 18 - 22 . http://ope.lightpublishing.cn/thesisDetails?columnId=1714600&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1714600&Fpath=&index=-1&l=zh .

M EITZ , K HILDEBRAND , T BOUBEKEUR , 等 . An evaluation of descriptors for large-scale image retrieval from sketched feature lines . Computers and Graphics , 2010 . 34 ( 5 ): 482 - 498 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=507e8c78ca61af83f996f7cf21cbbe3d http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=507e8c78ca61af83f996f7cf21cbbe3d .

VOSS R.F. Fractals in Nature: From Characterization to Simulation [M]. In: Peitgen HO., Saupe D. (eds) The Science of Fractal Images. Springer, 1988.

H ZHOU , J SUN , G TURK , 等 . Terrain synthesis from digital elevation models . IEEE Transactions on Visualization and Computer Graphics , 2007 . 13 ( 4 ): 834 - 848 . http://cn.bing.com/academic/profile?id=4b7a53bdb0ad3c4a76132af70002e8da&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=4b7a53bdb0ad3c4a76132af70002e8da&encoded=0&v=paper_preview&mkt=zh-cn .

王莹 , 王延杰 , 周渝人 , 等 . 基于注入式仿真平台的自适应真实感地形生成算法 . 光学精密工程 , 2014 . 22 ( 12 ): 3419 - 3426 . http://ope.lightpublishing.cn/thesisDetails?columnId=2155302&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=2155302&Fpath=&index=-1&l=zh .

Y WANG , Y J WANG , Y R ZHOU , 等 . Real adaptive topography optimization algorithm based on injection simulation platform . Opt. Precision Eng. , 2014 . 22 ( 12 ): 3419 - 3426 . http://ope.lightpublishing.cn/thesisDetails?columnId=2155302&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=2155302&Fpath=&index=-1&l=zh .

B RUSNELL , D MOULD , M G ERAMIAN . Feature-rich distance-based terrain synthesis . The Visual Computer , 2009 . 25 ( 5-7 ): 573 - 579 . DOI: 10.1007/s00371-009-0332-6 http://doi.org/10.1007/s00371-009-0332-6 .

J E GAIN, P MARAIS, W STRA?ER. Terrain sketching[C]. The 2009 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games , 2009.

F P TASSE , J E GAIN , P MARAIS . Enhanced texture-based terrain synthesis on graphics hardware . Computer Graphics Foru , 2012 . 31 ( 6 ): 1959 - 1972 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=99104e4e35058d0080b30763b36ffa1b http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=99104e4e35058d0080b30763b36ffa1b .

F P TASSE , A EMILIEN , M P CANI , 等 . Feature-based terrain editing from complex sketches . Computers & Graphics , 2014 . 4 101 - 115 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=86a0ad953d38ff71fd39213dacda812d http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=86a0ad953d38ff71fd39213dacda812d .

V A D PASSOS, T IGARASHI. Landsketch: A first person point-of-view example-based terrain modeling approach[C]. In: International Symposium on Sketch-based Interfaces & Modeling , 2013.

M ARIYAN, D. MOULD. Terrain synthesis using curve networks[C]. In: Graphics Interface Conference , 2015.

K KETABCHI, A RUNIONS, F F SAMAVATI. 3D maquetter: Sketch-based 3D content modeling for digital earth[C]. In: International Conference on Cyberworlds , 2016: 415.

M Becher , M Krone , G Reina , 等 . Feature-based volumetric terrain generation . IEEE Transactions on Visualization and Computer Graphics , 2017 . 8 ( 99 ): 1 - 1 . http://cn.bing.com/academic/profile?id=0f359928536329858adc954353067e13&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=0f359928536329858adc954353067e13&encoded=0&v=paper_preview&mkt=zh-cn .

TALGORN, F. BELHADJ. Real-time sketch-based terrain generation[C]. Computer Graphics International , 2018: 13-18.

赵祚喜 , 冯荣 , 朱裕昌 , 等 . 空间点的多视图DLT三维定位 . 光学精密工程 , 2020 . 28 ( 1 ): 212 - 222 . http://ope.lightpublishing.cn/thesisDetails?columnId=2095778&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=2095778&Fpath=&index=-1&l=zh .

ZUO-XI ZHAO , RONG FENG , YU-CHANG ZHU , 等 . Multi-view DLT three-dimensional positioning method for spatial points . Opt. Precision Eng. , 2020 . 28 ( 1 ): 212 - 222 . http://ope.lightpublishing.cn/thesisDetails?columnId=2095778&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=2095778&Fpath=&index=-1&l=zh .

李云雷 , 张曦 , 屠大维 . 基于立体定向靶标的探针式多视场三维视觉测量系统 . 光学精密工程 , 2019 . 27 ( 1 ): 34 - 44 . http://ope.lightpublishing.cn/thesisDetails?columnId=1422635&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1422635&Fpath=&index=-1&l=zh .

YUN-LEI LI , XI ZHANG , DA-WEI TU . Probe-based multi-view field 3D vision measurement system based on three-dimensional orientation target . Opt. Precision Eng. , 2019 . 27 ( 1 ): 34 - 44 . http://ope.lightpublishing.cn/thesisDetails?columnId=1422635&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1422635&Fpath=&index=-1&l=zh .

于洋 , 朴燕 , 倪焱 , 等 . 基于ROS与三维点云图像的室内物体精准定位 . 液晶与显示 , 2019 . 34 ( 6 ): 598 - 604 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs201906010 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs201906010 .

YANG YU , YAN PIAO , YAN NI , 等 . Precise location of indoor objects based on ROS and point cloud images . Chinese Journal of Liquid Crystals and Displays , 2019 . 34 ( 6 ): 598 - 604 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs201906010 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs201906010 .

韩延祥 , 张志胜 , 戴敏 . 用于目标测距的单目视觉测量方法 . 光学精密工程 , 2011 . 19 ( 5 ): 1110 - 1117 . http://d.wanfangdata.com.cn/periodical/gxjmgc201105024 http://d.wanfangdata.com.cn/periodical/gxjmgc201105024 .

Y X HAN , Z S ZHANG , M DAI . Monocular vision system for distance measurement based on feature points . Opt. Precision Eng. , 2011 . 19 ( 5 ): 1110 - 1117 . http://d.wanfangdata.com.cn/periodical/gxjmgc201105024 http://d.wanfangdata.com.cn/periodical/gxjmgc201105024 .

GODARD, CLéMENT, MAC AODHA O, et al . Unsupervised Monocular Depth Estimation with Left-Right Consistency[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

CHU H, MA W C, URTASUN R, et al . SurfConv: Bridging 3D and 2D Convolution for RGBD Images[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2018.

BATTIATO S, CURTI S, CASCIA M L. Depth map generation by image classification[C]. Three-dimensional Image Capture & Applications VI. International Society for Optics and Photonics , 2004.

HA H, IM S, PARK J, et al . High-quality depth from uncalibrated small motion Clip[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2016.

刘东生 , 陈建林 , 费点 , 等 . 基于深度相机的大场景三维重建 . 光学精密工程 , 2020 . 28 ( 1 ): 234 - 243 . http://ope.lightpublishing.cn/thesisDetails?columnId=1496705&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1496705&Fpath=&index=-1&l=zh .

DONG-SHENG LIU , JIAN-LIN CHEN , DIAN FEI , 等 . Three-dimensional reconstruction of large-scale scene based on depth camera . Opt. Precision Eng. , 2020 . 28 ( 1 ): 234 - 243 . http://ope.lightpublishing.cn/thesisDetails?columnId=1496705&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1496705&Fpath=&index=-1&l=zh .

ZHOU, PENGBO, LI K, WEI W, et al . Fast generation method of 3d scene in chinese landscape painting[J]. Multimedia Tools & Applications. doi: org/10.1007/s11042-019-7476-9.20.2019 http://dx.doi.org/org/10.1007/s11042-019-7476-9.20.2019 .

BLOOMENTHAL, JULES, ROKNE, et al . Homogeneous coordinates[J]. Visual Computer , 425(1994) 15-26.

孙洪泉 . 《分形几何与分形插值》 , : 北京科学出版社 , 2011 .

HONG-QUAN SUN . Fractal Geometry and Fractal Interpolation , : Beijing Science Press , 2011 .

K PERLIN . Improving noise . Acm Transactions on Graphics , 2002 . 21 ( 3 ): 681 - 682 . DOI: 10.1145/566654.566636 http://doi.org/10.1145/566654.566636 .

D MATTPHARR , N G HUMPHREYS . Physically based Rendering , : San Francisco Morgan Kaufmann , 2010 .

浏览量

471

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于特征点的单目视觉测量方法