帮助 关于我们

返回检索结果

主动目标几何建模研究方法综述
Active geometric reconstruction methods for objects: a survey

查看参考文献46篇

孔研自 1,2,3,4,5   朱枫 1,2,4,5 *   郝颖明 1,2,4,5   吴清潇 1,2,4,5   鲁荣荣 1,2,3,4,5  
文摘 目的目标建模是机器视觉领域的主要研究方向之一,主动目标建模是在保证建模完整度的情况下,通过有计划地调节相机的位姿参数,以更少的视点和更短的运动路径实现目标建模的智能感知方法。为了反映主动目标建模的研究现状和最新进展,梳理分析了2004年以来的相关文献,对国内外研究方法做出概括性总结。方法以重构模型类型和规划视点所用信息作为划分依据,将无模型的主动目标建模方法分为基于表面的主动目标建模方法、基于搜索的目标建模方法和两者相结合的方法3大类,重点对前两类方法进行综述,首先解释了每类方法的基本思想,总结每类方法涉及的问题,然后对相关问题的主要研究方法进行归纳和分析,最后将各个问题的解决方法进行合理的搭配组合,形成不同的主动目标建模方法,并对各类方法的优势和局限性进行了总结。结果各类主动目标建模算法在适用场景范围、计算复杂度等方面存在差异,但相对于传统的被动目标建模方法,当前的主动目标建模算法已经能够极大程度地提高建模任务的质量和降低建模所需代价。结论基于表面的主动目标建模方法思想相对简单,但仅适用于表面简单的目标建模。基于搜索的目标建模方法能够量化地评价每一个候选视点,适用广泛且涉及的问题相对于基于表面的方法有更大的解决空间,有更多的研究成果产生。将二者涉及问题的不同研究方法相搭配,可以构成不同的主动目标建模方法子类。
其他语种文摘 Objective Target modeling is one of the main research directions in the field of machine vision,and this technology is widely used in various fields. When modeling the geometry of an object,the data obtained from one viewpoint are often incomplete,and large-area losses may even occur. Therefore,obtaining the information of the target from different viewpoints and fusing the information are necessary to achieve a complete geometric modeling of the target. Active object reconstruction is an intelligent perception method that achieves target modeling with few viewpoints and short motion paths by systematically adjusting the pose parameters of the camera while ensuring model integrity. To reflect the research status and latest development of active object reconstruction,relevant studies since 2004 are combed and analyzed,and a summary of domestic and foreign research methods is made. Method At present,active object reconstruction is mainly aimed at two task types: model-based and non-model active object reconstruction. Model-based methods pre-plan a series of viewpoints before modeling and can achieve full coverage of the target with high quality. Non-model methods have no information on the target at all,and view planning is performed in real time during modeling. In practical applications,the second category appears frequently and is difficult; thus,this study only summarizes non-model methods. On the basis of the rebuilt model type and the information used during view planning,non-model active object reconstruction methods are divided into three categories,namely,surface based,search based,and combined. The basic ideas of each type of method are explained,and the problems involved are summarized. Surface-based methods use point cloud and triangular patch models. They extract shape information from the obtained local model and classify the shape of the unknown region to determine the next viewpoint. Search-based methods use voxel models. A certain method is employed to determine the candidate viewpoints, and then these viewpoints are scored by a reasonable evaluation function. The candidate viewpoint with the highest score is used as the next best view. The combined method uses the surface and voxel models and merges the advantages of the two methods comprehensively to provide effective information for view planning. However,combined methods have not been investigated much recently,and the first two methods have mainly been the focus. Surface-based methods involve problems of detection direction determination,unknown surface prediction,and next-best viewpoint determination. Searchbased methods involve problems of model type selection,search space determination,undetected area prediction,and design of the evaluation function to sort candidate viewpoints.
来源 中国图象图形学报 ,2019,24(7):1017-1027 【核心库】
DOI 10.11834/jig.180607
关键词 主动目标建模 ; 主动视觉 ; 视点规划 ; 传感器规划 ; 智能感知
地址

1. 中国科学院沈阳自动化研究所, 沈阳, 110016  

2. 中国科学院机器人与智能制造创新研究院, 沈阳, 110016  

3. 中国科学院大学, 北京, 100049  

4. 中国科学院光电信息处理重点实验室, 中国科学院光电信息处理重点实验室, 沈阳, 110016  

5. 辽宁省图像理解与视觉计算重点实验室, 辽宁省图像理解与视觉计算重点实验室, 沈阳, 110016

语种 中文
文献类型 综述型
ISSN 1006-8961
学科 自动化技术、计算机技术
基金 国家自然科学基金项目 ;  机器人学重点实验室自主课题项目 ;  国防科技创新特区项目
文献收藏号 CSCD:6532057

参考文献 共 46 共3页

1.  Fan H Q. A point set generation network for 3D object reconstruction from a single image. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition,2017:1-6 被引 1 次    
2.  梅峰. 基于RGB-D深度相机的室内场景重建. 中国图象图形学报,2015,20(10):1366-1373 被引 6 次    
3.  何炳蔚. 混合视觉系统中共同视场的确定与3维重建方法. 机器人,2011,33(5):614-620 被引 2 次    
4.  Lin C H. Learning efficient point cloud generation for dense 3D object reconstruction. Proceedings of the 32nd AAAI Conference on Artificial Intelligence,2018:7114-7121 被引 2 次    
5.  Choy C B. 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. Proceedings of the 14th European Conference on Computer Vision,2016:628-644 被引 6 次    
6.  Lun Z L. 3D shape reconstruction from sketches via multi-view convolutional networks. Proceedings of 2017 International Conference on 3D Vision,2017:67-77 被引 1 次    
7.  Chou H L. A quality controllable multi-view object reconstruction method for 3D imaging systems. Journal of Visual Communication and Image Representation,2010,21(5/6):427-441 被引 1 次    
8.  Connolly C. The determination of next best views. Proceedings of 1985 IEEE International Conference on Robotics and Automation,1985:432-435 被引 12 次    
9.  Aloimonos J. Active vision. International Journal of Computer Vision,1988,1(4):333-356 被引 3 次    
10.  Jing W. Sampling-based view planning for 3D visual coverage task with unmanned aerial vehicle. Proceedings of 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems,2016:1808-1815 被引 1 次    
11.  Hepp B. Plan3D: viewpoint and trajectory optimization for aerial multi-view stereo reconstruction. ACM Transactions on Graphics,2018,38(1):1-31 被引 1 次    
12.  Kaba M D. A reinforcement learning approach to the view planning problem. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition,2017:5094-5102 被引 1 次    
13.  Scott W. View planning for automated threedimensional object reconstruction and inspection. ACM Computing Surveys,2003,35(1):64-96 被引 15 次    
14.  Chen S Y. Active vision in robotic systems: a survey of recent developments. The International Journal of Robotics Research,2011,30(11):1343-1377 被引 4 次    
15.  何炳蔚. 一种具有自终止特性的视点规划方法. 中国图象图形学报,2006,11(12):1827-1833 被引 1 次    
16.  何炳蔚. 线激光三维测量仪中视觉传感器规划方法研究. 中国激光,2010,37(6):1618-1625 被引 8 次    
17.  Fang W. Automatic view planning for 3D reconstruction and occlusion handling based on the integration of active and passive vision. Proceedings of 2012 IEEE International Symposium on Industrial Electronics,2012:1116-1121 被引 2 次    
18.  黄立平. 基于机器人视觉伺服的确定下一最优视点的方法研究. 工业仪表与自动化装置,2015(2):7-11 被引 1 次    
19.  姚兴田. 自动3维重构中确定下一最优视点的方法研究. 江西师范大学学报:自然科学版,2013,37(6):569-573 被引 1 次    
20.  Scott W R. Model-based view planning. Machine Vision and Applications,2009,20(1):47-69 被引 11 次    
引证文献 1 篇

1 曹林 一种基于倾斜影像线特征的三维模型优化方法 南京航空航天大学学报,2020,52(6):980-988
被引 0 次

显示所有1篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号