计算机科学 ›› 2021, Vol. 48 ›› Issue (6A): 127-131.doi: 10.11896/jsjkx.200800035
袁晓磊, 岳晓峰, 方博, 马国元
YUAN Xiao-lei, YUE Xiao-feng, FANG Bo, MA Guo-yuan
摘要： 针对基于原始点对特征的三维目标识别算法中存在的效率低、易受干扰的问题,提出了一种分层全连接聚类算法来对三维目标进行识别。利用模型上的所有点对特征来完成全局模型的描述构建,并在局部坐标的二维空间上,利用投票方案和分层全连接聚类算法对候选位姿进行筛选,从而获得最优位姿。在UWA的数据集上的实验结果表明,与原始点对特征算法相比,所提出的分层全连接聚类算法在识别率和效率上都有一定程度的提升,并且该方法满足实用性和有效性要求。
中图分类号:
| [1] DROST B,ULRICH M,NAVAB N,et al.Model globally,match locally:Efficient and robust 3D object recognition[C]//ComputerVision & Pattern Recognition.IEEE,2010. [2] KIM E,MEDIONI G G.3D object recognition in range images using visibility context[C]//IEEE/RSJ International Confe-rence on Intelligent Robots & Systems.IEEE,2011. [3] DROST B,ILIC S.3D Object Detection and Localization Using Multimodal Point Pair Features[C]//2012 Second International Conference on 3d Imaging,Modeling,Processing,Visualization &Ttransmission.IEEE,2012:9-16. [4] CHOI C,TAGUCHI Y,TUZEL O,et al.Voting-based pose estimation for robotic assembly using a 3D sensor[C]//IEEE International Conference on Robotics & Automation.IEEE,2013:1724-1731. [5] CHOI C,TREVOR A J,CHRISTENSEN H I,et al.RGB-Dedge detection and edge-based registration[C]//2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.IEEE,2013:1568-1575. [6] TEJANI A,TANG D,KOUSKOURIDAS R,et al.Latent-Class Hough Forests for 3D Object Detection and Pose Estimation[C]//European Conference on Computer Vision.Cham:Sprin-ger,2014:462-477. [7] BIRDAL T,ILIC S.Point Pair Features Based Object Detection and Pose Estimation Revisited[C]//International Conference on 3d Vision.IEEE,2015:527-535. [8] HINTERSTOISSER S,LEPETI V,RAJKUMAR N,et al.Going Further with Point Pair Features[C]//European Conference on Computer Vision.Cham:Springer,2016:834-848. [9] DIYI L,SHOGO A,JIAQI M,et al.Point Pair Feature-Based Pose Estimation with Multiple Edge Appearance Models (PPF-MEAM) for Robotic Bin Picking[J].Sensors,2018,18(8):2719-2738. [10] YI J,LI X,YI H C,et al.3D Point Cloud Matching Algorithm Based on Point Pair Feature[J].Transducer and Microsystem Technologies,2019,38(9):115-117. [11] XIAO Z,GAO J,WU D,et al.A fast 3D object Recognition Algorithm Using Plane-constrained Point Pair Features[J].Multimedia Tools and Applications,2020,79(4):1-21. [12] GRA F.Clustering Algorithm Studies[C]//Aip Conference Proceedings.American Institute of Physics,2001. [13] XU R,WUNSCH D I.Survey of Clustering Algorithms[J].IEEE Trans Neural Netw,2005,16(3):645-678. [14] HKWEDLO W.Parallelizing Evolutionary Algorithms for Clustering Data[M]//Parallel Processing and Applied Mathematics.Springer Berlin Heidelberg,2005. [15] ROKACH L,MAIMON O.Clustering Methods[J].Data Mining &Knowledge Discovery Handbook,2005,3(3):321-352. [16] ALINIYA Z,MIRROSHANDEL S A.A Novel CombinatorialMerge-Split Approach for Automatic Clustering UsingImperia-list Competitive Algorithm[J].Expert Systems with Applications,2018,117(5):243-266. [17] HUYNH D Q.Metrics for 3D Rotations:Comparison and Ana-lysis[J].Journal of Mathematical Imaging & Vision,2009,35(2):155-164. [18] MIAN A S,BENNAMOUN M,OWENS R.Three-Dimensional Model-Based Object Recognition and Segmentation in Cluttered Scenes[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2006,28(10):1584-1601. |
| [1] | 郝强, 李杰, 张曼, 王路. 基于改进YOLOv3的空间非合作目标部件识别算法 Spatial Non-cooperative Target Components Recognition Algorithm Based on Improved YOLOv3 计算机科学, 2022, 49(6A): 358-362. https://doi.org/10.11896/jsjkx.210700048 |
| [2] | 乔梦雨, 王鹏, 吴娇, 张宽. 面向陆战场目标识别的轻量级卷积神经网络 Lightweight Convolutional Neural Networks for Land Battle Target Recognition 计算机科学, 2020, 47(5): 161-165. https://doi.org/10.11896/jsjkx.190300062 |
| [3] | 吴刚,徐利敏. 目标形状表达算法综述 Review of Shape Representation for Objects 计算机科学, 2019, 46(7): 30-37. https://doi.org/10.11896/j.issn.1002-137X.2019.07.005 |
| [4] | 程栋,王卫红. OpenMP多核计算技术在SAR图像处理中的应用 Application of OpenMP in SAR Image Processing 计算机科学, 2017, 44(Z6): 161-163. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.037 |
| [5] | 刘涛,吴泽民,姜青竹,曾明勇,彭韬频. 基于似物性的快速视觉目标识别算法 Fast Object Recognition Method Based on Objectness 计算机科学, 2016, 43(7): 73-76. https://doi.org/10.11896/j.issn.1002-137X.2016.07.012 |
| [6] | 皮嘉立,巫正中,陈卓. 基于Adaboost-CSHG的特定类目标跟踪识别 Specific Target Tracking and Recognition Based on Adaboost-CSHG 计算机科学, 2016, 43(4): 318-321. https://doi.org/10.11896/j.issn.1002-137X.2016.04.065 |
| [7] | 薛爱军,王晓丹,宋亚飞,雷蕾. 基于移动散射点模型的雷达回波仿真及分析 Simulation and Analysis of Radar Echo Based on Moving Scattering Center Model 计算机科学, 2013, 40(9): 201-203. |
| [8] | 高晶,吴昆,吴育峰,陈仲华. 一种基于图像灰度的红外目标识别算法 Infrared Target Recognition Algorithm Based on Image Grayscale 计算机科学, 2013, 40(9): 312-316. |
| [9] | 孙 源，陈 靖. 智能手机的移动增强现实技术研究 Mobile Augmented Reality Technology Applied on Mobile Phone Platform 计算机科学, 2012, 39(Z6): 493-498. |
| [10] | 陈雪松，徐学军，朱洪波. 基于图像势能理论的目标轮廓特征提取方法 Research on Target Contour Feature Extraction Based on Image Potential Energy Theory 计算机科学, 2011, 38(6): 270-274. |
| [11] | 王燕清，陈德运，石朝侠，刘泊，房国志. 基于一种新的目标识别的边缘爬行算法 Object Recognition Based on a New Method of Edge Crawling 计算机科学, 2010, 37(8): 266-269272. |
| [12] | 刘玮,陈新武,田金文. 目标语义概率模型在类目标识别和地物场景分析中的算法研究 Object Semantic Probabilistic Model and its Application in Category Object Recognition and Scene Analysis 计算机科学, 2009, 36(7): 273-277. https://doi.org/10.11896/j.issn.1002-137X.2009.07.067 |
| [13] | . 基于聚类分析和集成神经网络的序列图像多目标识别算法 计算机科学, 2009, 36(3): 215-219. |
| [14] | 李海涛,吴培良,孔令富. 目标主色集结合SIFT的彩色目标快速识别 Combining ODCS and SIFT for Fast Color Object Identification 计算机科学, 2009, 36(12): 257-258. |
| [15] | 魏丽 吴中福 李云 古毅. 感知归类在目标识别中的应用研究 计算机科学, 2006, 33(5): 238-240. |
|
||
首页