一种基于2D和3DSIFT特征级融合的一般物体识别算法

doi:10.3969/j.issn.0372-2112.2015.11.021

电子学报 ›› 2015, Vol. 43 ›› Issue (11): 2277-2283.DOI: 10.3969/j.issn.0372-2112.2015.11.021

一种基于2D和3DSIFT特征级融合的一般物体识别算法

李新德¹, 刘苗苗¹, 徐叶帆¹, 雒超民²

1. 东南大学自动化学院复杂工程测量与控制教育部重点实验室, 江苏南京 210096;
2. 底特律大学电子与计算机工程系, 美国底特律 48221

收稿日期:2015-01-08 修回日期:2015-06-02 出版日期:2015-11-25
- 通讯作者:
- 李新德
- 作者简介:
- 刘苗苗 女,1990年2月出生,河南安阳人.东南大学自动化学院硕士研究生.主要研究方向为模式识别与分类.E-mail:374561475@qq.com
- 基金资助:
- 国家自然科学基金 (No.60804063,No.61175091); 航空基金 (No.20140169002); 江苏省"青蓝工程"资助计划; 江苏省"六大高峰人才"资助计划

A Recognition Algorithm of Generic Objects Based on Feature-Level Fusion of 2D and 3D SIFT Descriptors

LI Xin-de¹, LIU Miao-miao¹, XU Ye-fan¹, LUO Chao-min²

1. Ministry of Education Key Laboratory of Measurement and Control, School of Automation, Southeast University, Nanjing, Jiangsu 210096, China;
2. Department of Electrical and Computer Engineering, University of Detroit Mercy, Detroit, Michigan 48221, USA

Received:2015-01-08 Revised:2015-06-02 Online:2015-11-25 Published:2015-11-25

摘要/Abstract

摘要：

如何选择合适的特征表示一般物体类间差异和类内共性至关重要,因此,本文在2D SIFT(Scale Invariant Feature Transform,SIFT)的基础上,提出了基于点云模型的3D SIFT特征描述子,进而提出一种基于2D和3D SIFT特征级融合的一般物体识别算法.分别提取物体2维图像和3维点云的2D和3D SIFT特征描述子,利用"词袋"(Bag of Words,BoW)模型得到物体特征向量,根据特征级融合将两个特征向量进行融合实现物体描述,运用有监督分类器支持向量机(Support Vector Machine,SVM)实现分类识别,给出最终识别结果.最后,实验验证了本文提出算法的好处.

关键词: 一般物体识别, 点云, 2D SIFT, 3D SIFT, 特征融合, BoW模型, SVM分类器

Abstract:

How to choose the appropriate feature to represent differences between classes and the common within class of generic objects is of great importance.So the 3D SIFT(scale invariant feature transform) descriptors of point clouds model based on the 2D SIFT is proposed.Then we propose a new algorithm based on multiple feature fusion of 2D and 3D SIFT descriptors respectively drawn from 2D images and 3D point clouds.The BoW(bag of words) model is used to calculate feature vectors and describe the objects according to the multiple feature fusion.The supervised support vector machine(SVM) classier is used to classify objects.Through several experiments,the advantage of this new algorithm is testified.

Key words: generic object recognition, point cloud, 2D SIFT, 3D SIFT, feature fusion, BoW, SVM

中图分类号:

TP391.4

李新德, 刘苗苗, 徐叶帆, 雒超民. 一种基于2D和3DSIFT特征级融合的一般物体识别算法[J]. 电子学报, 2015, 43(11): 2277-2283.

LI Xin-de, LIU Miao-miao, XU Ye-fan, LUO Chao-min. A Recognition Algorithm of Generic Objects Based on Feature-Level Fusion of 2D and 3D SIFT Descriptors[J]. Acta Electronica Sinica, 2015, 43(11): 2277-2283.

参考文献

[1] Rusu R B,Blodow N,Marton Z C,Beetz M.Aligning point cloud views using persistent feature histograms[A]. Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems[C]. Nice,France:IEEE,2008.3384-3391.
[2] Rusu R B,Blodow N,Beetz M.Fast point feature histograms(FPFH) for 3D registration[A]. Proceedings of IEEE International Conference on Robotics and Automation[C]. Kobe,Japan:IEEE,2009.3212-3217.
[3] Lazebnik S,Schmid C,Ponce J.A sparse texture representation using local affine regions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(8):1265-1278.
[4] Alexandre L A.3D descriptors for object and category recognition:a comparative evaluation[A]. Proceedings of IEEE International Conference on Intelligent Robotic Systems(Vol Workshop on Color-Depth Camera Fusion in Robotics)[C]. Vilamoura,Portugal:IEEE,2012.1-6.
[5] 陈北京,王蔚,宋加涛,任小波.一种融合二值边缘特征和灰度特征的人脸识别方法[J]. 电子学报,2009,37(6):1180-1184. Chen Bei-jing,Wang Wei,Song Jia-tao,Ren Xiao-bo.A novel face recognition method based on the fusion of binary edge and grayscale features[J]. Acta Electronica Sinica,2009,37(6):1180-1184.(in Chinese)
[6] 李新德,潘锦东,Dezert Jean.一种基于DSmT和HMM 的序列飞机目标识别算法[J]. 自动化学报,2014,40(12):2862-2876. Li Xin-de,Pan Jin-dong,Dezert Jean.A target recognition algorithm for sequential aircraft based on DSmT and HMM[J]. Acta Automatica Sinica,2014,40(12):2862-2876.(in Chinese)
[7] Bo L,Lai K,Ren X,Fox D.Object recognition with hierarchical kernel descriptors[A]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C]. CO,USA:Colorado Springs,2011.1729-1736.
[8] Bo L,Ren X,Fox D.Depth kernel descriptors for object recognition[A]. Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems[C]. San Francisco,CA,USA:IEEE,2011.821-826.
[9] Janoch A,Karayev S,Jia Y,Barron J T,Fritz M,Saenko K,Darrell T.A category-level 3-D object dataset:putting the kinect to work[A]. 2011 IEEE International Conference on Computer Vision Workshops(ICCV Workshops)[C]. Barcelona,Spanish:IEEE,2011.1168-1174.
[10] Mirdanies M,Prihatmanto A S,Rijanto E.Object recognition system in remote controlled weapon station using SIFT and SURF methods[J]. Mechatronics,Electrical Power,and Vehicular Technology,2013,4(2):99-108.
[11] Lowe D G.Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision,2004,60(2):91-110.
[12] Allaire S,Kim J J,Breen S L,Jaffray D A,Pekar V.Full orientation invariance and improved feature selectivity of 3D SIFT with application to medical image analysis[A]. Proceedings of 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops[C]. Anchorage,AK:IEEE,2008.1-8.
[13] Sivic J,Zisserman A.Video Google:a text retrieval approach to object matching in videos[A]. Proceedings of 9th IEEE International Conference on Computer Vision[C]. Nice,France:IEEE,2003.1470-1477.
[14] Arthur D,Vassilvitskii S.k-means++:The advantages of careful seeding[A]. Proceedings of the 18th annual ACM-SIAM symposium on discrete algorithms[C]. PA,USA:Society for Industrial and Applied Mathematics,2007.1027-1035.
[15] Lai K,Bo L,Ren X,Fox D.RGB-D dataset[DB]. http://rgbd-dataset.cs.washington.edu/dataset.html,2011-03-05.
[16] Rusu R B,Cousins S.3D is here:point cloud library(pcl)[A]. Proceedings of 2011 IEEE International Conference on Robotics and Automation[C]. Shanghai,China:IEEE,2011.1-4.
[17] Dezert J.Foundations for a new theory of plausible and paradoxical reasoning[J]. Information and Security,2002,9:13-57.
[18] 李新德,Dezert Jean,黄心汉,孟正大,吴雪建.一种快速分层递阶DSmT近似推理融合方法(A)[J]. 电子学报,2010,38(11):2566-2572. Li Xin-de,Dezert Jean,Huang Xin-han,Meng Zheng-da,Wu Xue-jian.A fast approximate reasoning method in hierarchical DSmT(A)[J]. Acta Electronica Sinica,2010,38(11):2566-2572.(in Chinese)
[19] Murphy C K.Combining belief functions when evidence conflicts[J]. Decision Support Systems,2000,29(1):1-9.

一种基于2D和3DSIFT特征级融合的一般物体识别算法

A Recognition Algorithm of Generic Objects Based on Feature-Level Fusion of 2D and 3D SIFT Descriptors

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	琚长瑞, 秦晓燕, 袁广林, 李豪, 朱虹. 尺度敏感损失与特征融合的快速小目标检测方法[J]. 电子学报, 2022, 50(9): 2119-2126.
[2]	王飞扬, 冀鹏欣, 孙笠, 危倩, 李根, 张忠宝. 一种基于深度学习的动态社交网络用户对齐方法[J]. 电子学报, 2022, 50(8): 1925-1936.
[3]	李超, 黄新宇, 王凯. 基于特征融合和自学习锚框的高分辨率图像小目标检测算法[J]. 电子学报, 2022, 50(7): 1684-1695.
[4]	彭闯, 王伦文, 胡炜林. 融合深度特征的电磁频谱异常检测算法[J]. 电子学报, 2022, 50(6): 1359-1369.
[5]	肖进胜, 张舒豪, 陈云华, 王元方, 杨力衡. 双向特征融合与特征选择的遥感影像目标检测[J]. 电子学报, 2022, 50(2): 267-272.
[6]	魏博文, 全红艳. 基于语义与形态特征融合的语义分割网络[J]. 电子学报, 2022, 50(11): 2688-2697.
[7]	杨创艳, 马军, 王晓东, 罗亭, 李卓睿. 特征融合与灰色回归的滚动轴承性能退化评估[J]. 电子学报, 2022, 50(1): 106-115.
[8]	赵琰, 赵凌君, 匡纲要. 基于注意力机制特征融合网络的SAR图像飞机目标快速检测[J]. 电子学报, 2021, 49(9): 1665-1674.
[9]	席亮, 刘涵, 樊好义, 张凤斌. 基于深度对抗学习潜在表示分布的异常检测模型[J]. 电子学报, 2021, 49(7): 1257-1265.
[10]	杨红红, 王刘丽, 张玉梅, 吴晓军, 党允彤. 基于序列多尺度特征融合表示的层级舞蹈动作姿态估计方法[J]. 电子学报, 2021, 49(12): 2428-2436.
[11]	黎毅达, 高发荣, 姚婷, 蔡利杰. 基于Fisher判别和GKF-RELM算法的多特征步态模式识别[J]. 电子学报, 2021, 49(10): 1993-2001.
[12]	黄鸿, 徐科杰, 石光耀. 联合多尺度多特征的高分遥感图像场景分类[J]. 电子学报, 2020, 48(9): 1824-1833.
[13]	程晓涛, 吉立新, 尹赢, 黄瑞阳. 基于D-S证据理论的网络表示融合方法[J]. 电子学报, 2020, 48(5): 854-860.
[14]	杨珂, 王敬宇, 戚琦, 孙海峰, 王晶, 廖建新. LSCN:一种用于动作识别的长短时序关注网络[J]. 电子学报, 2020, 48(3): 503-509.
[15]	李雅倩, 盖成远, 肖存军, 吴超, 刘佳甲. 基于细化多尺度深度特征的目标检测网络[J]. 电子学报, 2020, 48(12): 2360-2366.