GENERIC OBJECT RECOGNITION BASED ON FEATURE FUSION IN ROBOT PERCEPTION

被引：4

作者：

Li, Xinde ^{[1
]}

Luo, Chaomin ^{[2
]}

Dezert, Jean ^{[3
]}

Tan, Yingzi ^{[1
]}

机构：

[1] Southeast Univ, Sch Automat, Minist Educ, Key Lab Measurement & Control,CSE, Nanjing 210096, Jiangsu, Peoples R China

[2] Univ Detroit Mercy, ECE Dept, Detroit, MI 48221 USA

[3] French Aerosp Lab, F-91761 Palaiseau, France

来源：

INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION | 2016年 / 31卷 / 05期

关键词：

Generic object recognition; Point cloud; SIFT; Feature fusion; SVM; belief functions;

D O I：

10.2316/Journal.206.2016.5.206-4706

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A new generic object recognition (GOR) method for robot perception is proposed in this paper, based on multi-feature fusion of two-dimensional (2D) and 3D scale invariant feature transform descriptors drawn from 2D images and 3D point clouds. The trained support vector machine is utilized to construct multi-category classifiers that recognize the objects. According to our results, this new GOR approach achieves higher recognition rates than classical methods tested, even when one has large intra-class variations, or high inter-class similarities of the objects. Simulation results demonstrate the effectiveness and efficiency of the proposed GOR approach.

引用

页码：409 / 415

页数：7

共 50 条

[1] Generic object recognition based on feature fusion in robot perception
[J]. 1600, Acta Press, Building B6, Suite 101, 2509 Dieppe Avenue S.W., Calgary, AB, T3E 7J9, Canada (31):
[2] An object recognition approach based on feature fusion
Wang, RS
[J]. OBJECT DETECTION, CLASSIFICATION, AND TRACKING TECHNOLOGIES, 2001, 4554 : 1 - 8
[3] Feature-fusion based object tracking for robot platforms
Zhang, Xuguang
Liu, Honghai
Wang, Yanjie
[J]. INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION, 2011, 38 (01): : 66 - 75
[4] Shape of Object Recognition Based on Information Fusion for Intelligent Robot
Liu, Shuang
Li, Pengwei
[J]. PROCEEDINGS 2013 INTERNATIONAL CONFERENCE ON MECHATRONIC SCIENCES, ELECTRIC ENGINEERING AND COMPUTER (MEC), 2013, : 1288 - 1291
[5] Weak Metric Learning for Feature Fusion towards Perception-Inspired Object Recognition
Li, Xiong
Zhao, Xu
Fu, Yun
Liu, Yuncai
[J]. ADVANCES IN MULTIMEDIA MODELING, PROCEEDINGS, 2010, 5916 : 273 - +
[6] Visual Perception based Adaptive Feature Fusion for Visual Object Tracking
Krieger, Evan
Asari, Vijayan K.
[J]. 2017 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2017, : 1345 - 1350
[7] Video object segmentation based on dynamic perception update and feature fusion
Hou, Zhiqiang
Li, Fucheng
Dong, Jiale
Dai, Nan
Ma, Sugang
Fan, Jiulun
[J]. IMAGE AND VISION COMPUTING, 2024, 150
[8] Affordance-based 3D Feature for Generic Object Recognition
Iizuka, M.
Akizuki, S.
Hashimoto, M.
[J]. THIRTEENTH INTERNATIONAL CONFERENCE ON QUALITY CONTROL BY ARTIFICIAL VISION 2017, 2017, 10338
[9] Robot Robust Object Recognition based on Fast SURF Feature Matching
Du, Mingfang
Wang, Junzheng
Li, Jing
Cao, Haiqing
Cui, Guangtao
Fang, Jianjun
Lv, Ji
Chen, Xusheng
[J]. 2013 CHINESE AUTOMATION CONGRESS (CAC), 2013, : 581 - 586
[10] Small Object Recognition Algorithm Based on Hybrid Control and Feature Fusion
Zhu, Gaofeng
Wang, Zhixue
Zhu, Fenghua
Xiong, Gang
Li, Zheng
[J]. IEEE JOURNAL OF RADIO FREQUENCY IDENTIFICATION, 2024, 8 : 484 - 492

← 1 2 3 4 5 →