Two novel real-time local visual features for omnidirectional vision

被引：23

作者：

Lu, Huimin ^{[1
]}

Zheng, Zhiqiang ^{[1
]}

机构：

[1] Natl Univ Def Technol, Dept Automat Control, Coll Mechatron Engn & Automat, Changsha, Hunan, Peoples R China

来源：

PATTERN RECOGNITION | 2010年 / 43卷 / 12期

关键词：

Local visual feature; Omnidirectional vision; FAST; LBP; CS-LBP; Feature detector; Feature descriptor; LOCALIZATION; SCALE;

D O I：

10.1016/j.patcog.2010.06.020

中图分类号：

TP18 [人工智能理论];

学科分类号：

140502 [人工智能];

摘要：

Two novel real-time local visual features, namely FAST+LBP and FAST+CSLBP, are proposed in this paper for omnidirectional vision. They combine the advantages of two computationally simple operators by using FAST as the feature detector, and LBP and CS-LBP operators as feature descriptors. The matching experiments of the panoramic images from the COLD database were performed to determine their optimal parameters, and to evaluate and compare their performance with SIFT. The experimental results show that our algorithms perform better, and features can be extracted in real-time. Therefore, our local visual features can be applied to those computer/robot vision tasks with high real-time requirements. (C) 2010 Elsevier Ltd. All rights reserved.

引用

页码：3938 / 3949

页数：12

共 42 条

[1]

Abdel-Hakim A. E., 2006, P IEEE COMP SOC C CO, V2, P1978, DOI DOI 10.1109/CVPR.2006.95

[2]

Face description with local binary patterns:: Application to face recognition [J].