A comparative evaluation of interest point detectors and local descriptors for visual SLAM

被引:112
作者
Gil, Arturo [1 ]
Martinez Mozos, Oscar [2 ]
Ballesta, Monica [1 ]
Reinoso, Oscar [1 ]
机构
[1] Miguel Hernandez Univ, Dept Ind Syst Engn, Elche, Spain
[2] Univ Freiburg, Dept Comp Sci, Freiburg, Germany
关键词
Interest point detectors; Local descriptors; Visual landmarks; Visual SLAM;
D O I
10.1007/s00138-009-0195-x
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we compare the behavior of different interest point detectors and descriptors under the conditions needed to be used as landmarks in vision-based simultaneous localization and mapping (SLAM). We evaluate the repeatability of the detectors, as well as the invariance and distinctiveness of the descriptors, under different perceptual conditions using sequences of images representing planar objects as well as 3D scenes. We believe that this information will be useful when selecting an appropriate landmark detector and descriptor for visual SLAM.
引用
收藏
页码:905 / 920
页数:16
相关论文
共 31 条
[1]  
[Anonymous], 2006, P 9 EUR C COMP VIS 1
[2]  
[Anonymous], ALV VIS C
[3]  
[Anonymous], IJCAI WORKSH REAS UN
[4]  
[Anonymous], INT C COMP VIS
[5]  
[Anonymous], IEEE COMP SOC C COMP
[6]  
ARRAS KO, 2003, THESIS SWISS FEDERAL
[7]  
BIBER P, 2004, IEEE RSJ INT C INT R
[8]   Simultaneous localization and map-building using active vision [J].
Davison, AJ ;
Murray, DW .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (07) :865-880
[9]  
EUSTICE R, 2005, IEEE INT C ROB AUT
[10]  
Gil A., 2006, IEEE RSJ INT C INT R