作者: Arturo Gil , Oscar Martinez Mozos , Monica Ballesta , Oscar Reinoso
DOI: 10.1007/S00138-009-0195-X
关键词:
摘要: In this paper we compare the behavior of different interest point detectors and descriptors under conditions needed to be used as landmarks in vision-based simultaneous localization mapping (SLAM). We evaluate repeatability detectors, well invariance distinctiveness descriptors, perceptual using sequences images representing planar objects 3D scenes. believe that information will useful when selecting an appropriate landmark detector descriptor for visual SLAM.