Benchmarking visual SLAM methods in mirror environments  

作　　者：Peter Herbert Jing Wu Ze Ji Yu-Kun Lai 

机构地区：[1]School of Computer Science and Informatics,Cardiff University,Abacws Building,Senghennydd Rd,Cardiff CF244AG,UK [2]School of Engineering,Cardiff University,Queen’s Buildings,The Parade,Cardiff CF243AA,UK

出　　处：《Computational Visual Media》2024年第2期215-241,共27页计算可视媒体（英文版）

基　　金：funded by the UK EPSRC through a Doctoral Training Partnership No.EP/T517951/1(2435656).

摘　　要：Visual simultaneous localisation and mapping(vSLAM)finds applications for indoor and outdoor navigation that routinely subjects it to visual complexities,particularly mirror reflections.The effect of mirror presence(time visible and its average size in the frame)was hypothesised to impact localisation and mapping performance,with systems using direct techniques expected to perform worse.Thus,a dataset,MirrEnv,of image sequences recorded in mirror environments,was collected,and used to evaluate the performance of existing representative methods.RGBD ORB-SLAM3 and BundleFusion appear to show moderate degradation of absolute trajectory error with increasing mirror duration,whilst the remaining results did not show significantly degraded localisation performance.The mesh maps generated proved to be very inaccurate,with real and virtual reflections colliding in the reconstructions.A discussion is given of the likely sources of error and robustness in mirror environments,outlining future directions for validating and improving vSLAM performance in the presence of planar mirrors.The MirrEnv dataset is available at https://doi.org/10.17035/d.2023.0292477898.

关 键 词：visual simultaneous localisation and mapping(vSLAM) MIRROR LOCALISATION MAPPING REFLECTION datase 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]