过眼春光久已空,晒丝捣麦又匆匆。——(宋)陆游《夏日》
EVO工具用于评估SLAM算法在现有数据集上的效果。源码在 https://github.com/MichaelGrupp/evo。目前支持 TUM KITTI Euroc 等格式。evo工具提供了3种误差评估方式:
evo_ape
-absoulte pose errorevo_rpe
-relative pose errorevo_rpe
-for-each -sub-sequence-wise averaged pose error
4种工具:
evo_traj
- tool for analyzing, plotting or exporting one or more trajectoriesevo_res
- tool for comparing one or multiple result files from evo_ape or evo_rpeevo_fig
- (experimental) tool for re-opening serialized plots (saved with –serialize_plot)evo_config
- tool for global settings and config file manipulation
本文以VINS为例子介绍如何使用evo评估其在Euroc数据集上的效果。数据集网站: