hku-mars / FAST_LIO

A computationally efficient and robust LiDAR-inertial odometry (LIO) package
GNU General Public License v2.0
2.78k stars 936 forks source link

精度评估 #217

Closed forcazzx closed 1 year ago

forcazzx commented 1 year ago

请问论文中的绝对平移误差rmse是怎么评估的呢? 我下载了源码之后运行了nclt数据集,并用evo_ape评估了绝对平移误差rmse值,发现普遍比论文中给出的误差小,例如nclt9(20130110)这组,论文中给出的误差在5m左右,但是本地跑出来的误差为0.99m。

forcazzx commented 1 year ago

这是运行的配置文件 image

stale[bot] commented 1 year ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

duanxz0127 commented 10 months ago

请问论文中的绝对平移误差rmse是怎么评估的呢? 我下载了源码之后运行了nclt数据集,并用evo_ape评估了绝对平移误差rmse值,发现普遍比论文中给出的误差小,例如nclt9(20130110)这组,论文中给出的误差在5m左右,但是本地跑出来的误差为0.99m。

请问你找到原因了吗?我计算出的nclt9(20130110)这组ATE也是0.9m

hr2894235132 commented 10 months ago

这是运行的配置文件 image

您好,想问一下你NCLT的真值是怎么得到的呢?我下载的时间戳好像不对