Interior Points to Plane Error

Created by: All Camera-LiDAR pairs (optional)

Overview

Interior Points to Plane error reflects the error in fit between the LiDAR points observed on the surface of a circular target, and the actual target. Unlike other metrics, this metric is not generated in every run. This metric is only produced if the detect_interior_points flag is set to true in the circle object space detector.

Definition

Interior Points to Plane Error metrics contain the following fields:

Field	Type	Description
metadata	A common metadata object	The metadata associated with the point cloud this circle target was measured in.
object_space_id	UUID	The UUID of the object space that was being observed.
plane_inliers_x	An array of floats	All X-coordinates of points contained within the circle target.
plane_inliers_y	An array of floats	All Y-coordinates of points contained within the circle target.
plane_inliers_z	An array of floats	All Z-coordinates of points contained within the circle target.
world_extrinsics_component_ids	An array of UUIDs	The camera UUIDs for each world extrinsic in world_extrinsics
world_extrinsics	An array of world extrinsics objects	The world pose (camera from object space) that correspond to each circle_center_misalignment
plane_inliers_distances	An array of arrays of floats	The point-to-plane distances between the plane inlier points and the plane observed at a given world extrinsic.
plane_distance_rmse_per_we	An array of floats	Similar to plane_inliers_distances but represents the RMSE of all plane inlier distances.
plane_distance_rmse	Float	The plane inlier distance RMSE over all world extrinsics.

Analysis

This metric can be considered a companion metric to Circle Misalignment. While circle misalignment measures the error between the observed circle center in LiDAR space and the circle center estimated from each camera, interior points to plane error uses those same derived extrinsics to estimate the error in fit between the LiDAR points observed on the surface of the circle target and the actual target.

Why Optional?

This metric is not generated in every run; it's opt-in. This is because poor quality LiDAR can often given erroneous and erratic distance readings, even on flat surfaces. Using these observations in a calibration would just make things worse, not better. By making this metric optional, we allow the user the option to disregard these readings and just work with the circle center for calibration.