The outlier filter removes pixels that it deems as outliers within a small local region of neighboring pixels. The outliers are measured by how far away they are from their closest neighbors. If the distance exceeds the threshold of the outlier filter, the pixel is identified as an outlier and thus removed from the final point cloud.
The unit of the outlier filter threshold is in millimeters.
The outlier filter adds close to no additional processing time.
Why do you need the outlier filter?
It removes noisy points which may improve the performance of many vision algorithms, and it can also take away stray points that can cause issues for motion planning algorithms.
The outlier filter is a great way to remove stray points that can mess up motion planning for robots.
The Outlier filter is good at removing completely isolated floating points. However, it does not remove a dense group of floating points, that is what the Cluster Filter does.
Outlier filter is improved to remove fewer good points.