How can I adjust the basic parameters?

This article explains how to adjust the basic tracking parameters in REFLEKT ONE Sync.



In order to improve tracking quality, adjustments can be made in the Basic Parameters panel.

It is displayed in the basic Test & Adapt mode.


Sync_test adapt_parameters




Sync_adjust parameters


Explanation of each parameter:

  • Quality Threshold: This is a quality threshold for validating the tracking result. The value highly depends on your scenario. If the line-model matches the real object perfectly and there is no occlusion and a high value is recommended.  Since the LineModel does usually not perfectly match the real object, a lower value might work better. If the value is too low, the algorithm might start tracking the wrong object.
  • Line Sensitivity: Threshold for edge candidates in the tracking model and image. High values will only consider pixels and model parts with high contrast and depth variance as candidates. Low values will increase this tolerance. This is a trade-off. If there are too many candidates the algorithm might choose the wrong matches. If there are not enough candidates the model might not stick to the object in the image.
  • Static Scene: If this parameter is set to true, it is assumed that the real world model is not movable. Multiple keyframes are used to estimate the transformation between HoloLens tracking and the VisionLib tracking. The whole registration process is more stable, if this assumption can be made.
  • Extendible Tracking: If this value is set to true the model-based tracking will be extended with a SLAM-based tracking. This allows you to continue tracking even if the model isn’t visible in the camera image anymore. The user needs to perform a SLAM dance, which means to translate and rotate the camera, so that there is enough baseline for the feature reconstruction.