This post includes changelogs for the new Limelight OS 2023.6 as well as the previously released 2023.5 and 2023.4 images. 2023.5 and 2023.4 were detailed in the “Introducing Limelight 3” thread, but they were never given their own threads.
ChArUco calibration allows your LImelight to compute its intrinsic parameters and distortion coefficients. These are going to be slightly different for every image sensor + lens combo. When performed well, custom calibration may provide a slight accuracy increase in tx,ty, and all 3D estimates.
You should not consider calibration if you are simply centering an AprilTag / Retro marker on the movable crosshair or the center of the image. You should consider calibration if you need higher accuracy 3D measurements.
ChArUco calibration is considered to be better than checkerboard calibration because it handles occlusions, bad corner detections, and does not require the entire board to be visible. This makes it much easier to capture calibration board corners close to the edges and corners of your images. This is crucial for distortion coefficient estimation.
Limelight’s calibration process provides feedback at every step, and will ensure you do all that is necessary for good calibration results. A ton of effort has gone into making this process as bulletproof as possible.
Most importantly, you can visualize your calibration results right next to the default calibration. At a glance, you can understand whether your calibration result is reasonable or not.
You can also use the calibration dashboard as a learning tool. You can modify downloaded calibration results files and reupload them to learn how the intrinsics matrix and distortion coefficients affect targeting results, FOV, etc.
You only need to calibrate at 1280x960. Other input resolutions will automatically scale the intrinsic parameters. Hardware-zoomed pipelines will still use hard-coded calibrations and are not recommended for 3D functionality.
Take a look at this video:
Fixed regression - Limelight Robot-Space “Yaw” was inverted in previous releases. Limelight yaw in the web ui is now CCW-Positive internally.
Snapshot grid now loads low-res 128p thumbnails.
Limeilght Yaw is now properly presented in the 3d visualizers. It is ccw-positive in the visualizer and internally
Indicate which targets are currently being tracked in the field space visualizer
- Region selection now works as expected in neural detector pipelines.
- Add 5 new region options to select the center, top, left, right, top, or bottom of the unrotated target rectangle.
- :5807/hwreport will return a JSON response detailing camera intrinsics and distortion information
- Certain non-coplanar apriltag layouts were broken in MegaTag. This has been fixed, and pose estimation is now stable with all field tags. This enables stable pose estimation at even greater distances than before.
- TX and TY are more accurate than ever. Targets are fully undistorted, and FOV is determined wholly by camera intrinsics.
Specify the classes you want to track for easy filtering of unwanted detections.
Support any input resolution, support additional output shapes to support other object detection architectures. EfficientDet0-based models are now supported.