Age | Commit message (Collapse) | Author |
|
Regarding tweaks:
* EWA smoothing of head ROI. Smoothing strength is a UI setting.
* Adjustible zoom into the detected face. The predicted ROI is scaled by a factor the user can set. There is a sweet spot somewhere near 1.
* Adjustible number of threads
* The ROI is no longer taken as model output directly. This was actually not needed. Perhaps as auxiliary training objective for the network. But the tracker implementation now just uses a square area around the head center according to the predicted head size.
* Add comment and debug notification on face ROI model output
|
|
|
|
|
|
|
|
- Added support for MJPEG compression for neuralnet tracker
|
|
|
|
Issue: #1394
|
|
|
|
|
|
This is because multiple opentrack modules depend on different opencv
modules and whichever FIND_PACKAGE(OpenCV COMPONENTS ...) gets executed
first, wins. Following FIND_PACKAGE calls will exit and not populate the
component list any further.
This didn't break the build as the build code for tracker/nn wasn't the
one being executed first.
|
|
|
|
|
|
|
|
|
|
|
|
It crashes later though.
|
|
|
|
* Add ONNXRuntime_DIR variable
* Change target name to onnxruntime::onnxruntime following naming
conventions for imported libs
* Look for the DLL on windows and store it in a variable for later
* Correctly define the properties of the import library
* Change names and logic for global variables to follow standard conventions
* Change import library type from UNKNOWN to SHARED in order to make msvc
link against the .lib file, not the dll.
|
|
* Revert include header changes
* Address the following review remarks for include path
https://github.com/opentrack/opentrack/pull/1306#discussion_r680548570
https://github.com/opentrack/opentrack/pull/1306#discussion_r680548755
https://github.com/opentrack/opentrack/pull/1306#discussion_r680548800
https://github.com/opentrack/opentrack/pull/1306#discussion_r680549144
|
|
- Address review comment https://github.com/opentrack/opentrack/pull/1306#discussion_r680484878
- Update ONNXRuntime module to use a specific `onnxruntime` target.
- Use OpenCV components instead.
NOTE:
ONNXRuntinme may provide their own ONNXRuntimeConfig.cmake and
ONNXRuntimeVersion.cmake in the future.
See https://github.com/microsoft/onnxruntime/issues/3124 for reference
|
|
|
|
|
|
Meaning informative elements like the pose gizmo and bounding boxes
|
|
|
|
|
|
Powered by AI!
Models were generated with code from
https://github.com/DaWelter/neuralnet-tracker-traincode/releases/tag/v0.1
|