-
Notifications
You must be signed in to change notification settings - Fork 191
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
C++ Demo - Object Tracking (VitTrack) #240
Conversation
@fengyuentau I noticed that the "save" functionality should be optionally enabled to save an output |
"{save s |false |Specify to save a file with results. Invalid in case of camera input.}" | ||
"{vis v |false |Specify to open a new window to show results. Invalid in case of camera input.}"); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Seems like both of them are not used anywhere.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
They are now used! 👍 In both C++ and Python.
Ok, it would be like to have this fuctionality implemented. |
The functionality is added 💯 Saving works for both input videos and camera feed with matching FPS. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍 LGTM
This PR adds the C++ demo for the Object Tracking VitTrack model, as part of a request from #135.
demo.cpp
: Added to have matching functionality to thedemo.py
, text offsets in both versions were adjusted to prevent overlap and improve clarity.demo.py
: Updated to use save and vis flags for optional saving (disabled by default) and visualization (enabled by default) functionality.CMakeLists.txt
: Created to build with OpenCV 4.9.0 and enforces C++11 standards upon building.README.md
: Updated with C++ instructions.The interface matches other C++ demos within the set of ML models.
Average 100+ FPS on my laptop (AMD Ryzen 7 5800H) for a (640 x 480) webcam feed. FPS is slightly higher on a (1273 x 733) input video, see testing example below.
Testing