Closed AdrianPeniak closed 2 years ago
Thank you for the issue and I am so sorry for my VERY late response. As for the palm detection model, I think the problem is how you generate the anchors for the model's output. Maybe your anchor sequence does not match the model's output. I've tried a customized model from this repo: https://github.com/aashish2000/hand_tracking and it works like a charm. Here is my solution:
create_ssd_anchors_hand()
and its related functions to the following functions:
#include <fstream>
#include <sstream>
#include <string>
cv::Rect2f convertAnchorVectorToRect(const std::vector
std::vector
4. Change `NUM_BOXES_HAND` to 2944 instead of 2016
You can refer the above repo if you want to rotate the ROI. I hope this will help. Once again, sorry for make you wait for a really long time.
Thanks
Hi,
I would like to kindly ask you for help with hands detection using mediapipe and tensorflow. I used your awesome project (forked here https://github.com/AdrianPeniak/mediapipe_face_iris_cpp.git) and port it to linux env. However when I reuse your classes for hand detection using palm model I can't get good results (hands not detected, drawing random roi according code in repo). I understand that functions as getHighestScoreDetection() etc. must be rewritten, but I afraid that problem is somewhere before (e.g. image preprocessing).
Could you please take a look to my forked project?
Thanks for any advise.
Thanks