search

limgm / hand_tracking_samples_D400

IntelRealSense hand_tracking_samples for D400
Apache License 2.0
9 stars 3 forks source link

Classification stage in the CNN #3

Open miguelml99 opened 3 years ago

miguelml99 commented 3 years ago

I am using this project in my Bachelors thesis but I have encountered a problem My idea was to build a hand gesture recognition system that could tell what gesture is the system receiving as an input. I was hoping that the output could provide the label for the gestures' name.

However, from what I have experienced with this project, the output resulting from the classification layer is a series of values describing fingers' angles and hand orientation.

Is there a way in which the system could be trained so that the output of the classification stage provides the label for the gesture dataset name (as if we wanted to find out the gesture category each input belongs to)??

Thanks in advance.

limgm commented 3 years ago

Hi @miguelml99 thank you for your interest in this project, I have not used this code for quite a while so couldn't answer your question.

But if you are interested in hand gesture recognition from RGB image you may want to refer to a more recent project using Google's Mediapipe.

All the best to your project!

miguelml99 commented 3 years ago

Hi, @limgm Thank you for your response. I am using the realsense depth camera D435i so I need to benefit from depth images. However ill take a look into your RGB project, it seems promising and ambitious :)

Coming back to the hand tracking project, I have seen that you implemented the left-hand tracking capability. I haven't tried this one yet, but is there a way to recognize/track both left and right hands simultaneously?? (just in case you know/remember, I understand it´s been long since you last worked with this project. )

Thanks for your help!