Sign Up to our social questions and Answers Engine to ask questions, answer people’s questions, and connect with other people.
Login to our social questions & Answers Engine to ask questions answer people’s questions & connect with other people.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
I want to develop a gesture recognition. I’m considering using the Kinect to have 3D data, but I don’t know what features are the go-to features for gesture recognition.
What are the standard features used in gesture recognition? My intuition tells me optical flow would be useful, but I’m not sure how that would be used, to be honest. Clearly, the features will need to be temporal, rather than just spatial.
Thanks!
As far as I am aware Microsoft uses joint angles as features (as in, a feature approximates the state of the system and lets you distinguish various poses).
Here is a paper by some Microsoft Research researchers:
http://www.cs.dartmouth.edu/~cs104/BodyPartRecognition.pdf