Our great sponsors
-
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
I was trying to train a model which goes on top of one of the pose estimation models(posenet, movenet, mediapipe) which detects the action performed(waving, swipe right, etc), and I was planning on generating synthetic data for it. I saw that there's a project for unity PeopleSansPeople, but it's not right to train a model for action recognition. I would like something that either simulates a human doing a simple action, to which I would be able to add randomness to it. I was thinking to either use Unity or maybe write something that would model the human keypoints(the output of pose estimation) and simulate them.. I am wondering if there already exists something that you guys might know about??
I was indirectly involved in some similar research work, maybe these repos will help a little : https://github.com/DavidLSmyth/VirtualHumanBatchProcessing and https://github.com/DavidLSmyth/MotionCaptureClassifier. I'd advise using blender for this. The Bvh animation file format will probably be the easiest for you to work with, you can get joint positions for each frame pretty easily. The cmu mocap dataset might be suitable
I was indirectly involved in some similar research work, maybe these repos will help a little : https://github.com/DavidLSmyth/VirtualHumanBatchProcessing and https://github.com/DavidLSmyth/MotionCaptureClassifier. I'd advise using blender for this. The Bvh animation file format will probably be the easiest for you to work with, you can get joint positions for each frame pretty easily. The cmu mocap dataset might be suitable