Download presentation
Presentation is loading. Please wait.
Published byLewis Higgins Modified over 8 years ago
1
Rob Relyea | Program Manager, Kinect Team Johan Marien | Program Manager, Kinect Team
2
Rob Relyea | @rrelyea Principal Program Manager, Microsoft –Member of Kinect for Windows and Xbox Teams –Currently focused on Hand Pointer Gestures Deep on WPF/XAML –Formerly worked as Program Manager and Architect on WPF and XAML teams
3
Johan Marien | @jmarien Sr. Program Manager, Microsoft –Johan Marien is a Program Manager on the Kinect Team working on developer tooling.
4
Kinect Studio –Recording sensor data –Playback of data Gesture Recognition –Heuristic Recognition –Machine Learning Based Recognition [w/ Gesture Builder] Module Overview
5
Kinect Studio Recording and Playback
6
DEMO Kinect Studio 2.0 Connecting | Monitoring | Configuring Views
7
Recordable Data Sources Infrared 13 MB/s Depth 13 MB/s BodyFrameBodyIndex Color 120 MB/s Audio 32 KB/s Legend Record/Play Record Only
8
DEMO Kinect Studio 2.0 Recording | Playback
9
V2.0 Now can record Audio Playback works without sensor attached API access to playback/record –Kinect Studio, only uses these public APIs! Kinect Studio – Major Improvements
10
Gesture Recognition Heuristic + Machine Learning Approaches
11
DEMO Programmatic detection of a gesture/pose
12
Gesture Builder New tool, shipping with v2 SDK Organize data using projects and solutions Give meaning to data by tagging gestures Build gestures using machine learning technology –Adaptive Boosting (AdaBoost) Trigger Determines if player is performing gesture –Random Forest Regression (RFR) Progress Determines the progress of the gesture performed by player Analyze / test the results of gesture detection Live preview of results
13
Visual Gesture Builder Rinse and repeat Your Application Record example gestures using Kinect Studio Tag gestures using Gesture Builder Build and analyze gestures using Gesture Builder Preview gestures in Gesture Builder Call gesture detector for tracked bodies
14
DEMO Machine Learning Demo
15
Heuristic Gesture is a coding problem Quick to do simple gestures/poses (hand over head) ML can also be useful to find good signals for Heuristic approach Machine Learning (ML) with G.B. Gesture is a data problem Signals which may not be easily human understandable (progress in a baseball swing) Large investment for production Danger of over-fitting, causes you to be too specific – eliminating recognition of generic cases Gesture Recognition
16
DEMO Calling gesture detector from code
17
Kinect Studio –Recording sensor data –Playback of data –APIs with Microsoft.Kinect.Tools.dll Gesture Recognition –Heuristic Recognition –Machine Learning Based Recognition [w/ Gesture Builder] Summary
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.