GitHub - Pk-T/Gesture-Recognition-OpenCV: Basic gesture recognition which uses opencv to process images and SVM for classification of the gestures.

Pk-T / Gesture-Recognition-OpenCV Public

Notifications You must be signed in to change notification settings
Fork 3
Star 11

Basic gesture recognition which uses opencv to process images and SVM for classification of the gestures.

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
Code		Code
calibration		calibration
data		data
nestk		nestk
people-tracker		people-tracker
reconstructor		reconstructor
viewer		viewer
.gitattributes		.gitattributes
.gitignore		.gitignore
.gitmodules		.gitmodules
CMakeLists.txt		CMakeLists.txt
Copyright.txt		Copyright.txt
NEWS		NEWS
README		README
extract.sh		extract.sh
linux_build.sh		linux_build.sh
linux_configure.sh		linux_configure.sh
linux_configure_external_opencv.sh		linux_configure_external_opencv.sh
macosx_build.sh		macosx_build.sh
macosx_configure.sh		macosx_configure.sh

Repository files navigation

The training images have been removed but the model which was created using the images is present in the Code directory.
Software is written in Qt/C++ integrated with RGB Demo.

RGBDemo is a software to visualize, calibrate and process Kinect output

The code is based on the freenect library http://openkinect.org and
OpenCV http://opencv.willowgarage.com .

The demos are based on a library called nestk. The library itself is
easy to integrate to an existing project using cmake: just copy the
nestk folder as a subfolder of your project and you should be able to
start working with Kinect data. You can get a tutorial to get started
there: http://nicolas.burrus.name/index.php/Research/KinectUseNestk .

8 gestures are classified like:
Waving, Leg movement, Hand sweep, Nodding etc