View-Based Interpretation of Real-Time Optical Flow for Gesture Recognition
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
GWindows: robust stereo vision for gesture-based control of windows
Proceedings of the 5th international conference on Multimodal interfaces
Robust hand gesture analysis and application in gallery browsing
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Controlling your TV with gestures
Proceedings of the international conference on Multimedia information retrieval
Hand gesture video browsing for broadband-enabled HDTVs
Sarnoff'10 Proceedings of the 33rd IEEE conference on Sarnoff
Human gesture recognition using 3.5-dimensional trajectory features for hands-free user interface
Proceedings of the first ACM international workshop on Analysis and retrieval of tracked events and motion in imagery streams
Vision-based hand-gesture applications
Communications of the ACM
Hand gesture recognition using depth data
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Combining RGB and ToF cameras for real-time 3D hand gesture interaction
WACV '11 Proceedings of the 2011 IEEE Workshop on Applications of Computer Vision (WACV)
Gesture-recognizing hand-held interface with vibrotactile feedback for 3D interaction
IEEE Transactions on Consumer Electronics
Actual remote control: a universal remote control using hand motions on a virtual menu
IEEE Transactions on Consumer Electronics
Hi-index | 0.00 |
Motion recognition systems have been widely developed in the field of human computer interaction. Methods, such as pointing, dynamic gesture and static gesture or hand held devices have been proposed for motion recognition. The motion recognition systems have been gradually adapted to home appliances in our daily. In this paper, we focus on TV interaction, since the device is a recent representative multimedia device applying the motion technique. Most motion recognition systems utilize 3D data, such as horizontal, vertical and depth information by stereo camera or ToF (Time of Flight) camera. However, this paper proposes the different techniques for human-TV interaction. We propose an optical flow based motion recognition system that provides direction and speed, in addition to the position of the moving target in real time. These factors are useful in recognizing human motion more effectively and more dynamically. Therefore, we design the natural interaction for human-TV using these motion data. The calculation process of optical flow is outside the scope of this paper. This real time optical flow calculation is implemented using the FPGA chip supporting parallel processing by a hardware team in our laboratory. We propose a method for human motion recognition based on real time optical flow system.