Two-handed virtual manipulation
ACM Transactions on Computer-Human Interaction (TOCHI)
A System for Person-Independent Hand Posture Recognition against Complex Backgrounds
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
3D Hand Model Fitting for Virtual Keyboard System
WACV '07 Proceedings of the Eighth IEEE Workshop on Applications of Computer Vision
Gesture recognition with a Time-Of-Flight camera
International Journal of Intelligent Systems Technologies and Applications
| Hi-index | 0.00 |
The study of detecting and tracking hand gestures in general has been widely explored, yet the focus on fist gesture in particular has been neglected. Methods for processing fist gesture would allow more natural user experience in human-machine interaction (HMI), however, it requires a deeper understanding of fist kinematics. For the purpose of achieving grasping-moving-rotating activity with single hand (SH-GMR), the extraction of fist rotation is necessary. In this paper, a feature-based Fist Rotation Detector (FRD) is proposed to bring more flexibility to interactions with hand manipulation in the virtual world. By comparing to other candidate methods, edge-based methods are shown to be a proper way to tackle the detection. We find a set of "fist lines" that can be easily extracted and be used steadily to determine the fist rotation. The proposed FRD is described in details as a two-step approach: fist shape segmentation and fist rotation angle retrieving process. A comparison with manually measured ground truth data shows that the method is robust and accurate. A virtual reality application using hand gesture control with the FRD shows that the hand gesture interaction is enhanced by the SH-GMR.