Detecting Salient Motion by Accumulating Directionally-Consistent Flow
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer vision for computer games
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
Real Time Face and Object Tracking as a Component of a Perceptual User Interface
WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Foreground Object Detection in Changing Background Based on Color Co-Occurrence Statistics
WACV '02 Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision
Using Histograms to Detect and Track Objects in Color Video
AIPR '01 Proceedings of the 30th on Applied Imagery Pattern Recognition Workshop
Integral Histogram: A Fast Way To Extract Histograms in Cartesian Spaces
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Orientation histogram-based matching for region tracking
WIAMIS '07 Proceedings of the Eight International Workshop on Image Analysis for Multimedia Interactive Services
Realtime Coarse Pose Recognition Using a Multi-scaled Local Integral Histograms
ICCIT '07 Proceedings of the 2007 International Conference on Convergence Information Technology
Hi-index | 0.00 |
We present a vision based HCI system which exploits background subtraction comparing local orientation histograms. As a new virtual input device for game control, we focus on extracting coarse pose of the foreground object and its application to video game. The captured image is divided into the cells where the local orientation histogram with Gaussian kernel is computed and compared with the corresponding one using Bhattacharyya distance measure. The orientation histogram-based method is partially robust against illumination change and small moving objects in background. We also propose a vision-based interfacing system to existing game engines and appropriate modules that includes recognition process using neural network. The real-time 3D video games are implemented as a test-bed with the proposed system to prove the presented vision based system is highly applicable to let users control virtual environment without any hard-wired input devices.