Moving User Segmentation for Sports Simulator Using Frame Difference and Edge Detection
Hyungkwan Son1 and
Suyoung Chi2
1. University of Science and Technology / Computer Software & Engineering, Daejon, Korea
2. Electronics and Telecommunications Research Institute/ Cognitive System Research Department, Daejon, Korea
2. Electronics and Telecommunications Research Institute/ Cognitive System Research Department, Daejon, Korea
Abstract—This work presents a novel moving objectsegmentation approach using frame differencing methodand edge detection to provide customized coaching serviceto users in advanced sports simulator like horse riding. Togive this service in the simulator, exact user detection is veryimportant. If the segmenting user from its backgroundbecame better, we will get a better pose recognition results.In this paper, we will propose more exact user segmentationalgorithm which gives better segmentation result thancommon temporal differencing method. To do this, edgeimage is applied in two ways. One is to eliminate noises onthe temporal differencing image. Another is to makeconnected contour of user’s body shape. At the end of thispaper, the result of our method will be given.
Index Terms—edge detection, object segmentation, temporaldifferencing, logical AND
Cite: Hyungkwan Son and Suyoung Chi, "Moving User Segmentation for Sports Simulator Using Frame Difference and Edge Detection," International Journal of Signal Processing Systems, Vol. 1, No. 1, pp. 89-92, June 2013. doi: 10.12720/ijsps.1.1.89-92
Index Terms—edge detection, object segmentation, temporaldifferencing, logical AND
Cite: Hyungkwan Son and Suyoung Chi, "Moving User Segmentation for Sports Simulator Using Frame Difference and Edge Detection," International Journal of Signal Processing Systems, Vol. 1, No. 1, pp. 89-92, June 2013. doi: 10.12720/ijsps.1.1.89-92