An efficient augmented reality method for sports scene visualization from single moving camera

An algorithm to insert augmented reality in sports scenes is presented. The goal is to augment an image to the scene so that it appears as a part of the original scene. The proposed algorithm uses the homography relationship between the image coordinates and the world coordinates, then utilizes the Sift algorithm to find the corresponding points between two frames. By using the homography map we can detect the interested insertion region in each frame. To insert the virtual content, the algorithm segments the foreground and then uses the inverse homography map to insert the augmented reality in the original frame. The proposed algorithm is robust against camera movements. As shown in experimental results, the augmented image is well placed in the desired location. The experimental results show the strengths of the proposed method.

[1]  Tahar Battikh,et al.  Camera calibration using court models for real-time augmenting soccer scenes , 2011, Multimedia Tools and Applications.

[2]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[3]  Michael Beetz,et al.  ASPOGAMO: Automated Sports Games Analysis Models , 2009, Int. J. Comput. Sci. Sport.

[4]  Ja-Ling Wu,et al.  Virtual spotlighted advertising for tennis videos , 2010, J. Vis. Commun. Image Represent..

[5]  Yong Kwon Kim.  Computer in Secondary Schools : Relationships between Teachers Attitude and Skills and Implications for a Teacher Training Program , 1988 .

[6]  Steve Chi-Yin Yuen,et al.  Augmented Reality: An Overview and Five Directions for AR in Education , 2011 .

[7]  Shohreh Kasaei,et al.  Event Detection and Summarization in Soccer Videos Using Bayesian Network and Copula , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[8]  Changsheng Xu,et al.  @ICT: attention-based virtual content insertion , 2011, Multimedia Systems.

[9]  Loong Fah Cheong,et al.  Automatic camera calibration of broadcast tennis video with applications to 3D virtual content insertion and ball detection and tracking , 2009, Comput. Vis. Image Underst..

[10]  Chengke Wu,et al.  Registration using geometry features for augmented reality in soccer , 2008 .

[11]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[12]  D. W. F. van Krevelen,et al.  A Survey of Augmented Reality Technologies, Applications and Limitations , 2010, Int. J. Virtual Real..

[13]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[14]  Peter H. N. de With,et al.  A real-time augmented-reality system for sports broadcast video enhancement , 2007, ACM Multimedia.