Automatic pan control system for broadcasting ball games based on audience's face direction

ABSTRACT

We propose an automatic pan control system for broadcasting ball games by tracking face direction of audience. Presuming that the audience's face is directed to a notable play, we can shoot a broadcasting video by controlling the camera toward the audience's face direction. In our method, a court sensor which detects rough region where players exist is used in addition to the face sensor in order to obtain higher accuracy. Based on these sensors, the broadcasting video is generated by cylindrical mosaicing off-line. We conducted objective and subjective evaluation experiments and the result shows that our approach is better than previously proposed methods in respect of stable tracking and easy watching. Conclusively our method is as effective as the optimum camerawork.

REFERENCES

• 1: Y.Iguchi, M.Doi, Y.Manabe, K.Chihara, "Automatic Multi-Camera Control and Switching for Sports Game Broadcasting Based on Real-Time Video Analysis", The Institute of Image Information and Television Engineers, Vol. 56 No.2, pp.271--279, 2002(in Japanese).
• 2: K.Matsumoto, S.Sudo, H.Saito and S.Ozawa, "Optimized Camera Viewpoint Determination System for Soccer Game Broadcasting", Proc. MVA2000, IAPR Workshop on Machine Vision Applications, Tokyo, Nov. 2000, pp.115--118.
• 3: Marco La Cascia , Stan Sclaroff , Vassilis Athitsos, Fast, Reliable Head Tracking under Varying Illumination: An Approach Based on Registration of Texture-Mapped 3D Models, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.22 n.4, p.322-336, April 2000 [doi>10.1109/34.845375]
• 4: K.Hayashi, M.Hashimoto, H.Fujiwara and K.Sumi, "A Tracking Based Real-Time Head Direction Estimator to Detect Inattentiveness", 5th. Asian Pacific Conference on Computer Human Interaction, Nov. 2002, pp.682--692.
• 5: Richard Szeliski , Heung-Yeung Shum, Creating full view panoramic image mosaics and environment maps, Proceedings of the 24th annual conference on Computer graphics and interactive techniques, p.251-258, August 1997 [doi>10.1145/258734.258861]
• 6: High Resolution Full Spherical Videos, Proceedings of the International Conference on Information Technology: Coding and Computing, p.260, April 08-10, 2002
• 7: Production of Video Images by Computer Controlled Camera Operation Based on Distribution of Spatiotemporal Mutual Information, Proceedings of the International Conference on Pattern Recognition, p.4102, September 03-08, 2000
• 8: D.Kato, A.Ishikawa, T.Tsuda, S.Shimoda, H.Fukushima, "Automatic control of a robot camera for broadcasting and subjective evaluation and analysis of reproduced images", Proc. SPIE, Vol. 3959, pp.468--479.
• 9: S.Clippingdale and M.Fujii, "Face Recognition for Video Indexing : Randomization of Face Templates Improves Robustness to Facial Expression", Proc.VLBV '03, Springer-Verlag Lecture Notes in Computer Science, Madrid, 2003. Vol.2849, pp.32--40.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis
          Subjects: Object recognition

Additional Classification:
  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.5 Computational Geometry and Object Modeling
          Subjects: Geometric algorithms, languages, and systems
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis
          Subjects: Tracking; Time-varying imagery

General Terms:
Algorithms, Experimentation, Performance

Keywords:
automatic shooting, cylindrical panoramas, face direction, template matching