1

Egocentric View Transition forVideo Monitoring in a Distributed Camera Network

Chairman:Hung-Chi YangPresenter: Fong-Ren SieAdvisor: Yen-Ting ChenDate: 2013.3.20

Kuan-Wen Chen, Pei-Jyun Lee, and Yi-Ping Hung, Department of Computer Science and Information

Engineering Graduate Institute of Networking and Multimedia,

National Taiwan University, Taipei, Taiwan,2011

2

OutlineIntroductionMethodologyResultsConclusionsReferences

3

IntroductionMulti-camera systems used in

video surveillance applications◦Airport◦Railway security◦Traffic monitoring

4

IntroductionMulti-camera system

◦Advantage Can monitor the activities of targets over

a large area

Show multiple video streams on display simultaneously

5

IntroductionMulti-camera system

◦Disadvantage To security guards or users using the

system, with the number of video streams increasing the difficulty of monitoring increases.

The user needs to understand where the target is in the environment and the geometrical relationship between cameras.

6

IntroductionEgocentric view transition

◦Avoid the effect of uncomfortable flash caused by sudden view change

◦Help users understand the spatial relationships among the target, cameras, and environments easily

7

MethodologyThe basic concept of view

transition comes from view morphing ◦Virtual teleconference system◦Sports broadcasting system◦Photo browsing and exploring

system

8

MethodologyTo monitor multiple cameras,

some works embedded video surveillance images in a 3D model by using projective texture mapping to integrate live video streams with the model

9

MethodologyMulti-camera Tracking

◦In the overlapping case Multi-camera tracking is performed by

comparing the 3D positions estimated from each camera.

◦In the non-overlapping case which tracks targets across non-

overlapping cameras based on both spatio-temporal and appearance cues.

10

Methodology

Background Texture Adaptation◦We calculate the pixel density of

texture ratio of real camera to virtual camera by the following equation:

Rr>1 → Paste with that captured by cameras

Rr<1 →use the grid-texture

11

ConclusionsEgocentric view transition

which synthesizes the virtual views when switching cameras◦ Overlapping FOVs of cameras.

presented a framework to build a foreground billboard and put it to the 3D model.

12

Conclusions◦Non-overlapping FOVs of cameras. a better view transition effect use a particle system to visualize the

probability distribution of where the target is in the blind region

rule of setting virtual camera positions and a background texture adaptation method

13

References 1. Chen, K.W., Lai, C.C., Hung, Y.P., Chen, C.S.: An Adaptive

Learning Method for Target Tracking across Multiple Cameras. In: CVPR (2008)

2. Debevec, P.E., Taylor, C.J., Malik, J.: Modeling and Rendering Architecture from Photographs: A Hybrid Geometry- and Image-Based Approach. In: SIGGRAPH (1996)

3. Finke, R.A.: Principles of Mental Imagery. MIT Press, Cambridge (1989)

4. Girgensohn, A., Kimber, D., Vaughan, J., Yang, T., Shipman, F., Turner, T., Rieffel, E., Wilcox, L., Chen, F., Dunnigan, T.: DOTS: Support for Effective Video Surveillance. In:

MULTIMEDIA (2007) 5. Hsiao, C.H., Huang, W.C., Chen, K.W., Chang, L.W., Hung, Y.P.:

Generating Pictorial-Based Representation of Mental Image for Video Monitoring. In: IUI (2009)

6. Horprasert, T., Harwood, D., Davi, L.: A Statistical Approach for Real-Time Robust Background Subtraction and Shadow Detection. In: FRAME-RATE Workshop (1999)

14

References 7. Haan, G., Scheuer, J., Vries, R., Post, F.H.:

Egocentric Navigation for Video Surveillance in 3D Virtual Environments. In: IEEE Symposium on 3D User Interfaces (2009)

8. Hartley, R.I., Zisserman, A.: Multiple View Geometry, 2nd edn. Cambridge University Press, Cambridge (2004)

9. Katkere, A., Moezzi, S., Kuramura, D.Y., Kelly, P., Jain, R.: Towards Video-Based Immersive Environments. Multimedia System 5(2), 69–85 (1997)

10. Kanade, T., Narayanan, P., and Rander, P.: Virtualized Reality: Concept and Early Results. Tech. Rep. CMU-CS-95-153 (1995)

11. Levenberg, K.: A method for the solution of certain problems in least squares. Quarterly Applied Math. 2, 164–168 (1944)

12. Lei, B., Hendriks, E.: Real-Time Multi-Step View Reconstruction for a Virtual Teleconference System. EURASIP J. Appl. Signal Process 2002(10), 1067–1088 (2002)

15

References 13. Neumann, U., You, S., Hu, J., Jiang, B., Lee, J.: Augmented

Virtual Environment (AVE): Dynamic Fusion of Imagery and 3d Models. In: IEEE Virtual Reality (2003)

14. Ohta, Y., Kitahara, I., Kameda, Y., Ishikawa, H., Koyama, T.: Live 3D Video in Soccer Stadium. IJCV 75(1), 173–187 (2007)

15. Palmer, S.: Vision Science: Photons to Phenomenology. MIT Press, Cambridge (1999)

16. Reeves, W.T.: Particle Systems - a Technique for Modeling a Class of Fuzzy Objects. ACM Transactions on Graphics 2, 91–108 (1983)

17. Sawhney, H.S., Arpa, A., Kumar, R., Samarasekera, S., Aggarwal, M., Hsu, S., Nister, D., Hanna, K.: Video Flashlights: Read Time Rendering of Multiple Videos for Immersive Model Visualization. In: EGRW (2002)

18. Seitz, S., Dyer, C.: View Morphing. In: SIGGRAPH (1996) 19. Stauffer, C., Grimson, W.E.L.: Learning Patterns of Activity

using Real-Time Tracking. IEEE Transactions on PAMI 22(8), 747–757 (2000)

16

References 20. Segal, M., Korobkin, C., Widenfelt, R., Foran, J.,

Haeberli, P.: Fast Shadows and Lighting Effects Using Texture Mapping. In: SIGGRAPH (1992)

21. Snavely, N., Seitz, S.M., Szeliski, R.: Photo Tourism: Exploring Photo Collections in 3d. In: SIGGRAPH (2006)

22. Thorndyke, P., Hayes-Roth, B.: Differences in Spatial Knowledge Acquired from Maps and Navigation. Cognitive Psychology 14(4), 560–589 (1982)

23. Welch, G., Bishop, G.: An introduction to the kalman filter. Chapel Hill, NC, USA, Tech. Rep. (1995)

24. Wang, Y., Krum, D.M., Coelho, E.M., Bowman, D.A.: Contextualized Videos: Combining

Videos with Environment Models to Support Situational Understanding. IEEE TVCG 13(6), 1568–1575 (2007)

25. Zhang, Z.: A Flexible New Technique for Camera Calibration. IEEE Transactions on PAMI 22, 1330–1334 (2000)

17

Thank you for your attention