Motion Analysis for Duplicate Frame Removal in Wireless Capsule Endoscope Video

Wireless capsule Endoscopy (WCE) has rapidly shown its wide applications in medical domain last ten years thanks to its noninvasiveness for patients and support for thorough inspection through a patient-s entire digestive system including small intestine. However, one of the main barriers to efficient clinical inspection procedure is that it requires large amount of effort for clinicians to inspect huge data collected during the examination, i.e., over 55,000 frames in video. In this paper, we propose a method to compute meaningful motion changes of WCE by analyzing the obtained video frames based on regional optical flow estimations. The computed motion vectors are used to remove duplicate video frames caused by WCE-s imaging nature, such as repetitive forward-backward motions from peristaltic movements. The motion vectors are derived by calculating directional component vectors in four local regions. Our experiments are performed on small intestine area, which is of main interest to clinical experts when using WCEs, and our experimental results show significant frame reductions comparing with a simple frame-to-frame similarity-based image reduction method.

Authors:

• Min Kook Choi
• Hyun Gyu Lee
• Ryan You
• Byeong-Seok Shin
• Sang-Chul Lee

Keywords:

• Wireless capsule endoscopy
• optical flow
• duplicated image
• duplicated frame.

References:

[1] G. Iddan, G. Meron, A. Glukhovsky, P. Swain,
"Wireless capsule endoscopy", Nature, vol. 405, Issue 6785,
pp. 417-418, 2000.
[2] S. Hwang, J. H. Oh, J. Cox, S. J. Tang, H. F. Tibbals,
"Blood detection in wireless capsule endoscopy using
expectation maximization clustering", Proceedings of SPIE,
vol. 6144, pp. 577-587, 2006.
[3] J. Berens, M. Mackiewicz, D. Bell, "Stomach, intestine
and colon tissue discriminators for wireless capsule
endoscopy images", Proceedings of SPIE, Conference on
Medical Imaging, vol. 5747, pp. 283-290, 2005.
[4] B. Li, MQH. Meng, "Texture analysis for ulcer
detection in capsule endoscopy images", Image and Vision
Computing, vol. 27, pp. 1336-1342, 2009.
[5] B. Li, MQH. Meng, "Computer-based detection of
bleeding and ulcer in wireless capsule endoscopy images
by chromaticity moments", Computer in Biology and
Medicine, pp. 141-147, 2009.
[6] Berthold K. P. Horn, Brian G. Schunck, "Determining
Optical Flow", Artificial Intelligence, pp. 185-203, 1981.
[7] P. Anandan, "A computational framework and an
algorithm for the measurement of visual motion",
International Journal of Computer Vision, 2, pp. 283-310,
1989.
[8] E. Memin, P. Perez, "Hierarchical estimation and
segmentation of dense motion fields", International
Journal of Computer Vision, 46(2), pp. 129-155, 2002.
[9] T. Brox, A. Bruhn, N. Papenberg, J. Weickert, "High
accuracy optical flow estimation based on a theory for
warping", European Conference on Computer Vision,
LNCS 3024, pp. 25-36, 2004.
[10] S. Uras, F. Girosi, A. Verri, and V. Torre. "A
computational approach to motion perception", Biological
Cybernetics, 60, pp. 79-87, 1988.
[11] M. J.Black. P. Anandan, "The robust estimation of
multiple motions: parametric and piecewise smooth flow
fields", Computer Vision and Image Understanding, 63(1),
pp. 75-104, 1996.
[12] E. Memin. P. Perez, "A multigrid approach for
hierarchical motion estimation", In Proc. Sixth
International Conference on Computer Vision, pp. 933-938,
1998
[13] L. I. Rudin, S. Osher, E. Fatemi, "Nonlinear total
variation based noise removal algorithms", Physica D, 60,
pp. 259-268, 1992.
[14] I. Cohen, "Nonlinear variational method for optical
flow computation", Proc. Eighth Scan-dinavian Conference
on Image Analysis, volume 1, pp. 523-530, 1993
[15] L. Alvarez, J. Esclarin, M. Lefebure, J. Sanchez, "A
PDE model for computing the optical flow", In Proc. XVI
Congreso de Ecuaciones Diferenciales y Aplicationes,
pp.1349-1356, 1999., 1999.