TGSF/TLoG filter with optical flow techniques for large motion detection

• Autorzy: Sarker M. H. , Sloane A.
• Języki publikacji: EN

Abstrakty

EN

In this paper, detection and segmentation of large motion in moving image sequences is presented. For detecting motion, the intensity of each pixel is convolved with the second derivative of the Temporal Gaussian Smoothing Function (TGSF) or the Temporal Laplacian of Gaussian (TLoG) filter. The zero-crossing in a single frame of the resulting function indicates the positions of moving edges. An intensity change over time due to a small illumination effect does not produce a zero crossing. Therefore, such changes are not interpreted as human motion by this method. The optical flow velocity is computed by using the spatial and temporal derivatives of this function, and it is normal to the zero crossing contours. Pixels belonging to the normal velocities are projected back to the original color image sequences to achieve a segmented color image. Experiments show that a moving object is detected correctly, and good segmentation results are achieved.

Słowa kluczowe

EN

motion detection; TLoG filter; zero crossing; motion segmentation

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2007
• Tom: Vol. 16, No. 3/4
• Strony: 237--249
• Opis fizyczny: Bibliogr. 10 poz., il., tab., wykr.

Twórcy

autor

Sarker M. H.

autor

Sloane A.

• Department of EEE, Islamic University of Technology (IUT), Gazipur-1704, Bangladesh,

Bibliografia

• [1] Horn B. K. P. , Schunck B. G.: Determining optical flow. Artificial Intelligence, Vol. 17, No. (1-3), pp. 185-203, 1981.
• [2] Buxton B. F., Buxton H.: Monocular depth perception from optical flow by space time signal processing. Proceeding Royal Society of London, UK. Vol. B. 218, pp. 27-47, 1983.
• [3] Kearney J. K., Thompson W. B., Boley D. L. : Optical flow estimation: An Error Analysis of Gradient Based Methods with Local Optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 9, pp. 229-244, March, 1987.
• [4] Duncan J. H., Chou T. C.: On the detection of motion and computation of optical flow. IEEE Transactions on Patten Analysis and Machine Intelligence. Vol. 14, No. 3. pp. 346-352, 1992.
• [5] Press W. H., Teukolsky S. A., Vetterling W. T., Flannery B. P.: Numerical Recipes in C: The art of scientific computing. Cambridge University press London. 2nd. Edition, 1992.
• [6] Barron J. L., Fleet D. J., Beauchemin, S. S.: Performance of optical flow technique. International Journal of Computer Vision, Vol. 12, No. l, pp. 43-77, 1994.
• [7] Aggarwal J. K., Cai Q.: Human motion analysis: A review. Computer Vision and Image Understanding, Vol. 73, No. 3. pp. 420-440, March, 1999.
• [8] Byung-Gyu Kim, Jae-Ick Shim, Dong-Jo Park: Fast image segmentation based on multi-resolution analysis and wavelets. Pattern Recognition Letters 24, Elsevier, pp. 2995-3006, 2003.
• [9] Wang L. W. H., Tan, T.: Recent developments in human motion analysis. Pattern Recognition. Vol. 36, pp. 585-601, 2003.
• [10] Wilson P., Wilson A.: Visualization and Image Processing, M.Sc.Lecture note CP-4020 , Sem - 2, SCIT, University of Wolverhampton. UK, 2004.