Changes in the marine environment due to changes in the global environment are problems that have attracted attention in recent years. Consequently, the measurement of marine life forms and the surveying and studying of ecological systems have been extensively conducted from the viewpoint of environmental conservation. This paper proposes a new dynamic image processing method. It enables dynamic measurement of marine life, based on the dynamic images obtained by a marine ecological system measurement and recording support device that consists of various sensor nodes. A dynamic-image marine life detection method in which multi-template matching based on color orientation code matching is applied, and a method of motion estimating marine life, one in which a particle filter consisting of a double-likelihood function is used, are combined to develop a new dynamic image processing method and conduct ecology observations.

1. [1] K. E. Carpenter, “One-third of reef-building corals face elevated extinction risk from climate change and local impact,” Science, Vol.321, pp. 560-563, 2008.
2. [2] K. Kawabata, T. Kobayashi, T. Suzuki, and F. Takemura, “Development of a wireless sensor node for monitoring underwater conditions,” Proc. of 2011 Annual Conf. of I.E.E. of Japan, Industry Applications Society, 2-S8-2, 2011.
3. [3] D. Nakandakari and F. Takemura, “Development of remotely operated vehicle Propeller fabrication and control experiment,” The papers of Technical Meeting on Innovative Industrial System, IEEE Japan, pp. 59-63, 2010.
4. [4] N. Wajima, S. Takahashi, M. Ito, Y. Satoh, and S. Kaneko, “Tracking to a moving object by block discrimination method based on radial reach filter,” The J. of the Institute of Image Electronics Engineers of Japan, Vol.35, No.4, pp. 306-313, 2006.
5. [5] T. Honda, S. Takahashi, H. Takauji, and S. Kaneko, “Robust tracking method to moving object with random walk,” The J. of the Institute of Image Electronics Engineers of Japan: Visual computing, devices & communications, Vol.41, No.4, pp. 360-365, 2012.
6. [6] F. Ullah and S. Kaneko, “Using orientation codes for rotation invariant template matching,” Pattern Recognition, Vol.37, Issue 2, pp. 201-209, 2004.
7. [7] K. Kagoike, S. Takahashi, H. Takauji, and S. Kaneko, “Tracking method to random walk model based on orientation code matching,” Proc. of SPIE Int. Symposium on Optomechatronic Technologies, pp. 72660K-72660K8, 2008.
8. [8] T. Honda, H. Takauji, and S. Kaneko, “Robust color orientation code matching with weighting for fluctuation in illumination spectrum,” J. of the Japan Society for Precision Engineering, Vol.75, No.2, pp. 313-320, 2009.
9. [9] H. Kamada, S. Takahashi, H. Takauji, S. Kaneko, and K. Kawabata, “Robust tracking method for cell observation,” Proc. of RIKENHYU Joint Conf. 2012, PR-5, 2012.
10. [10] T. Higuchi, “Particle filter,” The J. of the Institute of Electronics, Information and Communication Engineers, Vol.88, No.12, pp. 989-994, 2005.
11. [11] T. Mita, T. Kaneko, and O. Hori, “Probabilistic ISC for matching images of objects having individual difference,” The J. of the Institute of Electronics, Information and Communication Engineers: D-II, Vol.J83-D-II, No.8, pp. 1614-1623, 2005.
12. [12] K. Shimizu, “Recent developments in directional statistics,” J. of Japanese Society of Computational Statistics, Vol.19, No.2, pp. 127-150, 2006.
13. [13] B. D. Lucas and T. Kanade, “An interactive image registration technique with an application to stereo vision,” Proc. of the 7th Int. Joint Conf. on Artificial Intelligence, pp. 674-679, 1981.