In the paper a monitoring approach is proposed for early detection of landslide or sediment movement related hazards. The method is based on adaptive sized multi-template matching. The size of templates is set according to the motion field of earth particles to ensure reliable matching. Furthermore to ensure reliable tracking of earth particles several patterns corresponding to different views of tracked objects (e.g. rotating stone) are considered. The suitability of the approach for specific landslide like scenarios has been validated by several experiments.

 

Published In : IJCSN Journal Volume 3, Issue 3

Date of Publication : 01 June 2014

Pages : 92 - 98

Figures : 13

Tables : 03

Publication Link : Cloud Based Web IDE for Collaborating Programmers

 

 

 

Takeshi Hashimoto : was born in Japan, on January 31, 1961. He received the Master degree in electrical engineering from Kyoto Institute of Technology, Japan, in 1987, and the Ph.D. degree in electrical engineering from Kyoto University, Japan, in 1996. He is presently Associate Professor in the Department of Electrical and Electronics Engineering at Shizuoka University, Japan. His domain work is developing image processing and image measurement.

András Rövid : was born in Slovakia, on April 20, 1978. He received the M.Sc. E.E. degree from the Technical University of Kosice, Slovakia, in 2001 and the Ph.D. degree from the Budapest University of Technology and Economics, Budapest, Hungary in 2005. He is currently Associate Professor at the Óbuda University, John von Neumann Faculty of Informatics. His main research topics include image processing, machine vision and system identification.

Satoshi Tsuchiya : is a professor of Graduate School of Agriculture, Shizuoka University, was born in 1952. His current interests include the initiation of Landslide and Debris flow, Sediment movement.

Yoichi Takebayashi : is a professor of Graduate School of Informatics, Shizuoka University. He was born in 1951. His research interests widely cover human-centered information technologies, including smart interactive systems, multimodal knowledge creation and commonsense thinking.

 

 

 

 

 

 

 

Landslide

Multi-Camera Measurement

Monitoring

Hazard Prediction

Template Matching

In this paper a particular solution has been proposed for monitoring the motion of earth particles in order to predict events such as landslide or hazardous sediment movement. The approach is based on template matching with adaptive windows size. The size of the template is set according to the spread level of earth particles in order to enhance the reliability of matching. Since the tracked targets such as stones or larger earth particles may rotate, the observed surface patterns may significantly change. The problem can be particularly resolved by using multiple patterns corresponding to different views of tracked target. As the results reflect the proposed algorithms may be suitable for monitoring specific landslide related events to collect time series for supporting the early prediction of related hazards.

 

 

 

 

 

 

 

 

 

[1] H. Chen; Z. Zeng, "Deformation prediction of landslide based on genetic-simulated annealing algorithm and BP neural network," Fourth IEEE International Workshop on Advanced Computational Intelligence (IWACI), 19- 21 Oct. 2011, pp.675-679.

[2] X. Cui, X. Zhao, M. Ji, S. Wang, P. Zhang, "Research on landslide prediction based on support vector model," IEEE International Conference on Computer Design and Applications (ICCDA), 25-27 June 2010, vol.3, pp.V3-540-V3-544.

[3] R Wang; L. Nie, "Landslide prediction in Fushun west open pit mine area with quadratic curve exponential smoothing method," 18th International Conference on Geoinformatics, 18-20 June 2010, pp.1-6.

[4] S. Ghuffar; B. Székely, A. Roncat, N. Pfeifer, "Landslide Displacement Monitoring Using 3D Range Flow on Airborne and Terrestrial LiDAR Data," Remote Sensing, Vol. 5, No. 6, 2013, pp. 2720-2745.

[5] A. Abellán, J. M. Vilaplana, J. Calvet, D. García-Sellés and E. Asensio, "Rockfall monitoring by Terrestrial Laser Scanning – case study of the basaltic rock face at Castellfollit de la Roca (Catalonia, Spain)," Natural Hazards and Earth System Science, Vol. 11, No. 3, 2011, pp. 829-841.

[6] A. Prokop, H. Panholzer, "Assessing the Capability of Terrestrial Laser Scanning for Monitoring Slow Moving Landslides," Natural Hazards and Earth System Science, Vol. 9, No. 6, 2009, pp. 1921–1928.

[7] A. Rövid, T. Hashimoto, "On Local Stereo Matching for High Precision Measurement," International Journal of Engineering and Innovative Technology, Vol. 3, No. 10, April 2014, pp. 23-32.

[8] Liu, Yonghuai, "A Mean Field Annealing Approach to Accurate Free Form Shape Matching," Journal of Pattern Recognition, Vol. 40, Issue 9, ISSN: 0031-3203, pp. 2418-2436, 2007.

[9] Jian Sun, Nan-Ning Zheng, Heung-Yeung Shum, "Stereo matching using belief propagation, " IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 7, pp. 787–800, July 2003.

[10] M. Bleyer, M. Gelautz, "Graph-Cut-Based Stereo Matching Using Image Segmentation with Symmetrical Treatment of Occlusions," Signal Processing: Image Communication, Vol. 22, Issue 2, ISSN 0923-5965, pp. 127–143, Feb. 2007.

[11] Manzella, Irene and Labiouse, Vincent, "Empirical and analytical analyses of laboratory granular flows to investigate rock avalanche propagation," Landslides, Springer-Verlag Vol. 10, No. 1, pp. 23-36, 2013.

[12] Hungr, Oldrich and Leroueil, Serge and Picarelli, Luciano, "The Varnes classification of landslide types, an update," Landslides, Springer Berlin Heidelberg, Vol. 11, No. 2, pp. 167-194, 2014.