Visual Rhythm-Based Method for Continuous Plankton Monitoring

Plankton microorganisms constitute the base of the marine food web and play a great role in global atmospheric carbon dioxide draw down. Moreover, being very sensitive to any environmental changes they allow noticing (and potentially counteracting) them faster than with any other means. As such they not only influence the fishery industry but are also frequently used to analyze changes in exploited coastal areas and the influence of these interferences on local environment and climate. As a consequence, there is a strong need for highly efficient systems allowing long time and large volume observation of plankton communities. The adopted sensors typically provide huge amounts of data that must be processed efficiently. This would provide us with better understanding of their role on global climate as well as help maintain the fragile environmental equilibrium. In this paper a new system for large volume plankton monitoring system is presented. It is based on visual analysis of small particles immersed in a water flux. The image sequences are analyzed with Visual Rhythm-based method which greatly accelerates the processing time and allows higher volume throughput. To assure maximal performance the algorithm was implemented using CUDA for GPGPU. The method was then tested on a large data set and compared with alternative frame-by-frame approach. The results prove that the method can be successfully applied for the large volume plankton monitoring problem, as well as in any other application where targets are to be detected and counted while moving in a unidirectional flux.

[1]  Hui Xiang,et al.  An Improved Graph-Based Image Segmentation Algorithm and Its GPU Acceleration , 2011, 2011 Workshop on Digital Media and Digital Content Management.

[2]  Tom Malone,et al.  A global continuous plankton recorder programme , 2010 .

[3]  Francisco Nivando Bezerra,et al.  Video transition detection using string matching: preliminary results , 2003, 16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003).

[4]  Marc Picheral,et al.  Digital zooplankton image analysis using the ZooScan integrated system , 2010 .

[5]  Josué Álvarez-Borrego,et al.  Comparative analysis of several digital methods to recognize diatoms , 2010 .

[6]  D. M. Kocak,et al.  Computer vision techniques for quantifying, tracking, and identifying bioluminescent plankton , 1999 .

[7]  Phil F. Culverhouse,et al.  Automatic image analysis of plankton: future perspectives , 2006 .

[8]  Patrick Horain,et al.  GPUCV: A Framework for Image Processing Acceleration with Graphics Processors , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[9]  E. Berdalet,et al.  Observational approaches to community structure, from microbes to zooplankton : Report of breakout group microbes and zooplankton , 2009 .

[10]  Teresa M. Mata,et al.  Microalgae for biodiesel production and other applications: A review , 2010 .

[11]  Roberto Marcondes Cesar Junior,et al.  Visual rhythm-based plankton detection method for ballast water quality assessment , 2012, 2012 19th IEEE International Conference on Image Processing.

[12]  Josué Álvarez-Borrego,et al.  Digital system of invariant correlation to position and rotation , 2010 .

[13]  I. Valiela.  Global Coastal Change , 2006 .

[14]  P. Utgoff,et al.  RAPID: Research on Automated Plankton Identification , 2007 .

[15]  Jr Strickler,et al.  Matched spatial filters in long working distance microscopy of phase objects , 1999 .

[16]  Min Gyo Chung,et al.  A scene boundary detection method , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).