High throughput analysis of plankton morphology and dynamic

Changes in morphology and swimming dynamics of plankton by exposure to toxic chemicals are studied using a novel a new paradigm of image acquisition and computer vision system. Single cell ciliate Stentor coeruleus enclosed in a drop of water provide a means to automatically deposit many individual samples on a at surface. Chemicals of interest are automatically added to each drop while the dynamical and morphological changes are captured with an optical microscope. With computer vision techniques, we analyze the motion trajectory of each plankton sample, along with its shape information, quantifying the sub-lethal impact of chemicals on plankton health. The system enables large screening of hundreds of chemicals of environmental interest which may make their way into water habitats.

[1]  V. Tartar Reactions of Stentor coeruleus to certain substances added to the medium. , 1957, Experimental cell research.

[2]  Allen R. Hanson,et al.  Automatic In Situ Identification of Plankton , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[3]  Robert J. Olson,et al.  Automated taxonomic classification of phytoplankton sampled with imaging‐in‐flow cytometry , 2007 .

[4]  Darwin G. Caldwell,et al.  A fast and precise micropipette positioning system based on continuous camera-robot recalibration and visual servoing , 2009, 2009 IEEE International Conference on Automation Science and Engineering.

[5]  Bruce A. Draper,et al.  Visual object tracking using adaptive correlation filters , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Harold W. Kuhn,et al.  The Hungarian method for the assignment problem , 1955, 50 Years of Integer Programming.

[7]  Guangrong Ji,et al.  ZooplanktoNet: Deep convolutional network for zooplankton classification , 2016, OCEANS 2016 - Shanghai.

[8]  Anna Freud,et al.  Design And Analysis Of Modern Tracking Systems , 2016 .