Abstract
Marine plankton abundance and dynamics in the open and interior ocean is still an unknown field. The knowledge of gelatinous zooplankton distribution is especially challenging, because this type of plankton has a very fragile structure and cannot be directly sampled using traditional net based techniques. To overcome this shortcoming, Computer Vision techniques can be successfully used for the automatic monitoring of this group.This paper presents the GUARD1 imaging system, a low-cost stand-alone instrument for underwater image acquisition and recognition of gelatinous zooplankton, and discusses the performance of three different methodologies, Tikhonov Regularization, Support Vector Machines and Genetic Programming, that have been compared in order to select the one to be run onboard the system for the automatic recognition of gelatinous zooplankton. The performance comparison results highlight the high accuracy of the three methods in gelatinous zooplankton identification, showing their good capability in robustly selecting relevant features. In particular, Genetic Programming technique achieves the same performances of the other two methods by using a smaller set of features, thus being the most efficient in avoiding computationally consuming preprocessing stages, that is a crucial requirement for running on an autonomous imaging system designed for long lasting deployments, like the GUARD1. The Genetic Programming algorithm has been installed onboard the system, that has been operationally tested in a two-months survey in the Ligurian Sea, providing satisfactory results in terms of monitoring and recognition performances.
Highlights
Automatic recognition of plankton is a rapid expanding field [1] and many approaches exist for the recognition and classification of micro-zooplankton specimens [2,3]
This paper presents the GUARD1 imaging system (EU patent application EP14188810) designed and developed for autonomous, long term and low-cost monitoring and recognition of gelatinous macro-zooplankton in order to assess their abundance and distribution
The proposed methodologies have been integrated with feature selection schemes for identifying the most suitable image features capable to discriminate jellies from other floating objects captured by the images, in order to optimize the recognition performances and the computational cost
Summary
Automatic recognition of plankton is a rapid expanding field [1] and many approaches exist for the recognition and classification of micro-zooplankton specimens [2,3]. Gelatinous zooplankton is a crucial actor in the trophic mesopelagic communities, with implications for the carbon cycle [5] and for fisheries, since it often competes with fish for food sources, and often is a critical indicator and driver of ecosystem performance and change [6]. The GUARD1 system uses a simple box-shaped moving average filter [52], with a box area of a size comparable with the size of expected objects (order of 20 pixels) This filter transforms the original image into a binary image that discriminates the image foreground from the image background. The foreground image regions (blobs) can be defined as the set of pixels with intensity value higher than the background and exceeding a given global threshold This filter has been efficiently implemented linearly in the number of pixels through the use of the integral image approach [53]. The information about the radiometric nature of the jellies, that appear brighter than the surround when illuminated, is used to tune the background/foreground segmenting filter
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
