ASL Environmental Sciences Inc. was awarded with a Natural Sciences and Engineering Research Council (NSERC) Engage Grant to cooperate with the University of Victoria on the development of a new automated or semi-automated analysis tool for Acoustic Zooplankton Fish Profiler (AZFP) data.
Specifically, the AZFP provides high temporal and spatial resolution acoustic backscatter.
The grant will enable the collaboration to focus on developing methods to automatically detect and classify fish backscatter from AZFP data.
[smlsubform prepend=”GET THE SAFETY4SEA IN YOUR INBOX!” showname=false emailtxt=”” emailholder=”Enter your email address” showsubmit=true submittxt=”Submit” jsthanks=false thankyou=”Thank you for subscribing to our mailing list”]
The partnership on the project is between Dr. Alexandra Branzan Albu’s research group from the Electrical and Computer Engineering Department of the University of Victoria along with ASL acoustic and remote sensing specialists.
AZFP data will be provided by Dr. Stéphane Gauthier of the Department of Fisheries and Oceans Canada who will also bring expertise in the areas of fisheries acoustics, data analyses and interpretation.
Moreover, Dr Albu and her team are expects on this issue, as they have experience in computer vision and machine learning.
The traditional AZFP processing techniques depend on human vision and visualization methods. In the meantime, the application of automated techniques will provide the creation of unbiased classifications that will be based on shape, structure and pattern detection.
Concluding, detection algorithms will be tested and tuned on data sets containing well-defined fish schools such as the ones produced by Pacific Herring, a small pelagic coastal species abundant in British Columbia’s waters.
