Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories

Autor: Jacopo Aguzzi, Emanuela Fanelli, Espen Johnsen, Vanesa López-Vázquez, Jose Manuel Lopez-Guede, Simone Marini
Přispěvatelé: Agencia Estatal de Investigación (España), Ministerio de Ciencia, Innovación y Universidades (España)
Jazyk: angličtina
Rok vydání: 2020
Předmět:
0106 biological sciences
Artificial intelligence
Aquatic Organisms
Computer science
Cabled observatories
Biodiversity
Video Recording
02 engineering and technology
lcsh:Chemical technology
computer.software_genre
01 natural sciences
Biochemistry
Analytical Chemistry
Observatory
0202 electrical engineering
electronic engineering
information engineering
lcsh:TP1-1185
Underwater
Instrumentation
artificial intelligence
cabled observatories
deep learning
machine learning
deep-sea fauna
Atomic and Molecular Physics
and Optics
Automatic image annotation
Deep-sea fauna
020201 artificial intelligence & image processing
Host (network)
Oceans and Seas
Context (language use)
Machine learning
Article
Animals
Humans
Marine ecosystem
14. Life underwater
Electrical and Electronic Engineering
Ecosystem
business.industry
010604 marine biology & hydrobiology
Deep learning
Image Enhancement
Pipeline (software)
Neural Networks
Computer
business
computer
Zdroj: Sensors; Volume 20; Issue 3; Pages: 726
Sensors (Basel, Switzerland)
Digital.CSIC. Repositorio Institucional del CSIC
instname
Sensors, Vol 20, Iss 3, p 726 (2020)
Sensors
ISSN: 1424-8220
2017-8786
DOI: 10.3390/s20030726
Popis: Special issue Imaging Sensor Systems for Analyzing Subsea Environment and Life).-- 25 pages, 8 figures, 4 tables, 1 appendix
An understanding of marine ecosystems and their biodiversity is relevant to sustainable use of the goods and services they offer. Since marine areas host complex ecosystems, it is important to develop spatially widespread monitoring networks capable of providing large amounts of multiparametric information, encompassing both biotic and abiotic variables, and describing the ecological dynamics of the observed species. In this context, imaging devices are valuable tools that complement other biological and oceanographic monitoring devices. Nevertheless, large amounts of images or movies cannot all be manually processed, and autonomous routines for recognizing the relevant content, classification, and tagging are urgently needed. In this work, we propose a pipeline for the analysis of visual data that integrates video/image annotation tools for defining, training, and validation of datasets with video/image enhancement and machine and deep learning approaches. Such a pipeline is required to achieve good performance in the recognition and classification tasks of mobile and sessile megafauna, in order to obtain integrated information on spatial distribution and temporal dynamics. A prototype implementation of the analysis pipeline is provided in the context of deep¿sea videos taken by one of the fixed cameras at the LoVe Ocean Observatory network of Lofoten Islands (Norway) at 260 m depth, in the Barents Sea, which has shown good classification results on an independent test dataset with an accuracy value of 76.18% and an area under the curve (AUC) value of 87.59%
This work was developed within the framework of the Tecnoterra (ICM-CSIC/UPC) and the following project activities: ARIM (Autonomous Robotic Sea-Floor Infrastructure for Benthopelagic Monitoring; MarTERA ERA-Net Cofound) and RESBIO (TEC2017-87861-R; Ministerio de Ciencia, Innovación y Universidades)
With the funding support of the ‘Severo Ochoa Centre of Excellence’ accreditation (CEX2019-000928-S), of the Spanish Research Agency (AEI)
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje