Expert, Crowd, Students or Algorithm: who holds the key to deep-sea imagery ‘big data’ processing?

Type Article
Date 2017-08
Language English
Author(s) Matabos MarjolaineORCID1, Hoeberechts Maia2, 3, Doya Carol4, Aguzzi Jacopo4, Nephin Jessica2, Reimchen Thomas E.5, Leaver Steve5, Marx Roswitha M.5, Albu Alexandra Branzan3, 6, Fier Ryan6, Fernandez-Arcaya Ulla4, Juniper S. Kim2, 5, 7
Affiliation(s) 1 : IFREMER, Ctr Bretagne, REM EEP, Lab Environm Profond, F-29280 Plouzane, France.
2 : Univ Victoria, Ocean Networks Canada, Victoria, BC V8W 2Y2, Canada.
3 : Univ Victoria, Dept Comp Sci, Victoria, BC, Canada.
4 : CSIC, Inst Marine Sci ICM, Paseo Maritimo Barceloneta 37-49, E-08003 Barcelona, Spain.
5 : Univ Victoria, Dept Biol, Victoria, BC, Canada.
6 : Univ Victoria, Dept Elect & Comp Engn, Victoria, BC, Canada.
7 : Univ Victoria, Sch Earth & Ocean Sci, Victoria, BC, Canada.
Source Methods In Ecology And Evolution (2041-210X) (Wiley), 2017-08 , Vol. 8 , N. 8 , P. 996-1004
DOI 10.1111/2041-210X.12746
WOS© Times Cited 24
Keyword(s) computer vision algorithms, crowdsourcing, deep-sea imagery, Digital Fishers, fish counting, OceanNetworks Canada, seafloor observatories, underwater video
Abstract 1.Recent technological development has increased our capacity to study the deep sea and the marine benthic realm, particularly with the development of multidisciplinary seafloor observatories. Since 2006, Ocean Networks Canada cabled observatories, have acquired nearly 65 TB and over 90,000 hours of video data from seafloor cameras and Remotely Operated Vehicles (ROVs). Manual processing of these data is time-consuming and highly labour-intensive, and cannot be comprehensively undertaken by individual researchers. These videos are a crucial source of information for assessing natural variability and ecosystem responses to increasing human activity in the deep sea.

2.We compared the performance of three groups of humans and one computer vision algorithm in counting individuals of the commercially important sablefish (or black cod) Anoplopoma fimbria, in recorded video from a cabled camera platform at 900 m depth in a submarine canyon in the Northeast Pacific. The first group of human observers were untrained volunteers recruited via a crowdsourcing platform and the second were experienced university students, who performed the task for their ichthyology class. Results were validated against counts obtained from a scientific expert.

3.All groups produced relatively accurate results in comparison to the expert and all succeeded in detecting patterns and periodicities in fish abundance data. Trained volunteers displayed the highest accuracy and the algorithm the lowest.

4.As seafloor observatories increase in number around the world, this study demonstrates the value of a hybrid combination of crowdsourcing and computer vision techniques as a tool to help process large volumes of imagery to support basic research and environmental monitoring. Reciprocally, by engaging large numbers of online participants in deep-sea research, this approach can contribute significantly to ocean literacy and informed citizen input to policy development.
Full Text
File Pages Size Access
Author's final draft 33 1 MB Open access
1 MB Access on demand
2 MB Access on demand
1 MB Access on demand
14 1 MB Access on demand
9 1 MB Access on demand
Top of the page

How to cite 

Matabos Marjolaine, Hoeberechts Maia, Doya Carol, Aguzzi Jacopo, Nephin Jessica, Reimchen Thomas E., Leaver Steve, Marx Roswitha M., Albu Alexandra Branzan, Fier Ryan, Fernandez-Arcaya Ulla, Juniper S. Kim (2017). Expert, Crowd, Students or Algorithm: who holds the key to deep-sea imagery ‘big data’ processing? Methods In Ecology And Evolution, 8(8), 996-1004. Publisher's official version : , Open Access version :