A novel morphometry-based protocol of automated video-image analysis for species recognition and activity rhythms monitoring in deep-sea fauna.

Jacopo Aguzzi,Ryoichi Iwase,Paolo Menesatti,Corrado Costa,Eva Ramirez-Llorda,Yoshihiro Fujiwara

doi:10.3390/s91108438

Abstract

The understanding of ecosystem dynamics in deep-sea areas is to date limited by technical constraints on sampling repetition. We have elaborated a morphometry-based protocol for automated video-image analysis where animal movement tracking (by frame subtraction) is accompanied by species identification from animals' outlines by Fourier Descriptors and Standard K-Nearest Neighbours methods. One-week footage from a permanent video-station located at 1,100 m depth in Sagami Bay (Central Japan) was analysed. Out of 150,000 frames (1 per 4 s), a subset of 10.000 was analyzed by a trained operator to increase the efficiency of the automated procedure. Error estimation of the automated and trained operator procedure was computed as a measure of protocol performance. Three displacing species were identified as the most recurrent: Zoarcid fishes (eelpouts), red crabs (Paralomis multispina), and snails (Buccinum soyomaruae). Species identification with KNN thresholding produced better results in automated motion detection. Results were discussed assuming that the technological bottleneck is to date deeply conditioning the exploration of the deep-sea.

Highlights

The identification of species and their behavioural rhythms in deep-water continental margins and deep-sea areas is of actual and elevated importance for fishery management and biodiversity estimation [1]
The use of video filming techniques for species recognition and behavioural study was attempted in coastal areas
The use of this technique for the study of behavioural rhythms remains to date largely underexploited at any depth, especially in the deep-sea

Summary

Introduction

The identification of species and their behavioural rhythms in deep-water continental margins and deep-sea areas is of actual and elevated importance for fishery management and biodiversity estimation [1]. Species rhythmic movements in relation to recognised geophysical cycles such as the fluctuations in light intensity (day-night based) or in hydrodynamism (internal-tide based) may bring animals in and out from punctual trawl sampling windows [3]. This phenomenon could consistently alter the estimation of species biomasses and areas of distribution of their populations [4]. The use of this technique for the study of behavioural rhythms remains to date largely underexploited at any depth, especially in the deep-sea The reasons for this are mainly related to the lack of automation in footage analysis. This obliges researchers to the manual examination of thousands of images [10,11]

Methods

Results

Discussion

Conclusion