Automatic detection, identification and counting of anguilliform fish using in situ acoustic camera data: Development of a cross-camera morphological analysis approach

Acoustic cameras are increasingly used in monitoring studies of diadromous fish populations, even though analyzing them is time-consuming. In complex in situ contexts, anguilliform fish may be especially difficult to identify automatically using acoustic camera data because the undulation of their body frequently results in fragmented targets. Our study aimed to develop a method based on a succession of computer vision techniques, in order to automatically detect, identify and count anguilliform fish using data from multiple models of acoustic cameras. Indeed, several models of cameras, owning specific technical characteristics, are used to monitor fish populations, causing major differences in the recorded data shapes and resolutions. The method was applied to two large datasets recorded at two distinct monitoring sites with populations of European eels with different length distributions. The method yielded promising results for large eels, with more than 75% of eels automatically identified successfully using datasets from ARIS and BlueView cameras. However, only 42% of eels shorter than 60 cm were detected, with the best model performances observed for detection ranges of 4-9 m. Although improvements are required to compensate for fish-length limitations, our cross-camera method is promising for automatically detecting and counting large eels in long-term monitoring studies in complex environments.

[1]  Yaoguang Wei,et al.  Monitoring fish using imaging sonar: Capacity, challenges and future perspective , 2022, Fish and Fisheries.

[2]  R. Unsworth,et al.  Adaptive Resolution Imaging Sonar (ARIS) as a tool for marine fish identification , 2021 .

[3]  Robert P. Mueller,et al.  Deep Learning for Automated Detection and Identification of Migrating American Eel Anguilla rostrata from Imaging Sonar Data , 2021, Remote. Sens..

[4]  T. Linnansaari,et al.  Object and behavior differentiation for improved automated counts of migrating river fish using imaging sonar data , 2021 .

[5]  F. Bourrin,et al.  Movements of Non-Migrant European Eels in an Urbanised Channel Linking a Mediterranean Lagoon to the Sea , 2021, Water.

[6]  Jani Helminen,et al.  Length measurement accuracy of Adaptive Resolution Imaging Sonar (ARIS) and a predictive model to assess adult Atlantic salmon (Salmo salar) into two size categories with long-range data in a river. , 2020, Journal of fish biology.

[7]  R. V. Hal,et al.  Behavioural responses of eel ( Anguilla anguilla ) approaching a large pumping station with trash rack using an acoustic camera (DIDSON) , 2020 .

[8]  K. Kaifu,et al.  Increasing or decreasing? - Current status of the Japanese eel stock , 2019 .

[9]  C. Leone,et al.  Fish movements and schooling behavior across the tidal channel in a Mediterranean coastal lagoon: An automated approach using acoustic imaging , 2019, Fisheries Research.

[10]  J. Guillard,et al.  Manual fish length measurement accuracy for adult river fish using an acoustic camera (DIDSON). , 2019, Journal of fish biology.

[11]  T. McCarthy,et al.  Use of an acoustic camera to monitor seaward migrating silver-phase eels (Anguilla anguilla) in a regulated river , 2019, Ecohydrology & Hydrobiology.

[12]  Ludwig Bothmann,et al.  Realtime classification of fish in underwater sonar videos , 2016 .

[13]  Jean-Luc Baglinière,et al.  The use of acoustic cameras in shallow waters: new hydroacoustic tools for monitoring migratory fish population. A review of DIDSON technology , 2015 .

[14]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[15]  J. Hightower,et al.  Combining Split-Beam and Dual-Frequency Identification Sonars to Estimate Abundance of Anadromous Fishes in the Roanoke River, North Carolina , 2015 .

[16]  L. Beaulaton,et al.  Climbing back up what slippery slope? Dynamics of the European eel stock and its management in historical perspective , 2014 .

[17]  Jan Kubečka,et al.  Evaluation of potential bias in observing fish with a DIDSON acoustic camera , 2014 .

[18]  Emmanuelle Gouillart,et al.  scikit-image: image processing in Python , 2014, PeerJ.

[19]  K. Able,et al.  Application of Mobile Dual-frequency Identification Sonar (DIDSON) to Fish in Estuarine Habitats , 2014 .

[20]  Verena M. Trenkel,et al.  Underwater acoustics for ecosystem-based management: state of the science and proposals for ecosystem indicators , 2011 .

[21]  Steven J. Fleischman,et al.  Accuracy and Precision of Salmon Length Estimates Taken from DIDSON Sonar Images , 2010 .

[22]  Jun Han,et al.  Automated acoustic method for counting and sizing farmed fish during transfer using DIDSON , 2009, Fisheries Science.

[23]  T. Mulligan,et al.  Classifying Sonar Images: Can a Computer-Driven Process Identify Eels? , 2008 .

[24]  Suzanne L. Maxwell,et al.  Assessing a dual-frequency identification sonars' fish-counting accuracy, precision, and turbid river range capability. , 2007, The Journal of the Acoustical Society of America.

[25]  Ferdinand van der Heijden,et al.  Efficient adaptive density estimation per image pixel for the task of background subtraction , 2006, Pattern Recognit. Lett..

[26]  Sylvie Dufour,et al.  The silvering process of Anguilla anguilla: a new classification from the yellow resident to the silver migrating stage , 2005 .

[27]  Zoran Zivkovic,et al.  Improved adaptive Gaussian mixture model for background subtraction , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[28]  B. Jonsson,et al.  A 13-year study of the population dynamics and growth of the European eel Anguilla anguilla in a Norwegian river: evidence for density-dependent mortality, and development of a model for predicting yield , 1988 .

[29]  Patrick Shen-Pei Wang,et al.  A comment on “a fast parallel algorithm for thinning digital patterns” , 1986, CACM.

[30]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[31]  Jong-Sen Lee,et al.  Digital Image Enhancement and Noise Filtering by Use of Local Statistics , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  J. Parsons,et al.  Relationship between elver recruitment and changes in the sex ratio of silver eels Anguilla anguilla L. migrating from Lough Neagh, Northern Ireland , 1977 .

[33]  E. Faliex,et al.  In situ evaluation of European eel counts and length estimates accuracy from an acoustic camera (ARIS) , 2020, Knowledge and Management of Aquatic Ecosystems.

[34]  C. Wagner,et al.  Downstream migration dynamics of female and male silver eels (Anguilla anguilla L.) in the regulated German lowland Warnow River , 2014 .

[35]  P. Sasal,et al.  Silver eel population size and escapement in a Mediterranean lagoon: Bages-Sigean, France , 2008 .

[36]  James D. Miller,et al.  Fishery Data Series No . 07-44 Evaluation of a Dual-Frequency Imaging Sonar for Detecting and Estimating the Size of Migrating Salmon , 2007 .

[37]  J. Holmes,et al.  Accuracy and precision of fish-count data from a “dual-frequency identification sonar” (DIDSON) imaging system , 2006 .

[38]  E. John Simmonds,et al.  Fisheries Acoustics , 1992, Fish & Fisheries Series.