Detecting Marine Species in Echograms via Traditional, Hybrid, and Deep Learning Frameworks

This paper provides a comprehensive comparative study of traditional, hybrid, and deep learning (DL) methods for detecting marine species in echograms. Acoustic backscatter data obtained from multi-frequency echosounders is visualized as echograms and typically interpreted by marine biologists via manual or semi-automatic methods, which are time-consuming. Challenges related to automatic echogram interpretation are the variable size and acoustic properties of the biological targets (marine life), along with significant inter-class similarities. Our study explores and compares three types of approaches that cover the entire range of machine learning methods. Based on our experimental results, we conclude that an end-to-end DL-based framework, that can be readily scaled to accommodate new species, is overall preferable to other learning approaches for echogram interpretation, even when only a limited number of annotated training samples is available.

[1]  Rodney D. Hale,et al.  Acoustic species identification in the Northwest Atlantic using digital image processing , 2000 .

[2]  Juho Mäkiö,et al.  A Joint Application of Fuzzy Logic Approximation and a Deep Learning Neural Network to Build Fish Concentration Maps Based on Sonar Data , 2019, CMIS.

[3]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  H. Kawamura,et al.  Discriminating fish species by an Echo sounder in a set-net using a CNN , 2017, 2017 21st Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES).

[5]  T. Stanton.  30 years of advances in active bioacoustics: A personal perspective , 2012 .

[6]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Yingfeng Cai,et al.  A Comparative Study of State-of-the-Art Deep Learning Algorithms for Vehicle Detection , 2019, IEEE Intelligent Transportation Systems Magazine.

[8]  Arnt-Børre Salberg,et al.  Acoustic classification in multifrequency echosounder data using deep convolutional neural networks , 2020 .

[9]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[10]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[11]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  J. Kiefer,et al.  Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[13]  Mark Fisher,et al.  JellyMonitor: automated detection of jellyfish in sonar images using neural networks , 2018, 2018 14th IEEE International Conference on Signal Processing (ICSP).

[14]  D. Lemon,et al.  Multiple-frequency moored sonar for continuous observations of zooplankton and fish , 2012, 2012 Oceans.

[15]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Alexandra Branzan Albu,et al.  A Deep Learning-based Framework for the Detection of Schools of Herring in Echograms , 2019, ArXiv.

[17]  Inmaculada Pulido-Calvo,et al.  Acoustic identification of small pelagic fish species in Chile using support vector machines and neural networks , 2010 .

[18]  Zhiguo Cao,et al.  Counting Fish in Sonar Images , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[19]  Pierre Petitgas,et al.  Standard protocols for the analysis of school based data from echo sounder surveys , 2000 .

[20]  Ariel G. Cabreira,et al.  Artificial neural networks for fish-species identification , 2009 .

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  Arnt-Børre Salberg,et al.  Machine intelligence and the data-driven future of marine science , 2020, ICES Journal of Marine Science.

[23]  Rolf J. Korneliussen,et al.  Acoustic identification of marine species using a feature library , 2016 .

[24]  Paul G. Fernandes,et al.  Classification of Southern Ocean krill and icefish echoes using random forests , 2016 .

[25]  Jianlong Li,et al.  Study on Echo Features and Classification Methods of Fish Species , 2018, 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP).

[26]  David G. Reid.  Report on Echo Trace Classification , 2000 .

[27]  Peyman Hosseinzadeh Kassani,et al.  A comparative study of deep learning architectures on melanoma detection. , 2019, Tissue & cell.

[28]  Derek Bradley,et al.  Adaptive Thresholding using the Integral Image , 2007, J. Graph. Tools.

[29]  S. Gauthier,et al.  Species composition and acoustic signatures of mesopelagic organisms in a subtropical convergence zone, the New Zealand Chatham Rise , 2014 .

[30]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Ichiro Aoki,et al.  Classification of fish schools based on evaluation of acoustic descriptor characteristics , 2009, Fisheries Science.

[32]  John K. Horne,et al.  Acoustic approaches to remote species identification: a review , 2000 .