Segmentation of Fish in Realistic Underwater Scenes using Lightweight Deep Learning Models

Gordon Böer, Rajesh Veeramalli, Hauke Schramm, Hauke Schramm

2021

Abstract

The semantic segmentation of fish in real underwater scenes is a challenging task and an important prerequisite for various processing steps. With a good segmentation result, it becomes possible to automatically extract the fish contour and derive morphological features, both of which can be used for species identification and fish biomass assessment. In this work, two deep learning models, DeepLabV3 and PSPNet, are investigated for their applicability to fish segmentation for a fish stock monitoring application with low light cameras. By pruning these networks and employing a different encoder, they become more suitable for systems with limited hardware, such as remotely operated or autonomously operated underwater vehicles. Both segmentation models are trained and evaluated on a novel dataset of underwater images showing Gadus morhua in its natural behavior. On a challenging test set, which includes fish recorded at difficult visibility conditions, the PSPNet performs best, and achieves an average pixel accuracy of 96.8% and an intersection-over-union between the predicted and the target mask of 73.8%. It achieves this with a very limited parameter set of 94,393 trainable parameters.

Paper Citation

in Harvard Style

Böer G., Veeramalli R. and Schramm H. (2021). Segmentation of Fish in Realistic Underwater Scenes using Lightweight Deep Learning Models. In Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS, ISBN 978-989-758-537-1, pages 158-164. DOI: 10.5220/0010712700003061

in Bibtex Style

@conference{robovis21,
author={Gordon Böer and Rajesh Veeramalli and Hauke Schramm},
title={Segmentation of Fish in Realistic Underwater Scenes using Lightweight Deep Learning Models},
booktitle={Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS,},
year={2021},
pages={158-164},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010712700003061},
isbn={978-989-758-537-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS,
TI - Segmentation of Fish in Realistic Underwater Scenes using Lightweight Deep Learning Models
SN - 978-989-758-537-1
AU - Böer G.
AU - Veeramalli R.
AU - Schramm H.
PY - 2021
SP - 158
EP - 164
DO - 10.5220/0010712700003061