Abstract
A non-invasive Underwater Fish Observatory (UFO) was developed and deployed on the seafloor to perform continuous recording of stereo video and sonar data as well as various oceanic parameters at a high temporal sampling rate. The acquired image data is processed to automatically detect, classify and measure the size of passing aquatic organisms. An important subtask in this processing chain is the semantic segmentation of the previously detected animals. Within this publication, a former segmentation system, that only considered a binary classification of fish and background, is extended to a multi-class segmentation system by including an additional species. Since the images usually contain a lot of background, the semantic segmentation is a problem with a high class imbalance, which demands special care in the choice of loss functions and evaluation metrics. Therefore, three different loss functions, namely Dice loss, Focal loss and Lovasz loss, which are well suited for class-imbalance problems, are investigated and their effect on the final mean intersection-over-union (IoU) on a separate test set is explored. For the given dataset, the model trained with a Focal loss performed best achieving an average, class specific IoU of 0.982 for the background class, 0.828 for the Aurelia aurita and 0.678 for the Gadus morhua.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Geomar helmholtz centre for ocean research kiel. https://www.geomar.de/, Accessed 28 Mar 2022
Macartney germany gmbh. https://www.macartney.de/, Accessed 28 Mar 2022
rosemann software gmbh. https://www.camiq.net, Accessed 28 Mar 2022
Thuenen institute. https://www.thuenen.de, Accessed 28 Mar 2022
Abdeldaim, A.M., Houssein, E.H., Hassanien, A.E.: Color image segmentation of fishes with complex background in water. In: Hassanien, A.E., Tolba, M.F., Elhoseny, M., Mostafa, M. (eds.) AMLTA 2018. AISC, vol. 723, pp. 634–643. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-74690-6_62
Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017)
Berman, M., Triki, A.R., Blaschko, M.B.: The lovász-softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4413–4421 (2018)
Biewald, L.: Experiment tracking with weights and biases (2020). https://www.wandb.com/software available from wandb.com
Böer., G., Veeramalli., R., Schramm., H.: 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 - ROBOVIS, pp. 158–164. INSTICC, SciTePress (2021). https://doi.org/10.5220/0010712700003061
Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)
Dearden, P., Theberge, M., Yasué, M.: Using underwater cameras to assess the effects of snorkeler and scuba diver presence on coral reef fish abundance, family richness, and species composition. Environ. Monit. Assess. 163(1), 531–538 (2010)
Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)
Fernandes, A.F.: Deep learning image segmentation for extraction of fish body measurements and prediction of body weight and carcass traits in nile tilapia. Comput. Electron. Agric. 170, 105274 (2020)
Garcia, R.: Automatic segmentation of fish using deep learning with application to fish size measurement. ICES J. Marine Sci. 77(4), 1354–1366 (2020)
Güler, R.A., Neverova, N., Kokkinos, I.: Densepose: dense human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7297–7306 (2018)
Harvey, E.S., Santana-Garcon, J., Goetze, J., Saunders, B.J., Cappo, M.: The use of stationary underwater video for sampling sharks. In: Shark Research: Emerging Technologies and Applications for the Field and Laboratory, pp. 111–132 (2018)
He, K., Gkioxari, G., Dollár, P., Girshick, R.B.: Mask R-CNN. CoRR abs/1703.06870 (2017). http://arxiv.org/abs/1703.06870
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021)
Jaccard, P.: The distribution of the flora in the alpine zone. 1. New Phytologist 11(2), 37–50 (1912)
Kawabata, K., et al.: Underwater image gathering by utilizing stationary and movable sensor nodes: towards observation of symbiosis system in the coral reef of okinawa. Int. J. Distrib. Sensor Netw. 10(7), 835642 (2014)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Konovalov, D.A., Saleh, A., Efremova, D.B., Domingos, J.A., Jerry, D.R.: Automatic weight estimation of harvested fish from images. In: 2019 Digital Image Computing: Techniques and Applications (DICTA), pp. 1–7. IEEE (2019)
Längkvist, M., Kiselev, A., Alirezaie, M., Loutfi, A.: Classification and segmentation of satellite orthoimagery using convolutional neural networks. Remote Sens. 8(4), 329 (2016)
Letessier, T.B., Juhel, J.B., Vigliola, L., Meeuwig, J.J.: Low-cost small action cameras in stereo generates accurate underwater measurements of fish. J. Exp. Marine Biol. Ecol. 466, 120–126 (2015)
Li, L., Dong, B., Rigall, E., Zhou, T., Donga, J., Chen, G.: Marine animal segmentation. IEEE Trans. Circ. Syst. Video Technol. 32, 2303–2314 (2021)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Marchesan, M., Spoto, M., Verginella, L., Ferrero, E.A.: Behavioural effects of artificial light on fish species of commercial interest. Fisher. Res. 73(1–2), 171–185 (2005)
Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565–571. IEEE (2016)
Qin, H., Peng, Y., Li, X.: Foreground extraction of underwater videos via sparse and low-rank matrix decomposition. In: 2014 ICPR Workshop on Computer Vision for Analysis of Underwater Imagery, pp. 65–72. IEEE (2014)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Rosen, S., Holst, J.C.: Deepvision in-trawl imaging: sampling the water column in four dimensions. Fisher. Res. 148, 64–73 (2013)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Sekachev, B., et al.: opencv/cvat: v1.1.0 (2020). https://doi.org/10.5281/zenodo.4009388
Sorensen, T.A.: A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on danish commons. Biol. Skar. 5, 1–34 (1948)
Spampinato, C., Giordano, D., Di Salvo, R., Chen-Burger, Y.H.J., Fisher, R.B., Nadarajan, G.: Automatic fish classification for underwater species behavior understanding. In: Proceedings of the First ACM International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams, pp. 45–50 (2010)
Treml, M., et al.: Speeding up semantic segmentation for autonomous driving (2016)
Wilhelms, I., et al.: Atlas of length-weight relationships of 93 fish and crustacean species from the north sea and the north-east atlantic. Technical report, Johann Heinrich von Thünen Institute, Federal Research Institute for Rural \(\ldots \) (2013)
Williams, K., Lauffenburger, N., Chuang, M.C., Hwang, J.N., Towler, R.: Automated measurements of fish within a trawl using stereo images from a camera-trawl device (camtrawl). Methods Oceanogr. 17, 138–152 (2016)
Yadan, O.: Hydra - a framework for elegantly configuring complex applications. Github (2019). https://github.com/facebookresearch/hydra
Yakubovskiy, P.: Segmentation models pytorch (2020). https://github.com/qubvel/segmentation_models.pytorch
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Learning a discriminative feature network for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1857–1866 (2018)
Yu, C., et al.: Segmentation and measurement scheme for fish morphological features based on mask r-cnn. Inf. Process. Agric. 7(4), 523–534 (2020)
Zarco-Perello, S., Enríquez, S.: Remote underwater video reveals higher fish diversity and abundance in seagrass meadows, and habitat differences in trophic interactions. Sci. Rep. 9(1), 1–11 (2019)
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881–2890 (2017)
Acknowledgements
This work was in part financially supported by the German Federal Ministry of Food and Agriculture (BMEL), grant number 2819111618. The planning and construction, the sensor integration and the operation of the UFO has been realized by the MacArtney Germany GmbH [2]. All species identifications of imaged underwater organisms, as well as the biological accompanying studies, were carried out by the Helmholtz Centre for Ocean Research Kiel [1]. The administrative project coordination and validation of biophysical data was done by the Thuenen institute [4]. The recording of the camera data was realised using the CamIQ software, which has been supplied by the rosemann software GmbH [3].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Böer, G., Schramm, H. (2022). Semantic Segmentation of Marine Species in an Unconstrained Underwater Environment. In: Galambos, P., Kayacan, E., Madani, K. (eds) Robotics, Computer Vision and Intelligent Systems. ROBOVIS ROBOVIS 2020 2021. Communications in Computer and Information Science, vol 1667. Springer, Cham. https://doi.org/10.1007/978-3-031-19650-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-19650-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19649-2
Online ISBN: 978-3-031-19650-8
eBook Packages: Computer ScienceComputer Science (R0)