Development of Coral Investigation System Based on Semantic Segmentation of Single-Channel Images

Among aquatic biota, corals provide shelter with sufficient nutrition to a wide variety of underwater life. However, a severe decline in the coral resources can be noted in the last decades due to global environmental changes causing marine pollution. Hence, it is of paramount importance to develop and deploy swift coral monitoring system to alleviate the destruction of corals. Performing semantic segmentation on underwater images is one of the most efficient methods for automatic investigation of corals. Firstly, to design a coral investigation system, RGB and spectral images of various types of corals in natural and artificial aquatic sites are collected. Based on single-channel images, a convolutional neural network (CNN) model, named DeeperLabC, is employed for the semantic segmentation of corals, which is a concise and modified deeperlab model with encoder-decoder architecture. Using ResNet34 as a skeleton network, the proposed model extracts coral features in the images and performs semantic segmentation. DeeperLabC achieved state-of-the-art coral segmentation with an overall mean intersection over union (IoU) value of 93.90%, and maximum F1-score of 97.10% which surpassed other existing benchmark neural networks for semantic segmentation. The class activation map (CAM) module also proved the excellent performance of the DeeperLabC model in binary classification among coral and non-coral bodies.

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

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

[3]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Rizwan Ali Naqvi,et al.  Learning Medical Image Denoising with Deep Dynamic Residual Attention Network , 2020, Mathematics.

[5]  S. Negahdaripour,et al.  Development and application of a video-mosaic survey technology to document the status of coral reef communities , 2007, Environmental monitoring and assessment.

[6]  Lionel Camus,et al.  Underwater hyperspectral classification of deep sea corals exposed to 2-methylnaphthalene , 2019, PloS one.

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  T. Done,et al.  Quantitative video sampling of coral reef benthos: large-scale application , 1995, Coral Reefs.

[9]  Chris Roelfsema,et al.  Towards Automated Annotation of Benthic Survey Images: Variability of Human Experts and Operational Modes of Automation , 2015, PloS one.

[10]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[11]  Martin Ludvigsen,et al.  Shallow-Water Habitat Mapping using Underwater Hyperspectral Imaging from an Unmanned Surface Vehicle: A Pilot Study , 2019, Remote. Sens..

[12]  Dejun Zhang,et al.  Single spectral imagery and faster R-CNN to identify hazardous and noxious substances spills. , 2019, Environmental pollution.

[13]  Liang-Gee Chen,et al.  Fast video segmentation algorithm with shadow cancellation, global motion compensation, and adaptive threshold techniques , 2004, IEEE Transactions on Multimedia.

[14]  Morgan S. Pratchett,et al.  Diversity and functional importance of coral‐feeding fishes on tropical coral reefs , 2008 .

[15]  Christophe Delacourt,et al.  Detection of changes in shallow coral reefs status: Towards a spatial approach using hyperspectral and multispectral data , 2019, Ecological Indicators.

[16]  Giovanni Chimienti,et al.  Underwater Hyperspectral Imaging for seafloor and benthic habitat mapping , 2018, 2018 IEEE International Workshop on Metrology for the Sea; Learning to Measure Sea Health Parameters (MetroSea).

[17]  B. Deronde,et al.  Mapping of coral reefs using hyperspectral CASI data; a case study: Fordata, Tanimbar, Indonesia , 2008 .

[18]  Serge Andréfouët,et al.  Spectral reflectance of coral reef bottom-types worldwide and implications for coral reef remote sensing , 2003 .

[19]  N. Kanopoulos,et al.  Design of an image edge detection filter using the Sobel operator , 1988 .

[20]  F. Su,et al.  Using Landsat Data to Detect Change in Live to Recently (<6 Months) Dead Coral Cover in the Western Xisha Islands, South China Sea , 2020 .

[21]  Rafael García,et al.  Image-Based Coral Reef Classification and Thematic Mapping , 2013, Remote. Sens..

[22]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[23]  M. Yasué,et al.  Using underwater cameras to assess the effects of snorkeler and SCUBA diver presence on coral reef fish abundance, family richness, and species composition , 2010, Environmental monitoring and assessment.

[24]  宋 宏 Song Hong,et al.  Development of an underwater spectral imaging system based on LCTF , 2020 .

[25]  Larry S. Davis,et al.  A survey of edge detection techniques , 1975 .

[26]  Woong-Kee Loh,et al.  Artificial Intelligence-based Semantic Segmentation of Ocular Regions for Biometrics and Healthcare Applications , 2020, Computers, Materials & Continua.

[27]  Aksel Alstad Mogstad,et al.  Spectral characteristics of coralline algae: a multi-instrumental approach, with emphasis on underwater hyperspectral imaging , 2017 .

[28]  George Papandreou,et al.  DeeperLab: Single-Shot Image Parser , 2019, ArXiv.

[29]  Michael S. Lew,et al.  Deep learning for visual understanding: A review , 2016, Neurocomputing.

[30]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[31]  Nikolaos Doulamis,et al.  Deep Learning for Computer Vision: A Brief Review , 2018, Comput. Intell. Neurosci..

[32]  Importance of live coral habitat for reef fishes , 2014, Reviews in Fish Biology and Fisheries.

[33]  Eric A. Hoffman,et al.  Tensor scale-based anisotropic region growing for segmentation of elongated biological structures , 2012, 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI).

[34]  Erik Valdemar Cuevas Jiménez,et al.  A novel multi-threshold segmentation approach based on differential evolution optimization , 2010, Expert Syst. Appl..

[35]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[36]  Muhammad Suzuri Hitam,et al.  Modification of canny edge detection for coral reef components estimation distribution from underwater video transect , 2017, 2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[37]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[38]  Hui Huang,et al.  Classification of Freshwater Zooplankton by Pre-trained Convolutional Neural Network in Underwater Microscopy , 2020 .

[39]  Suchendra M. Bhandarkar,et al.  A Comparison of Deep Learning Methods for Semantic Segmentation of Coral Reef Survey Images , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[40]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Iasonas Kokkinos,et al.  Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs , 2014, ICLR.

[43]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Le Doan Dung.  The status of coral reefs in central Vietnam's coastal water under climate change , 2020, Aquatic Ecosystem Health and Management.

[45]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.