Deep Semantic Segmentation in an AUV for Online Posidonia Oceanica Meadows Identification

Recent studies have shown evidence of a significant decline of the Posidonia oceanica (P.O.) meadows on a global scale. The monitoring and mapping of these meadows are fundamental tools for measuring their status. We present an approach based on a deep neural network to automatically perform a high-precision semantic segmentation of the P.O. meadows in sea-floor images, offering several improvements over the state-of-the-art techniques. Our network demonstrates outstanding performance over diverse test sets, reaching a precision of 96.57% and an accuracy of 96.81%, surpassing the reliability of labeling the images manually. Moreover, the network is implemented in an autonomous underwater vehicle, performing an online P.O. segmentation, which will be used to generate real-time semantic coverage maps.

[1]  Seymour Geisser,et al.  The Predictive Sample Reuse Method with Applications , 1975 .

[2]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[3]  Ron Kohavi,et al.  The Case against Accuracy Estimation for Comparing Induction Algorithms , 1998, ICML.

[4]  A. Buja,et al.  Loss Functions for Binary Class Probability Estimation and Classification: Structure and Applications , 2005 .

[5]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[6]  Alan K. Mackworth,et al.  Artificial Intelligence , 2010 .

[7]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[8]  Núria Marbà,et al.  Mediterranean warming triggers seagrass (Posidonia oceanica) shoot mortality , 2009 .

[9]  G. Pergent,et al.  Seagrass (Posidonia oceanica) monitoring in western Mediterranean: implications for management and conservation , 2010, Environmental monitoring and assessment.

[10]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[11]  V. Parravicini,et al.  Evaluating change in seagrass meadows: A time-framed comparison of Side Scan Sonar maps , 2013 .

[12]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[13]  Nikola Miskovic,et al.  Monitoring of seagrass by lightweight AUV: A Posidonia oceanica case study surrounding Murter island of Croatia , 2014, 22nd Mediterranean Conference on Control and Automation.

[14]  Fabio Bruno,et al.  PILOT APPLICATION OF 3D UNDERWATER IMAGING TECHNIQUES FOR MAPPING POSIDONIA OCEANICA (L.) DELILE MEADOWS , 2015 .

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

[16]  T. Komatsu,et al.  Simulation of seagrass bed mapping by satellite images based on the radiative transfer model , 2015, Ocean Science Journal.

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

[18]  Michele Gristina,et al.  Seagrass meadows (Posidonia oceanica) distribution and trajectories of change , 2015, Scientific Reports.

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

[20]  Francesco Visin,et al.  A guide to convolution arithmetic for deep learning , 2016, ArXiv.

[21]  Antoni Burguera,et al.  Machine learning and deep learning strategies to identify Posidonia meadows in underwater images , 2017, OCEANS 2017 - Aberdeen.

[22]  Geoff Nitschke,et al.  Improving Deep Learning using Generic Data Augmentation , 2017 .

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

[24]  Antoni Burguera,et al.  Visual Discrimination and Large Area Mapping of Posidonia Oceanica Using a Lightweight AUV , 2017, IEEE Access.

[25]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Francisco Bonin-Font,et al.  USBL Integration and Assessment in a Multisensor Navigation Approach for AUVs , 2017 .

[27]  Roberto Cipolla,et al.  MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving , 2016, 2018 IEEE Intelligent Vehicles Symposium (IV).

[28]  Eduard Vidal,et al.  Sparus II AUV—A Hovering Vehicle for Seabed Inspection , 2018, IEEE Journal of Oceanic Engineering.

[29]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.