The Marine Debris Dataset for Forward-Looking Sonar Semantic Segmentation

Accurate detection and segmentation of marine debris is important for keeping the water bodies clean. This paper presents a novel dataset for marine debris segmentation collected using a Forward Looking Sonar (FLS). The dataset consists of 1868 FLS images captured using ARIS Explorer 3000 sensor. The objects used to produce this dataset contain typical house-hold marine debris and distractor marine objects (tires, hooks, valves,etc), divided in 11 classes plus a background class. Performance of state of the art semantic segmentation architectures with a variety of encoders have been analyzed on this dataset and presented as baseline results. Since the images are grayscale, no pre-trained weights have been used. Comparisons are made using Intersection over Union (IoU). The best performing model is Unet with ResNet34 backbone at 0.7481 mIoU.

[1]  Matias Valdenegro-Toro,et al.  Submerged marine debris detection with autonomous underwater vehicles , 2016, 2016 International Conference on Robotics and Automation for Humanitarian Applications (RAHA).

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

[3]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[5]  S. Negahdaripour,et al.  On feature extraction and region matching for forward scan sonar imaging , 2012, 2012 Oceans.

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

[7]  S. Negahdaripour,et al.  Forward-look 2-D sonar image formation and 3-D reconstruction , 2013, 2013 OCEANS - San Diego.

[8]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Eugenio Culurciello,et al.  LinkNet: Exploiting encoder representations for efficient semantic segmentation , 2017, 2017 IEEE Visual Communications and Image Processing (VCIP).

[10]  John A. Fawcett,et al.  A Template Matching Procedure for Automatic Target Recognition in Synthetic Aperture Sonar Imagery , 2010, IEEE Signal Processing Letters.

[11]  Yang Zhang,et al.  Segmentation, classification and modeling of two-dimensional forward-scan sonar imagery for efficient coding and synthesis , 2016, OCEANS 2016 MTS/IEEE Monterey.

[12]  Silvia Silva da Costa Botelho,et al.  Underwater place recognition using forward-looking sonar images: A topological approach , 2019, J. Field Robotics.

[13]  Yvan Petillot,et al.  Automated approach to classification of mine-like objects in sidescan sonar using highlight and shadow information , 2004 .

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

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

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

[17]  Antonio Torralba,et al.  LabelMe: A Database and Web-Based Tool for Image Annotation , 2008, International Journal of Computer Vision.

[18]  Tim Tiedemann,et al.  Concept of a Robotic System for Autonomous Coarse Waste Recycling , 2021, ICINCO.

[19]  A. Fullana,et al.  Marine debris occurrence and treatment: A review , 2016 .

[20]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[21]  Junaed Sattar,et al.  TrashCan: A Semantically-Segmented Dataset towards Visual Detection of Marine Debris , 2020, ArXiv.

[22]  Matias Valdenegro-Toro,et al.  Deep Neural Networks for Marine Debris Detection in Sonar Images , 2019, ArXiv.

[23]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.