Deep learning-based water segmentation for autonomous surface vessel

Mohd Adam, Muhammad Ammar and Ibrahim, Ahmad Imran and Zainal Abidin, Zulkifli and Mohd Zaki, Hasan Firdaus (2020) Deep learning-based water segmentation for autonomous surface vessel. In: 10th IGRSM International Conference and Exhibition on Geospatial & Remote Sensing, 20-21st October 2020, Kuala Lumpur.

	PDF - Published Version Restricted to Registered users only Download (955kB) | Request a copy
	PDF (SCOPUS) - Supplemental Material Restricted to Registered users only Download (244kB) | Request a copy

Abstract

Visual-based obstacle detection from an autonomous surface vessel (ASV) is a complex task due to high variance of scene properties such as different illumination and presence of reflections. One approach in implementing the task is through extracting waterlines to enable inferring of vessel orientation and obstacles presence. Classical computer vision algorithms for detection holds limitation in robustness and scalability. With recent breakthroughs in deep neural network architectures, vision-based object detection is seen to obtain high performance. In this work, the deep learning models based on Convolutional Neural Network (CNN) to implement binary semantic segmentation is studied. This architecture identifies each pixel to water and non-water classes. In purpose of benchmarking models, Fully Convolutional Network (FCN), SegNet and U-Net are trained on a publicly available dataset, IntCatch Vision Data Set (ICVDS), to evaluate the performance. From the experiments carried out, quantitative results show effectiveness of the models with accuracy all above 95.55% and lowest average speed of 11 frames per second. To improve, pre-trained networks (VGG 16, Resnet-50 and MobileNet) are used as a backbone, obtaining an improved accuracy above 98.14% with lowest inferring speed of 10 frame per second. Using the developed ASV, new dataset of 143 images called Malaysia ASV Dataset (MASVD) is collected, labelled and made publicly available. The trained models are tested with the newly collected dataset obtaining accuracy of 75%. The high accuracy performance shows potential for the models to be employed for collision avoidance algorithm in ASV navigation.

Item Type:	Conference or Workshop Item (Plenary Papers)
Additional Information:	7667/83658 Presentation was done via online
Uncontrolled Keywords:	Benchmarking, Convolution, Convolutional neural networks, Deep neural networks, Network architecture, Object detection, Obstacle detectors, Remote sensing, Semantics, Unmanned surface vehicles
Subjects:	T Technology > T Technology (General)
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering Kulliyyah of Engineering > Department of Mechatronics Engineering
Depositing User:	Dr Ahmad Imran Ibrahim
Date Deposited:	13 Oct 2020 12:23
Last Modified:	09 Nov 2020 15:15
URI:	http://irep.iium.edu.my/id/eprint/83658

Actions (login required)

View Item