Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/37229

Title: Underwater scene segmentation by deep neural network
Authors: Zhou, Yang
Wang, Jiangtao
Li, Baihua
Meng, Qinggang
Rocco, Emanuele
Saiani, Andrea
Issue Date: 2019
Citation: ZHOU, Y. ... et al., 2019. Underwater scene segmentation by deep neural network.Presented at the 2nd UK Robotics and Autonomous Systems Conference, (UK-RAS 2019), Loughborough University, 24th January.
Abstract: A deep neural network architecture is proposed in this paper for underwater scene semantic segmentation. The architecture consists of encoder and decoder networks. Pretrained VGG-16 network is used as a feature extractor, while the decoder learns to expand the lower resolution feature maps. The network applies max un-pooling operator to avoid large number of learnable parameters, and, in order to make use of the feature maps in encoder network, it concatenates the feature maps with decoder and encoder for lower resolution feature maps. Our architecture shows capabilities of faster convergence and better accuracy. To get a clear view of underwater scene, an underwater enhancement neural network architecture is described in this paper and applied for training. It speeds up the training process and convergence rate in training.
Description: This is a conference paper.
Sponsor: The authors are grateful to the EPSRC Centre for Doctoral Training in Embedded Intelligence under grant reference EP/L014998/1 for financial support sponsored by Witted Srl, Italy
Version: Published
URI: https://dspace.lboro.ac.uk/2134/37229
Publisher Link: https://www.ukras.org/wp-content/uploads/2019/03/UKRAS19-Proceedings-Final.pdf
Appears in Collections:Conference Papers and Presentations (Computer Science)

Files associated with this item:

File Description SizeFormat
UKRAS 2019-Yang.pdfPublished version422.98 kBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.