Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

MOTION SALIENCY BASED GENERATIVE ADVERSARIAL NETWORK FOR UNDERWATER MOVING OBJECT SEGMENTATION

Abstract: 

The underwater moving object segmentation is a challenging task. The problems like absorbing, scattering and attenuation of light rays between the scene and the imaging platform degrades the visibility of image or video frames. Also, the back-scattering of light rays further increases the problem of underwater video analysis, because the light rays interact with underwater particles and scattered back to the sensor. In this paper, a novel Motion Saliency Based Generative Adversarial Network (GAN) for Underwater Moving Object Segmentation (MOS) is proposed. The proposed network comprises of both identity mapping and dense connections for underwater MOS. To the best of our knowledge, this is the first paper with the concept of GAN-based unpaired learning for MOS in underwater videos. Initially, current frame motion saliency is estimated using few initial video frames and current frame. Further, estimated motion saliency is given as input to the proposed network for foreground estimation. To examine the effectiveness of proposed network, the Fish4Knowledge underwater video dataset and challenging video categories of ChangeDetection.net-2014 datasets are considered. The segmentation accuracy of existing state-of-the-art methods are used for comparison with proposed approach in terms of average F-measure. From experimental results, it is evident that the proposed network shows significant improvement as compared to the existing state-of-the-art methods for MOS

up
0 users have voted:

Paper Details

Authors:
Prashant W. Patil, Omkar Thawakar, Akshay Dudhane, Subrahmanyam Murala
Submitted On:
15 September 2019 - 11:02am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Akshay Dudhane
Paper Code:
2587
Document Year:
2019
Cite

Document Files

Poster.pdf

(235)

Poster.pdf

(219)

Subscribe

[1] Prashant W. Patil, Omkar Thawakar, Akshay Dudhane, Subrahmanyam Murala, "MOTION SALIENCY BASED GENERATIVE ADVERSARIAL NETWORK FOR UNDERWATER MOVING OBJECT SEGMENTATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4621. Accessed: Sep. 19, 2020.
@article{4621-19,
url = {http://sigport.org/4621},
author = {Prashant W. Patil; Omkar Thawakar; Akshay Dudhane; Subrahmanyam Murala },
publisher = {IEEE SigPort},
title = {MOTION SALIENCY BASED GENERATIVE ADVERSARIAL NETWORK FOR UNDERWATER MOVING OBJECT SEGMENTATION},
year = {2019} }
TY - EJOUR
T1 - MOTION SALIENCY BASED GENERATIVE ADVERSARIAL NETWORK FOR UNDERWATER MOVING OBJECT SEGMENTATION
AU - Prashant W. Patil; Omkar Thawakar; Akshay Dudhane; Subrahmanyam Murala
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4621
ER -
Prashant W. Patil, Omkar Thawakar, Akshay Dudhane, Subrahmanyam Murala. (2019). MOTION SALIENCY BASED GENERATIVE ADVERSARIAL NETWORK FOR UNDERWATER MOVING OBJECT SEGMENTATION. IEEE SigPort. http://sigport.org/4621
Prashant W. Patil, Omkar Thawakar, Akshay Dudhane, Subrahmanyam Murala, 2019. MOTION SALIENCY BASED GENERATIVE ADVERSARIAL NETWORK FOR UNDERWATER MOVING OBJECT SEGMENTATION. Available at: http://sigport.org/4621.
Prashant W. Patil, Omkar Thawakar, Akshay Dudhane, Subrahmanyam Murala. (2019). "MOTION SALIENCY BASED GENERATIVE ADVERSARIAL NETWORK FOR UNDERWATER MOVING OBJECT SEGMENTATION." Web.
1. Prashant W. Patil, Omkar Thawakar, Akshay Dudhane, Subrahmanyam Murala. MOTION SALIENCY BASED GENERATIVE ADVERSARIAL NETWORK FOR UNDERWATER MOVING OBJECT SEGMENTATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4621