Multi-fish Detection And Tracking Using Track-mask Region Convolutional Neural Network

Deep learning has become more common in recent years due to its excellent results in many areas. This thesis primarily focuses on multi-fish detection and tracking methods in underwater videos. The existing multi-fish detection methods for underwater videos have a low detection rate and consumes...

Full description

Bibliographic Details
Main Author: Alshdaifat, Nawaf Farhan Fankur
Format: Thesis
Language:English
Published: 2023
Subjects:
Online Access:http://eprints.usm.my/60661/
http://eprints.usm.my/60661/1/NAWAF%20FARHAN%20FANKUR%20ALSHDAIFAT%20-%20TESIS24.pdf
_version_ 1848884506557153280
author Alshdaifat, Nawaf Farhan Fankur
author_facet Alshdaifat, Nawaf Farhan Fankur
author_sort Alshdaifat, Nawaf Farhan Fankur
building USM Institutional Repository
collection Online Access
description Deep learning has become more common in recent years due to its excellent results in many areas. This thesis primarily focuses on multi-fish detection and tracking methods in underwater videos. The existing multi-fish detection methods for underwater videos have a low detection rate and consumes time in the training and testing process due to the underwater conditions and the overfitting during training. Many multi-fish detection and tracking methods for underwater videos (based on deep learning) where low accuracy for multi-fish tracking and occlusion instances during multi-fish tracking leads to inability to distinguish edges, and inability to handle each detected object over time. Therefore, this research aims to improve and enhance methods for multi-fish detection and tracking in underwater videos based on the latest deep learning algorithms. The proposed improved multi-fish detection method involves three main steps: 1) Improving ResNet-101 backbone for better fish detection, 2) Enhancing the Region Proposal Network (RPN) method based on Faster R-CNN for multi-fish detection and 3) An improved multi-fish detection method in terms of accuracy and with a lower training and testing times by utilising the aforementioned methods. The proposed multi-fish tracking method (Track-Mask R-CNN) also exhibits similar enhanced characteristics compared to the state-of-art methods (using fish dataset). An accuracy of 86.7% and 78.9% have been achieved for the proposed multi-fish detection and tracking respectively.
first_indexed 2025-11-15T19:07:47Z
format Thesis
id usm-60661
institution Universiti Sains Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T19:07:47Z
publishDate 2023
recordtype eprints
repository_type Digital Repository
spelling usm-606612024-05-23T02:47:32Z http://eprints.usm.my/60661/ Multi-fish Detection And Tracking Using Track-mask Region Convolutional Neural Network Alshdaifat, Nawaf Farhan Fankur QA75.5-76.95 Electronic computers. Computer science Deep learning has become more common in recent years due to its excellent results in many areas. This thesis primarily focuses on multi-fish detection and tracking methods in underwater videos. The existing multi-fish detection methods for underwater videos have a low detection rate and consumes time in the training and testing process due to the underwater conditions and the overfitting during training. Many multi-fish detection and tracking methods for underwater videos (based on deep learning) where low accuracy for multi-fish tracking and occlusion instances during multi-fish tracking leads to inability to distinguish edges, and inability to handle each detected object over time. Therefore, this research aims to improve and enhance methods for multi-fish detection and tracking in underwater videos based on the latest deep learning algorithms. The proposed improved multi-fish detection method involves three main steps: 1) Improving ResNet-101 backbone for better fish detection, 2) Enhancing the Region Proposal Network (RPN) method based on Faster R-CNN for multi-fish detection and 3) An improved multi-fish detection method in terms of accuracy and with a lower training and testing times by utilising the aforementioned methods. The proposed multi-fish tracking method (Track-Mask R-CNN) also exhibits similar enhanced characteristics compared to the state-of-art methods (using fish dataset). An accuracy of 86.7% and 78.9% have been achieved for the proposed multi-fish detection and tracking respectively. 2023-09 Thesis NonPeerReviewed application/pdf en http://eprints.usm.my/60661/1/NAWAF%20FARHAN%20FANKUR%20ALSHDAIFAT%20-%20TESIS24.pdf Alshdaifat, Nawaf Farhan Fankur (2023) Multi-fish Detection And Tracking Using Track-mask Region Convolutional Neural Network. PhD thesis, Universiti Sains Malaysia.
spellingShingle QA75.5-76.95 Electronic computers. Computer science
Alshdaifat, Nawaf Farhan Fankur
Multi-fish Detection And Tracking Using Track-mask Region Convolutional Neural Network
title Multi-fish Detection And Tracking Using Track-mask Region Convolutional Neural Network
title_full Multi-fish Detection And Tracking Using Track-mask Region Convolutional Neural Network
title_fullStr Multi-fish Detection And Tracking Using Track-mask Region Convolutional Neural Network
title_full_unstemmed Multi-fish Detection And Tracking Using Track-mask Region Convolutional Neural Network
title_short Multi-fish Detection And Tracking Using Track-mask Region Convolutional Neural Network
title_sort multi-fish detection and tracking using track-mask region convolutional neural network
topic QA75.5-76.95 Electronic computers. Computer science
url http://eprints.usm.my/60661/
http://eprints.usm.my/60661/1/NAWAF%20FARHAN%20FANKUR%20ALSHDAIFAT%20-%20TESIS24.pdf