Coordinate-Aware Mask R-CNN with Group Normalization: A underwater marine animal instance segmentation framework

Dewei Yi, Hasan Bayarov Ahmedov, Shouyong Jiang, Yiren Li, Sean Joseph Flinn, Paul G. Fernandes

Research output: Contribution to journalArticlepeer-review

24 Downloads (Pure)

Abstract

Unsustainable fishing, driven by bycatch and discards, harms marine ecosystems. Addressing this, we propose a Coordinate-Aware Mask R-CNN (CAM-RCNN) method to enhance fish detection in commercial trawls. Leveraging CoordConv and Group Normalization, our approach improves generalisation and stability. To tackle class imbalance, a compound Dice and cross-entropy loss is employed, and image data are enhanced through multi-scale retinex and colour restoration. Evaluating on two fishing datasets, CAM-RCNN excels in accuracy and generalisation, achieving the best Average Precision (AP) for instance mask and BBOX prediction in both source (39.7%, 40.2%) and target domains (24.4%, 24.2%). This method promotes sustainable fishing by selectively capturing desired fish, reducing harm to non-target species.

Original languageEnglish
Article number127488
JournalNeurocomputing
Volume583
Early online date6 Mar 2024
DOIs
Publication statusE-pub ahead of print - 6 Mar 2024

Keywords

  • Convolutional neural network (CNN)
  • Generalisability
  • Instance segmentation
  • Underwater dataset

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cognitive Neuroscience
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Coordinate-Aware Mask R-CNN with Group Normalization: A underwater marine animal instance segmentation framework'. Together they form a unique fingerprint.

Cite this