A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis

Abstract

Visual analysis of complex fish habitats is an important step towards sustainable fisheries for human consumption and environmental protection. Deep Learning methods have shown great promise for scene analysis when trained on large-scale datasets. However, current datasets for fish analysis tend to focus on the classification task within constrained, plain environments which do not capture the complexity of underwater fish habitats. To address this limitation, we present DeepFish as a benchmark suite with a large-scale dataset to train and test methods for several computer vision tasks. The dataset consists of approximately 40 thousand images collected underwater from 20 \green{habitats in the} marine-environments of tropical Australia. The dataset originally contained only classification labels. Thus, we collected point-level and segmentation labels to have a more comprehensive fish analysis benchmark. These labels enable models to learn to automatically monitor fish count, identify their locations, and estimate their sizes. Our experiments provide an in-depth analysis of the dataset characteristics, and the performance evaluation of several state-of-the-art approaches based on our benchmark. Although models pre-trained on ImageNet have successfully performed on this benchmark, there is still room for improvement. Therefore, this benchmark serves as a testbed to motivate further development in this challenging domain of underwater computer vision. Code is available at: https://github.com/alzayats/DeepFish

arXiv comment10 pages, 5 figures, 3 tables, Accepted for Publication in Scientific Reports (Nature) 14 August 2020

References in corpus (1)

• Underwater Fish Detection with Weak Multi-Domain Supervision

Cited by in corpus (10)

• Fish Tracking, Counting, and Behaviour Analysis in Digital Aquaculture: A Comprehensive Survey
• Adaptive deep learning framework for robust unsupervised underwater image enhancement
• Semi-Supervised Visual Tracking of Marine Animals using Autonomous Underwater Vehicles
• Deep learning with self-supervision and uncertainty regularization to count fish in underwater images
• Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclustering
• Transfer learning with generative models for object detection on limited datasets
• Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy
• AQUA20: A Benchmark Dataset for Underwater Species Classification under Challenging Conditions
• How to Track and Segment Fish without Human Annotations: A Self-Supervised Deep Learning Approach
• Overcoming Annotation Bottlenecks in Underwater Fish Segmentation: A Robust Self-Supervised Learning Approach