Marine scientists use remote underwater video recording to survey fish species in their natural habitats. This helps them understand and predict how fish respond to climate change, habitat degradation, and fishing pressure. This information is essential for developing sustainable fisheries for human consumption, and for preserving the environment. However, the enormous volume of collected videos makes extracting useful information a daunting and time-consuming task for a human. A promising method to address this problem is the cutting-edge Deep Learning (DL) technology.DL can help marine scientists parse large volumes of video promptly and efficiently, unlocking niche information that cannot be obtained using conventional manual monitoring methods. In this paper, we provide an overview of the key concepts of DL, while presenting a survey of literature on fish habitat monitoring with a focus on underwater fish classification. We also discuss the main challenges faced when developing DL for underwater image processing and propose approaches to address them. Finally, we provide insights into the marine habitat monitoring research domain and shed light on what the future of DL for underwater image processing may hold. This paper aims to inform a wide range of readers from marine scientists who would like to apply DL in their research to computer scientists who would like to survey state-of-the-art DL-based underwater fish habitat monitoring literature.
A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis
James Cook University（詹姆斯库克大学）；University of British Columbia（不列颠哥伦比亚大学）；Element AI
对复杂鱼类生境的视觉分析是实现可持续渔业供人类消费和环境保护的重要一步。在大规模数据集上训练时，深度学习方法在景物分析方面表现出了巨大的潜力。然而，目前的鱼类分析数据集往往集中在有限的，平原环境中的分类任务，不捕捉水下鱼类栖息地的复杂性。为了解决这一限制，我们将DeepFish作为一个具有大规模数据集的基准套件，用于训练和测试几个计算机视觉任务的方法。该数据集包括从澳大利亚热带地区的20个\green{habitats in the}海洋环境中收集的大约4万张水下图像。数据集最初只包含分类标签。因此，我们收集了点级和分割标签，以获得更全面的鱼类分析基准。这些标签使模型能够学习自动监控鱼的数量，识别它们的位置并估计它们的大小。我们的实验提供了一个深入的分析数据集的特点，和性能评估的几个国家的最先进的方法的基础上，我们的基准。尽管在ImageNet上预训练的模型在这个基准测试中表现出色，但仍有改进的空间。因此，该基准作为一个测试平台，以激励在水下计算机视觉这一具有挑战性的领域的进一步发展。代码可在：https://github.com/alzayats/DeepFish
CUREE: A Curious Underwater Robot for Ecosystem Exploration
Woods Hole Oceanographic Institution (WHOI)（伍兹霍尔海洋研究所）；MIT-WHOI Joint Program in Oceanography/Applied Ocean Science and Engineering（麻省理工学院-伍兹霍尔海洋研究所海洋学/应用海洋科学与工程联合项目）
Overcoming Annotation Bottlenecks in Underwater Fish Segmentation: A Robust Self-Supervised Learning Approach
College of Science and Engineering, James Cook University（詹姆斯库克大学科学与工程学院）；ARC Research Hub for Supercharging Tropical Aquaculture through Genetic Solutions, James Cook University（詹姆斯库克大学ARC热带水产养殖基因解决方案研究中心）
Closer to Ground Truth: Realistic Shape and Appearance Labeled Data Generation for Unsupervised Underwater Image Segmentation
NORCE Norwegian Research Center AS（NORCE挪威研究中心）；National University of Science and Technology "Politehnica" Bucharest（布加勒斯特理工科学技术大学）；"Simion Stoilow" Institute of Mathematics of the Romanian Academy（罗马尼亚科学院西米翁斯托伊洛夫数学研究所）
EPANet: Efficient Path Aggregation Network for Underwater Fish Detection
Dalian Key Laboratory of Smart Fishery（大连智能渔业重点实验室）；College of Information Engineering, Dalian Ocean University（大连海洋大学信息工程学院）；Key Laboratory of Environment Controlled Aquaculture（环境可控水产养殖重点实验室）；Dalian Polytechnic University School of International Education（大连职业技术学院国际教育学院）
Deep learning with self-supervision and uncertainty regularization to count fish in underwater images
Universitat de Barcelona（巴塞罗那大学）；Universidade Federal de Santa Catarina（圣卡塔琳娜联邦大学）；Max Planck Institute of Animal Behavior（马克斯·普朗克动物行为研究所）；Universidade Federal do Paraná（巴拉那联邦大学）；Witwatersrand University（威特沃特斯兰德大学）；Oregon State University（俄勒冈州立大学）；University of Zurich（苏黎世大学）；Universitat Autonoma de Barcelona（巴塞罗那自治大学）
FinSight-Net:A Physics-Aware Decoupled Network with Frequency-Domain Compensation for Underwater Fish Detection in Smart Aquaculture
Dalian Key Laboratory of Smart Fishery（大连智能渔业重点实验室）；College of Information Engineering, Dalian Ocean University（大连海洋大学信息工程学院）；Key Laboratory of Environment Controlled Aquaculture（环境可控养殖重点实验室）；Dalian Polytechnic University School of International Education（大连职业技术学院国际教育学院）
Automated high-frequency quantification of fish communities and biomass using computer vision
Graduate School of Life Sciences, Tohoku University（东北大学生命科学研究生院）；Advanced Institute for Marine Ecosystem Change (WPI-AIMEC), Tohoku University（东北大学海洋生态系统变化先进研究所）；Graduate School of Science and Engineering, University of the Ryukyus（冲绳大学理学研究院）；Faculty of Science, University of the Ryukyus（冲绳大学理学部）
How to Track and Segment Fish without Human Annotations: A Self-Supervised Deep Learning Approach
College of Science and Engineering, James Cook University（詹姆斯库克大学科学与工程学院）；ARC Research Hub for Supercharging Tropical Aquaculture through Genetic Solutions, James Cook University（詹姆斯库克大学ARC热带水产养殖遗传解决方案研究中心）
Detecting Endangered Marine Species in Autonomous Underwater Vehicle Imagery Using Point Annotations and Few-Shot Learning
Australian Centre for Robotics, University of Sydney（悉尼大学澳大利亚机器人中心）；Marine Technology Department, Norwegian University of Science and Technology（挪威科技大学海洋技术系）；Institute for Marine and Antarctic Studies, University of Tasmania（塔斯马尼亚大学海洋与南极研究所）
How many labels do you need? A decision framework for cross-habitat marine species recognition
College of Science and Engineering, James Cook University（詹姆斯·库克大学科学与工程学院）；Centre for AI and Data Science Innovation, James Cook University（詹姆斯·库克大学人工智能与数据科学创新中心）
AquaFeat+: an Underwater Vision Learning-based Enhancement Method for Object Detection, Classification, and Tracking
Centro de Ciências Computacionais (C3), Universidade Federal do Rio Grande (FURG), Brazil（巴西里约格兰德联邦大学计算科学研究中心（C3））；Instituto de Ciências Exatas e Tecnologia (ICET), Universidade Federal do Amazonas (UFAM), Brazil（巴西亚马逊联邦大学精确科学与技术研究所（ICET））
Temperate Fish Detection and Classification: a Deep Learning based Approach
University of Agder (UiA)（阿格德大学）；Institute of Marine Research (IMR)（海洋研究所）
在海洋生态学的广泛应用中，广泛使用水下相机。尽管如此，为了有效地处理产生的大量数据，我们需要开发能够自动检测和识别胶片上捕获的物种的工具。在自然环境中从视频和图像中对鱼类进行分类可能具有挑战性，因为噪声和光照变化以及周围栖息地。在本文中，我们提出了一种两步深度学习方法，用于在没有预过滤的情况下检测和分类温带鱼类。第一步是检测图像中的每一条鱼，不受物种和性别的影响。为此，我们采用了You Only Look Once（YOLO）目标检测技术。在第二步中，我们采用了一个卷积神经网络（CNN）与挤压和激励（SE）架构的分类图像中的每一条鱼没有预过滤。我们采用迁移学习来克服温带鱼类训练样本有限的问题，提高分类的准确率。这是通过使用ImageNet训练目标检测模型和通过公共数据集（Fish 4Knowledge）训练鱼类分类器来完成的，因此目标检测和分类器都使用感兴趣的温带鱼类进行更新。从预训练获得的权重作为先验应用于后训练。我们的解决方案在预训练上达到了99.27%的最先进的准确率。训练后的准确率百分比值良好;在有和没有图像增强的情况下分别为83.68\%和87.74\%，这表明该解决方案在更广泛的数据集上是可行的。
A Survey of Fish Tracking Techniques Based on Computer Vision
College of Information and Electrical Engineering, China Agricultural University（中国农业大学信息与电气工程学院）；National Innovation Center for Digital Fishery, Ministry of Agriculture and Rural Affairs（农业农村部数字渔业创新中心）；College of Engineering, China Agricultural University（中国农业大学工学院）
A computer vision method to estimate ventilation rate of Atlantic salmon in sea fish farms
Coastal and Marine Research Centre, Australian Rivers Institute, Griffith University（格里菲斯大学澳大利亚河流研究所海岸与海洋研究中心）；Institute for Integrated and Intelligent Systems, School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院集成与智能系统研究所）；Blue Economy Cooperative Research Centre（蓝色经济合作研究中心）；Tassal Group（Tassal集团）
