Deep Learning-Based Fish Detection Using Above-Water Infrared Camera for Deep-Sea Aquaculture: A Comparison Study

Author:

Li Gen1234,Yao Zidan5,Hu Yu1234,Lian Anji1,Yuan Taiping1234,Pang Guoliang1234,Huang Xiaohua1234

Affiliation:

1. South China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Guangzhou 510300, China

2. Key Laboratory of Open-Sea Fishery Development, Ministry of Agriculture and Rural Affairs, Guangzhou 510300, China

3. Research and Development Center for Tropical Aquatic Products, South China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Sanya 572018, China

4. Sanya Tropical Fisheries Research Institute, Sanya 572018, China

5. School of Marine Engineering Equipment, Zhejiang Ocean University, Zhoushan 316022, China

Abstract

Long-term, automated fish detection provides invaluable data for deep-sea aquaculture, which is crucial for safe and efficient seawater aquafarming. In this paper, we used an infrared camera installed on a deep-sea truss-structure net cage to collect fish images, which were subsequently labeled to establish a fish dataset. Comparison experiments with our dataset based on Faster R-CNN as the basic objection detection framework were conducted to explore how different backbone networks and network improvement modules influenced fish detection performances. Furthermore, we also experimented with the effects of different learning rates, feature extraction layers, and data augmentation strategies. Our results showed that Faster R-CNN with the EfficientNetB0 backbone and FPN module was the most competitive fish detection network for our dataset, since it took a significantly shorter detection time while maintaining a high AP50 value of 0.85, compared to the best AP50 value of 0.86 being achieved by the combination of VGG16 with all improvement modules plus data augmentation. Overall, this work has verified the effectiveness of deep learning-based object detection methods and provided insights into subsequent network improvements.

Funder

Major Science and Technology Plan of Hainan Province

Hainan Province Science and Technology Special Fund

Central Public-interest Scientific Institution Basal Research Fund, South China Sea Fisheries Research Institute

Central Public-interest Scientific Institution Basal Research Fund

Publisher

MDPI AG

Reference34 articles.

1. Food and Agriculture Organization (2022). The State of World Fisheries and Aquaculture 2022 (SOFIA): Towards Blue Transformation, Food & Agriculture Organization of the United Nations (FAO).

2. A Global View of Aquaculture Policy;Naylor;Food Policy,2023

3. The Human Cost of Global Fishing;Willis;Mar. Policy,2023

4. Intelligent Monitoring and Control Technologies of Open Sea Cage Culture: A Review;Wei;Comput. Electron. Agric.,2020

5. Analyzing Industrialization of Deep-Sea Cage Mariculture in China: Review and Performance;Yu;Rev. Fish. Sci. Aquac.,2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3