Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Accelerating Active Learning for Image Classification Through FPGA-Based Implementation.

Sensors (Basel, Switzerland)·2026

Same author

High-Accuracy Deep Learning-Based Detection and Classification Model in Color-Shift Keying Optical Camera Communication Systems.

Sensors (Basel, Switzerland)·2025

Same author

Development and Application of an Optoelectronic Sensor for Flame Monitoring of a Copper Concentrate Flash Burner.

Sensors (Basel, Switzerland)·2025

Same author

The feeding mode effect: influence on particle ingestion by four invertebrates from Sub-Antarctic and Antarctic waters.

Environmental science and pollution research international·2025

Same author

First report of Patagonian toothfish (Dissostichus eleginoides) metabolic rate and its scaling on a surface culture system.

Brazilian journal of biology = Revista brasleira de biologia·2025

Same author

The Genomic Signature and Transcriptional Response of Metal Tolerance in Brown Trout Inhabiting Metal-Polluted Rivers.

Molecular ecology·2024

Search research articles

相关实验视频

Updated: Jul 11, 2025

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Published on: November 20, 2017

一种基于深度学习的空间光谱分类方法,用于控制智利海底鱼的着陆量.

Jorge E Pezoa¹, Diego A Ramírez¹, Cristofher A Godoy¹

¹Department of Electrical Engineering, Universidad de Concepción, Concepción 4070409, Chile.

Sensors (Basel, Switzerland)

|November 14, 2023

概括

一种新的深度学习方法使用红-绿-蓝 (RGB) 图像和可见和近红外 (VIS-NIR) 频谱,以超过94%的准确性对智利五种主要的海底鱼类进行分类,有助于可持续的渔业管理.

关键词:

这是VIS-NIR.深度学习是一种深度学习.鱼类鱼类鱼类鱼类的鱼类鱼类.超光谱成像技术的使用.图像处理是图像处理的过程.机器学习是机器学习.

更多相关视频

A Standardized Procedure for Monitoring Harmful Algal Blooms in Chile by Metabarcoding Analysis

A Standardized Procedure for Monitoring Harmful Algal Blooms in Chile by Metabarcoding Analysis

Published on: August 26, 2021

Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information

Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information

Published on: June 13, 2020

相关实验视频

Last Updated: Jul 11, 2025

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Published on: November 20, 2017

A Standardized Procedure for Monitoring Harmful Algal Blooms in Chile by Metabarcoding Analysis

A Standardized Procedure for Monitoring Harmful Algal Blooms in Chile by Metabarcoding Analysis

Published on: August 26, 2021

Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information

Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information

Published on: June 13, 2020

科学领域:

海洋生物学和生态学
人工智能和机器学习
渔业科学与管理渔业科学与管理

背景情况:

过度开发鱼类资源威胁到海洋生态系统和渔业.
准确监测鱼类的着陆对于可持续的资源管理和配额执行至关重要.
目前用于鱼类物种识别的方法可能是劳动密集型的,容易出错.

研究的目的:

开发和评估基于深度学习的空间光谱方法,用于分类五种重要的海底鱼类物种.
评估这种方法在智利渔业中对鱼类着陆量进行自动监测的潜力.
提高鱼类物种识别用于渔业管理的准确性和效率.

主要方法:

采用了具有两个处理通道的卷积神经网络 (CNN) 架构.
美国有线电视新闻网处理了鱼样的红绿蓝 (RGB) 图像和可见和近红外 (VIS-NIR) 反射频谱.
五种海上鱼类物种被分类,包括Engraulis ringens,Merluccius gayi,Strangomera bentincki,Normanichthtys crockeri和Stromateus stellatus.

主要成果:

拟议的深度学习模型在所有性能指标上实现了超过94%的分类准确性.
与现有的最先进的技术相比,空间光谱方法显示出更高的性能.
该方法成功地区分了目标和非目标鱼类.

结论:

开发的深度学习方法显示了自动化,准确的鱼类物种分类的巨大潜力.
这项技术可以帮助有效监测鱼类的着陆量,并确保遵守捕捞配额.
实施这种方法可以促进海洋资源的可持续管理.