Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

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

Circulating microRNAs as diagnostic biomarkers and pathogenic mediators in type 2 diabetic retinopathy: a systematic review.

Acta diabetologica·2026
Same author

Electronic Engineering of Donor-Acceptor Covalent Organic Frameworks via Fluorine Substitution for Efficient Solar Hydrogen Production.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Hemodynamic Assessment in Newborn Infants With Sepsis: A Prospective Observational Study.

Cureus·2026
Same author

Risk Factors Associated With Febrile Seizures in Young Children: Clinical, Biochemical, and Genetic Perspectives.

Cureus·2026
Same author

<i>Plasmodium vivax</i> malaria in India: microbiological barriers to diagnosis, treatment, and elimination.

Clinical microbiology reviews·2026
Same author

Ce-Doped SnO<sub>2</sub> Nanoparticles for Efficient Photocatalytic Degradation of Organic Dyes and Antibiotics Under Sunlight Exposure.

ChemPlusChem·2026

相关实验视频

Updated: Jun 6, 2025

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar
07:14

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar

Published on: May 1, 2018

7.7K

使用集体深度学习技术从合成孔径雷达图像中检测船只.

Himanshu Gupta1, Om Prakash Verma2, Tarun Kumar Sharma3

  • 1Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, 576104, Karnataka, India.

Scientific reports
|November 26, 2024
PubMed
概括

本研究介绍了YYOLO,这是用于合成孔径雷达 (SAR) 船舶检测的整体模型. eYOLO在SAR图像中有效识别各种尺寸的船只,改善海上监视和减少虚假报警.

关键词:
组合学习学习 组合学习船舶检测检测船只的检测.合成光圈雷达 (SAR) 是一种有权重的盒子核聚变.这是一个YOLO YOLO.

更多相关视频

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
06:25

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

8.4K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

470

相关实验视频

Last Updated: Jun 6, 2025

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar
07:14

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar

Published on: May 1, 2018

7.7K
Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
06:25

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

8.4K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

470

科学领域:

  • 遥感 遥感 遥感 遥感
  • 人工智能的人工智能
  • 海上安全 海上安全 海上安全

背景情况:

  • 合成开口雷达 (SAR) 对于海上监视至关重要,有助于交通管理,海盗侦测和防止非法捕捞.
  • 现有的SAR船只检测模型在规模差异和船只尺寸分布不均的情况下扎,导致对小型船只的不敏感性和虚假报警的增加.

研究的目的:

  • 开发一种有效的组合模型,用于SAR图像中的多尺度船舶检测.
  • 解决现有模型在准确识别不同尺寸的船舶方面的局限性.

主要方法:

  • 通过整合YOLOv4和YOLOv5架构,开发了YYOLO组合模型.
  • 使用加权盒融合,将YOLOv4和YOLOv5.5的输出结合起来.
  • 通过联合损失函数的概括交叉被用于增强模型的概括性和降低尺度灵敏度.

主要成果:

  • eYOLO 模型在多尺度船舶检测方面表现出高性能.
  • 在开源SAR-ship数据集上获得了91.49%的F1得分和92.00%的平均平均精度 (mAP).
  • 在各种规模检测船只方面超越现有方法.

结论:

  • 拟议的YyOLO模型对于SAR图像中的多尺度船舶检测是有效的.
  • 整体方法和普遍的 IoU 损失显著提高了检测精度,降低了尺度的灵敏度.
  • eYOLO为加强海上监视和安全提供了一个有前途的解决方案.