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

Tandem Mass Spectrometry01:21

Tandem Mass Spectrometry

Tandem mass spectrometry is a technique that uses multiple mass analyzers in series to obtain a higher selectivity and reduce chemical noise during analyte detection. Instruments with multiple analyzers separated by an interaction cell enable secondary fragmentation and selected study of the fragment ions.Secondary fragmentations occur in the interaction cell and can be induced by various factors. Fragmentation induced by collision with inert gases, such as N2, Ar, He, etc., is called...

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

Optimized fetal head circumference estimation in 2D ultrasound using EfficientNet-B7 and Adam optimizer.

BMC pediatrics·2026
Same author

Integrative framework for cancer detection via integro-differential equations using deep learning techniques.

Scientific reports·2026
Same author

Hybrid Fennec Fox-Sand Cat optimized cascaded ANFIS MPPT for enhanced control of DFIG-based WECS with grid support.

Scientific reports·2025
Same author

Deep Learning-Driven Early Diagnosis of Respiratory Diseases using CNN-RNN Fusion on Lung Sound Data.

Scientific reports·2025
Same author

Explainable deep reinforcement learning for climate forecasting with transfer learning.

Environmental science and pollution research international·2025
Same author

Intelligent MPPT and coordinated control for voltage stability in brushless DFIG wind turbines.

Scientific reports·2025

相关实验视频

Updated: Jul 1, 2026

Multi-color Localization Microscopy of Single Membrane Proteins in Organelles of Live Mammalian Cells
11:06

Multi-color Localization Microscopy of Single Membrane Proteins in Organelles of Live Mammalian Cells

Published on: June 30, 2018

8.4K

MSRP-TODNet:用于微小物体检测的多尺度增强区域智能分析器.

Thulasi Bikku1, K P N V Satya Sree2, Srinivasarao Thota3

  • 1Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amaravati, Andhra Pradesh, 522503, India.

BMC research notes
|April 30, 2025
PubMed
概括

在实时监控中检测小物体是通过GAN用于微小物体检测 (MSRP-TODNet) 的多尺度区域智能像素分析改进的. 这种方法增强了特征地图,以提高空中图像的精度.

关键词:
和特征金字塔网络 (FPN).深度学习 (DL) 是指深度学习.预处理 预处理强化学习 (RL) 是一种强化学习.小物体检测 小物体检测

更多相关视频

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

6.8K
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

428

相关实验视频

Last Updated: Jul 1, 2026

Multi-color Localization Microscopy of Single Membrane Proteins in Organelles of Live Mammalian Cells
11:06

Multi-color Localization Microscopy of Single Membrane Proteins in Organelles of Live Mammalian Cells

Published on: June 30, 2018

8.4K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

6.8K
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

428

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 实时监控面临的挑战在检测小,遥远的物体,由于有限的像素数据,影响分类器的性能.
  • 深度学习 (DL) 方法通过特征图增强检测,但通常会产生高计算成本.

研究的目的:

  • 引入多尺度区域智能像素分析与GAN用于微小对象检测 (MSRP-TODNet) 模型.
  • 提高实时监控应用中检测小物体的准确性和效率.

主要方法:

  • 使用改进的维纳波器 (IWF) 和调整的对比度增强方法 (ACEM) 进行预处理图像.
  • 使用多代理强化学习 (MARL) 进行区域像素分析和特征图生成.
  • 采用增强特征金字塔网络 (EFPN) 进行特征地图合并.
  • 实现生成对抗网络 (GAN) 用于使用边界框进行最终对象检测.

主要成果:

  • 在DOTA数据集上,MSRP-TODNet在IOU 0.5时实现了84.2%的平均平均精度 (mAP),在IOU 0.5:0.95时达到54.1%.
  • 与TPH-YOLOv5,YOLOv7-Tiny和DRDet相比,该模型表现出优异的性能,检测性能幅度为1.7%-6.1%.
  • 获得了84.0%的F1评分,突出了其在小物体检测方面的有效性.

结论:

  • MSRP-TODNet提供了一个强大的解决方案,用于在UAV监控等具有挑战性的环境中准确,实时检测小物体.
  • 拟议的框架通过增强特征表示和减少计算负载,有效地解决了传统方法的局限性.
  • 该模型在基准数据集上的性能验证了其在空中图像分析中的实际应用潜力.