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

Data Collection by Observations01:08

Data Collection by Observations

12.1K
Data collection refers to a systematic way of obtaining, observing, measuring, and analyzing accurate information. Observational studies are one of the most widely used methods of data collection. It involves collecting data by observing the behavior and physical characteristics of a sample without making any modifications to the sample.
An astronomer viewing the motion and brightness of stars in the sky and recording the data is an example of observational data collection. A botanist recording...
12.1K

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

Flight style and metabolism shape the tempo of genome evolution in birds.

PLoS biology·2026
Same author

Comparative Transcriptomics Deciphers Quinclorac Selectivity in Rice and Tobacco.

Physiologia plantarum·2026
Same author

Engineered extracellular vesicles for drug delivery in hepatocellular carcinoma.

International journal of pharmaceutics·2026
Same author

Dissolved organic matter composition influences catalytic oxidation behavior and product evolution in real water matrices.

Journal of hazardous materials·2026
Same author

Experimental investigation on the remediation of Cd-contaminated paddy soil by electrogeochemical survey technology in Guilin city, Guangxi.

Scientific reports·2026
Same author

Unraveling the Electronic Origin of Selectivity in Ambimodal Transition States with Valence Bond Theory.

The journal of physical chemistry. A·2026

相关实验视频

Updated: Jul 15, 2025

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

568

鸟类物体检测:数据集构建,模型性能评估和模型轻量化.

Yang Wang1,2, Jiaogen Zhou2, Caiyun Zhang2

  • 1Department of Computer Science and Technology, Tongji University, Shanghai 201804, China.

Animals : an open access journal from MDPI
|September 28, 2023
PubMed
概括

研究人员开发了最大的鸟物检测数据集 (GBDD1433-2023),以改善鸟类识别和现场调查. 双阶段模型表现出色,新的轻量级方法提高了鸟类识别的离线部署.

关键词:
适应性本地化蒸蒸鸟类计数 鸟类计数 鸟类计数鸟类监测 鸟类监测 鸟类监测模型的轻量化减轻.对象检测检测对象检测对象检测

更多相关视频

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.5K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

相关实验视频

Last Updated: Jul 15, 2025

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

568
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.5K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

科学领域:

  • 计算机视觉 计算机视觉
  • 鸟类学 鸟类学是一门学科.
  • 机器学习 机器学习

背景情况:

  • 对象检测有助于鸟类识别和现场调查.
  • 缺乏专门的鸟类数据集和基准标准阻碍了进步.

研究的目的:

  • 构建最大的鸟类物体检测数据集 (GBDD1433-2023).
  • 评估用于鸟类识别的主流物体检测模型.
  • 提出用于鸟类检测的轻量级模型.

主要方法:

  • 创建了GBDD1433-2023,包含1433个物种和148,000张图像.
  • 与八个物体检测模型进行了比较,包括Faster R-CNN和Cascade R-CNN.
  • 开发了一种适应性局部化蒸,用于轻型模型.

主要成果:

  • 两阶段模型实现了73.7%的mAP,优于单阶段模型.
  • 两阶段模型显示出更好的稳定性,以缩放和背景变化.
  • 鸟类计数的准确性显著下降,超过每张图像的五只鸟.

结论:

  • GBDD1433-2023数据集支持鸟类物体检测研究.
  • 双阶段模型对于鸟类检测任务是优越的.
  • 带有蒸的轻量级模型适用于离线鸟类识别.