相关实验视频

Updated: May 19, 2026

Flying Insect Detection and Classification with Inexpensive Sensors

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

混合机器学习与深度学习方法对虫检测和计数的比较研究

Amira Ghezal¹, Andreas König¹

¹Lehrstuhl Kognitive Integrierte Sensorsysteme, Fachbereich Elektrotechnik und Informationstechnik, RPTU Kaiserslautern-Landau, 67663 Kaiserslautern, Germany.

Sensors (Basel, Switzerland)

|August 28, 2025

概括

传统的机器学习 (ML) 方法比深度学习 (DL) 更好地检测高光谱图像中的瓦罗亚破坏者,特别是在资源有限的环境中. 在蜜蜂健康监测方面,ML提供了更快的处理和可比的准确性.

科学领域:

农业科学
计算机科学
昆虫学

背景情况:

瓦罗亚破坏者虫对全世界蜜蜂群体构成重大威胁.
精确有效地检测这些虫对于有效的害虫管理和保护蜜蜂健康至关重要.
超光谱成像为虫检测提供了一个有前途的非侵入性方法.

研究的目的:

对传统的机器学习 (ML) 和深度学习 (DL) 方法进行比较评估,以检测和计数Varroa破坏性虫.
在不同的数据条件下使用超光谱图像来评估ML和DL模型的性能.
根据资源可用性和性能要求,为选择适当的虫检测策略提供实际指导.

主要方法:

使用主组件分析 (PCA),k-Nearest Neighbors (kNN) 和支持矢量机 (SVM) 的传统ML管道被实施.
使用ResNet-50和ResNet-101骨干的更快R-CNN的深度学习 (DL) 方法在同一数据集上进行了微调.
这两种方法在超光谱图像上进行了检测和计数精度的评估.

主要成果:

通过对CPU进行快速训练和推断,ML管道实现了高性能 (精度=0.9983,回忆=0.9947).
尽管需要GPU加速和更长的训练时间,DL模型 (ResNet-50/101) 的精度较低 (0.966/0.971) 和回忆率较低 (0.757/0.829).
与DL相比,ML在有限的数据条件下表现出更高的稳定性.

结论:

传统的ML方法更适合在资源有限的环境中对超光谱图像进行检测.
虽然DL方法很强大,但在培训时间,计算资源和可重复性方面存在挑战.
这项研究为选择蜜蜂养殖中最佳的虫检测策略提供了宝贵的见解,平衡性能与实际实施.

关键词:

检测瓦罗亚虫深度学习超光谱成像机器学习模型比较

更多相关视频

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

相关概念视频

Aggregates Classification

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...

Methods of Classification and Identification

Methods of Classification and Identification

Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...