Visual Diagnosis of the Varroa Destructor Parasitic Mite in Honeybees Using Object Detector Techniques

Bilík, Šimon; Kratochvíla, Lukáš; Ligocki, Adam; Boštík, Ondřej; Zemčík, Tomáš; Hýbl, Matouš; Horák, Karel; Žalud, Luděk

doi:10.3390/s21082764

Cited by 40 publications

(28 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In terms of video detection, various image processing techniques and training software have been employed to identify the presence of a mite in video recordings of the adult bees or within brood cells (Ramirez et al 2012;Elizondo et al 2013;Chazette et al 2016;Bjerge et al 2019;Bilik et al 2021). This work is currently in a prototype phase with some limitations, including video clarity affecting the chance of a successful detection (Elizondo et al 2013) and the requirement for powerful hardware to carry out complex computations (Bilik et al 2021). In the field, videos can only be recorded at the hive entrance (Bjerge et al 2019), high-lighting another flaw as this type of monitoring presently cannot take place within the darkness of the hive.…”

Section: Remote Varroa Monitoring Techniquesmentioning

confidence: 99%

Varroa destructor mites regularly generate ultra-short, high magnitude vibrational pulses.

Hall¹,

Bencsik²,

Newton³

et al. 2022

entomologia

View full text Add to dashboard Cite

The ectoparasitic mite Varroa destructor is considered one of the greatest threats to the honeybee Apis mellifera. To successfully manage mite populations residing in the colony, beekeepers must stay informed of infestation levels in their apiaries. The remote, non-destructive detection of Varroa mites in honeybee hives would therefore be highly desirable.Here we show that an ultra-sensitive (1000 mV/g) accelerometer can detect vibrational waveforms originating from one individual mite. We further focus on a commonly observed pulsing behaviour never before described, characterising its physical features, periodicity and strength. The spectral features of the detected pulses strongly depend on the substrate on which they are produced. The characteristics of the vibrational pulse, particularly its repeatability and strength, indicate that mite vibrations could be successfully detected in a fully populated honeybee hive. These features, combined with the remarkably high varroa muscular power output (up to 810nW) indicate that this pulse may be functional for the mite. Our results uncover an exciting novel behaviour and provide a foundation for the remote detection of mites in beehives using vibration capture.

show abstract

Section: Remote Varroa Monitoring Techniquesmentioning

confidence: 99%

Varroa destructor mites regularly generate ultra-short, high magnitude vibrational pulses.

Hall¹,

Bencsik²,

Newton³

et al. 2022

entomologia

View full text Add to dashboard Cite

show abstract

“…Another possibility to utilize deep learning to detect Varroa mites is object detection. Bilik et al (2021) used YOLO (you only look once) and SSD (single shot detector) object detectors to be implemented in a real-time computer vision-based honey bee inspection system. This system can be used as online monitoring tool where video or photo data are analyzed.…”

Section: Ai-based Systems and Deep Learningmentioning

confidence: 99%

“…Optical counters can register individual Varroa mites on bees. With this capability, dispersal routes can be better investigated, and the reinvasion behaviour of Varroa destructor can be described in detail (Chazette, Becker, & Szczerbicka, 2016;Bjerge et al, 2019;Bilik et al, 2021).…”

Section: Field Of Usementioning

confidence: 99%

Approaches, challenges and recent advances in automated bee counting devices: A review

Odemer

2021

Annals of Applied Biology

View full text Add to dashboard Cite

For nearly 100 years, electronic bee counters have been developed using various technologies to track the foraging activity of mostly honey bee colonies. These counters should enable remote monitoring of the hives without disturbing natural flight behavior while generating precise scientific data. Today, however, there are not many counters on the market, that are able to fulfill this task. One main challenge is the lack of standardized methods to validate a counter's precision, but validation is crucial to categorize and judge the data produced by the counter, especially for scientific purposes. Another challenge is the interpretation of flight data to measure the effects of environmental or anthropogenic sources. Nevertheless, recent developments in the field are promising. This review describes the historic development of automated bee flight measurement and critically compares validation methods to encourage their improvement. Lastly, to increase the comparability of future analyses with bee counters, current advances in data interpretation are also presented.

show abstract

“…An object detector-based bee colony health status monitoring method with online measurement and processing potential has been developed using YOLO and SSD [ 29 ]. A mobile vision-based food grading evaluation system was proposed using the YOLOv3 model to overcome the challenge of detecting and outputting small defective areas of bananas [ 30 ].…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Network for Object Detection in Garlic Root Cutting Equipment

Yang

Peng²,

Zhang³

et al. 2022

Foods

View full text Add to dashboard Cite

Traditional manual garlic root cutting is inefficient and can cause food safety problems. To develop food processing equipment, a novel and accurate object detection method for garlic using deep learning—a convolutional neural network—is proposed in this study. The you-only-look-once (YOLO) algorithm, which is based on lightweight and transfer learning, is the most advanced computer vision method for single large object detection. To detect the bulb, the YOLOv2 model was modified using an inverted residual module and residual structure. The modified model was trained based on images of bulbs with varied brightness, surface attachment, and shape, which enabled sufficient learning of the detector. The optimum minibatches and epochs were obtained by comparing the test results of different training parameters. Research shows that IRM-YOLOv2 is superior to the SqueezeNet, ShuffleNet, and YOLOv2 models of classical neural networks, as well as the YOLOv3 and YOLOv4 algorithm models. The confidence score, average accuracy, deviation, standard deviation, detection time, and storage space of IRM-YOLOv2 were 0.98228, 99.2%, 2.819 pixels, 4.153, 0.0356 s, and 24.2 MB, respectively. In addition, this study provides an important reference for the application of the YOLO algorithm in food research.

show abstract

Visual Diagnosis of the Varroa Destructor Parasitic Mite in Honeybees Using Object Detector Techniques

Cited by 40 publications

References 26 publications

Varroa destructor mites regularly generate ultra-short, high magnitude vibrational pulses.

Varroa destructor mites regularly generate ultra-short, high magnitude vibrational pulses.

Approaches, challenges and recent advances in automated bee counting devices: A review

Convolutional Neural Network for Object Detection in Garlic Root Cutting Equipment

Contact Info

Product

Resources

About