Detection of pollen bearing honey bees in hive entrance images

Stojnić, Vladan; Risojević, Vladimir; Pilipović, Ratko

doi:10.1109/infoteh.2018.8345546

Cited by 7 publications

(12 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bee counting (omnidirectional) [Schurischuster et al, 2018] 1920 × 1080 (30fps) GMMs, Color Histograms, Dense SURF, Varroa mites detection Naive Bayes, SVM & RF [Magnier et al, 2018 Edge detection, fit ellipses, concordance Bee tracking & counting [Stojnic et al, 2018] 1280 × 720 SIFT, VLAD & SVM Pollen sacs detection [Sledevic, 2018] 1920 × 1024 (3fps) CNN Pollen sacs detection [Shimasaki et al, 2018] 1024 Bee counting (omnidirectional) [Bjerge et al, 2019] 1296 × 966 (31fps) SIFT, SURF, ORB, LDA & CNN Varroa mites detection [Shimasaki et al, 2020] 1024 × 1024 (500fps) STFT Bee tracking & wing-flapping freq. measures [Mukherjee and Kulyukin, 2020] 160 × 120, 320 × 240 & 640 × 480 (25fps) DPIV Bee tracking (directional) [Ngo et al, 2021]…”

Section: Opencv Algorithmsmentioning

confidence: 99%

“…Since bees are more yellow and brown than blue, filtering their shadows remains an easy task ( [Magnier et al, 2018]). In [Stojnic et al, 2018], the approach starts with considering images in the CIE LAB space and considering the two non-illumination channels, so that differences in light levels are not seen. This segmentation method is compared with k-means.…”

Section: Selection Of Computer Vision Pb Papersmentioning

confidence: 99%

“…This study compares the accuracy and F1-score of different combinations of color models, image features, and classification methods and obtains a maximum accuracy of over 80%. In [Stojnic et al, 2018], pollen-bearing bees and non-pollen bearing bees are classified thanks to SVM mixed with PCA using SIFT and VALD to compute image descriptors. A maximum of 0.915 AUC score is obtained (See Table 3).…”

Section: Models and Accuracymentioning

confidence: 99%

See 2 more Smart Citations

Toward an intelligent and efficient beehive: A survey of precision beekeeping systems and services

Hadjur

Ammar

Lefèvre

2022

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Since the end of the 20 th century, bees are suffering from increasing stress factors, leading domesticated colonies to die or at least be less productive. Precision beekeeping (PB) is an emerging field of agriculture that aims at protecting bees, supporting beekeepers, and optimizing apiary production thanks to digital infrastructures. The digitalization of apiculture first involves systems from the field of the Internet of Things (IoT), with the development of sensors to collect and transfer bee-related data. Then, data analysis comes into play, providing models that connect the data with the biological states of beehives, sometimes thanks to artificial intelligence (AI).In this paper, we describe the recent advances in precision beekeeping as systems and as services. Different types of sensors, networks, and power sources in PB are covered. The collection and use of data are described, and the performances of PB services are assessed. We also estimate the sustainability of the proposed solutions, taking into account their scalability, efficiency, and economic cost, because beekeepers need deployable research results.

show abstract

Section: Opencv Algorithmsmentioning

confidence: 99%

Section: Selection Of Computer Vision Pb Papersmentioning

confidence: 99%

Section: Models and Accuracymentioning

confidence: 99%

See 1 more Smart Citation

Toward an intelligent and efficient beehive: A survey of precision beekeeping systems and services

Hadjur

Ammar

Lefèvre

2022

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

show abstract

“…There are pieces of evidence [27] that reinforce that bee diseases or pests are a significant reason for colonies to die. Varroa destructor is considered most harmful and catastrophic for the bee colonies [27], [28]. Once infected with the mite, the whole territory can die within one year, leaving the effect on neighbouring colonies too [29].…”

Section: Precision Beekeepingmentioning

confidence: 99%

A CNN-Based Identification of Honeybees' Infection using Augmentation

Kaur

Ardekani

Sharifzadeh

et al. 2022

2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)

View full text Add to dashboard Cite

Artificial Intelligence (AI) solutions have been extensively explored and implemented in the apiculture industry. Designing an efficient system for continuous observation of bees for their health and activities has been a challenge and of great interest among researchers. Several studies manifest that AI-based solutions can accommodate the purpose of beehive monitoring. However, the systems constructed based on computer vision techniques are found to be incompetent with noisy and insufficient data. This research proposes a computer vision-based approach to classify bee images for infected or healthy bees, dealing with indistinct and inadequate image data. As a solution, image contrast enhancement and data augmentation methods are used to improve the quality and size of data, respectively. The foggy bee images are managed using the Contrast Limited Adaptive Histogram Equalization (CLAHE), enhancing the image contrast to make it more understandable. The small dataset is augmented using an advanced method, Deep Convolutional Generative Adversarial Networks (DCGAN), which is capable of generating new images resembling the real ones. We investigate the capability of DCGAN as an alternative to the conventional augmentation technique that uses the varied geometric transformation of the image. An optimized Convolutional Neural Network (CNN) model is used to classify the augmented bee image data. Further, one of the transfer learning techniques, VGG16, is applied to compare the classifiers' performance on the same data sets. The effectiveness of the preprocessing method CLAHE and augmentation method DCGAN is assessed against original images and conventional augmentation methods. The classifiers CNN and VGG16 are compared alongside for their performance on non-augmented and augmented data sets. The investigations conducted on the given bee data sets delivered promising results. The CLAHE pre-processing method not only improved the image sharpness by 10% but also enhanced the CNN classifier's performance as compared to the original images. The optimized CNN's performance enhanced with conventional geometrically transformed augmented data. However, the classifier outperformed with added DCGAN generated synthetic images in the original data set providing up to 99.9% accuracy. Further, fine-tuned transfer learning classification model provided comparable accuracy alongside CNN with added efficiency building and executing the model. The success of this preliminary investigation paves the way to explore different variations of Generative Adversarial Network (GAN) to augment the image data together with enhancing its quality.

show abstract

“…Stojnić [14] proposed an approach that starts by segmenting honey bees from images using two segmentation methods based on colour descriptors. Then, Support Vector Machines (SVM) are trained on few variations of VLAD and SIFT descriptors to classify the images into two classes (with or without pollen).…”

Section: Related Workmentioning

confidence: 99%

Towards Precise Recognition of Pollen Bearing Bees by Convolutional Neural Networks

Monteiro

Pinto

Rufino

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Automatic recognition of pollen bearing bees can provide important information both for pollination monitoring and for assessing the health and strength of bee colonies, with the consequent impact on people's lives, due to the role of bees in the pollination of many plant species. In this paper, we analyse some of the Convolutional Neural Networks (CNN) methods for detection of pollen bearing bees in images obtained at hive entrance. In order to show the influence of colour we preprocessed the dataset images. Studying the results of nine state-of-the-art CNNs, we provide a baseline for pollen bearing bees recognition based in deep learning. For some CNNs the best results were achieved with the original images. However, our experiments showed evidence that DarkNet53 and VGG16 have superior performance against the other CNNs tested, with unsharp masking preprocessed images, achieving accuracy results of 99.1% and 98.6%, respectively.

show abstract

Detection of pollen bearing honey bees in hive entrance images

Cited by 7 publications

References 7 publications

Toward an intelligent and efficient beehive: A survey of precision beekeeping systems and services

Toward an intelligent and efficient beehive: A survey of precision beekeeping systems and services

A CNN-Based Identification of Honeybees' Infection using Augmentation

Towards Precise Recognition of Pollen Bearing Bees by Convolutional Neural Networks

Contact Info

Product

Resources

About