Automated monitoring and analyses of honey bee pollen foraging behavior using a deep learning-based imaging system

Ngo, Thi Nha; Rustia, Dan Jeric Arcega; Yang, En‐Cheng; Lin, Ta‐Te

doi:10.1016/j.compag.2021.106239

Cited by 46 publications

(20 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…If the CNN model was trained on a dataset collected from an entrance of a single beehive and the trained model was further used to classify frames from that beehive, then the classification accuracy was as high as was achieved by Ngo et al [23] and Rodriguez et al [24]. Ngo et al [23] used a GPU-based Jetson TX2 embedded system; Babic et al [25] implemented their classification algorithm on an Intel i3 CPU and then accelerated it with a Raspberry Pi. All the other approaches were implemented on a PC and were based on CPU and GPU cores.…”

Section: Methodsmentioning

confidence: 99%

“…CNN-based image analysis methods are often applied for bee tracking and pollen detection in images [5]. Almost always, the dataset of bee images is collected using a contrast background (blue, green, or black) to improve the bee detectability [23][24][25][26][27]. In a related state-of-the-art imaging system, the pollen detection accuracy varied in the range of 89-99% and basically depended on the applied segmentation, classification methods, and dataset.…”

Section: Introductionmentioning

confidence: 99%

“…A Kalman filter and the Hungarian algorithm were applied for tracking multiple bees. Recently, the authors extended their study with CNN-based bee detection [23]. A tiny YOLOv3 model was trained for the detection of multiple bees with pollen grains and non-pollen.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

FPGA Implementation of a Convolutional Neural Network and Its Application for Pollen Detection upon Entrance to the Beehive

2022

View full text Add to dashboard Cite

The condition of a bee colony can be predicted by monitoring bees upon hive entrance. The presence of pollen grains gives beekeepers significant information about the well-being of the bee colony in a non-invasive way. This paper presents a field-programmable-gate-array (FPGA)-based pollen detector from images obtained at the hive entrance. The image dataset was acquired at native entrance ramps from six different hives. To evaluate and demonstrate the performance of the system, various densities of convolutional neural networks (CNNs) were trained and tested to find those suitable for pollen grain detection at the chosen image resolution. We propose a new CNN accelerator architecture that places a pre-trained CNN on an SoC FPGA. The CNN accelerator was implemented on a cost-optimized Z-7020 FPGA with 16-bit fixed-point operations. The kernel binarization and merging with the batch normalization layer were applied to reduce the number of DSPs in the multi-channel convolutional core. The estimated average performance was 32 GOPS for a single convolutional core. We found that the CNN with four convolutional and two dense layers gave a 92% classification accuracy, and it matched those declared for state-of-the-art methods. It took 8.8 ms to classify a 512 × 128 px frame and 2.4 ms for a 256 × 64 px frame. The frame rate of the proposed method outperformed the speed of known pollen detectors. The developed pollen detector is cost effective and can be used as a real-time image classification module for hive status monitoring.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

FPGA Implementation of a Convolutional Neural Network and Its Application for Pollen Detection upon Entrance to the Beehive

2022

View full text Add to dashboard Cite

show abstract

“…Foraging: Foraging behaviour directly influences colony productivity and insect pollination capability [Ngo et al, 2021a]. It forms a key part of research on insect behaviour, as well as plant reproductive biology and evolutionary ecology.…”

Section: Investigative Monitoringmentioning

confidence: 99%

A Framework for Better Sensor-Based Beehive Health Monitoring

Zaman

Dorin

2022

Preprint

View full text Add to dashboard Cite

Hive bees provide essential pollination services to human agriculture. Managed honey bees in particular pollinate many crops, but also create honey and other bee products that are now of global economic importance. Key aspects of honey bee behaviour can be understood by observing hives. Hence, the limitations of manual observation are increasingly being addressed by new technologies that automate and extend the reach of hive monitoring. Here we propose a framework to classify and clarify the potential for sensor-assisted hive monitoring to inform apiculture and, ultimately, improve hive bee management. This framework considers hive monitoring approaches across three newly proposed categories: Operational monitoring, Investigative monitoring, and Predictive monitoring. These categories constitute a new ``OIP Framework'' of hive monitoring. Each category has its own requirements for underlying technology that includes sensors and ICT resources we outline. Each category is associated with particular outcomes and benefits for apiculture and hive health monitoring detailed here. Application of these three classes of sensor-assisted hive monitoring can simplify understanding and improve best-practice management of hive bees. Our survey and classification of hive monitoring to date show that it is seldom practiced beyond honey bees, despite the need to understand bumble bees and stingless bees also. Perhaps unsurprisingly, sensor-based hive monitoring is shown to remain primarily a practice of developed nations. Yet we show how all countries, especially developing nations, stand to gain substantially from the benefits improved sensor-based hive monitoring offers. These include a better understanding of environmental change, an increased ability to manage pollination, an ability to respond rapidly to hive health issues such as pests and pathogens, and even an ability to react quickly to the danger posed to insects and humans alike by extreme events such as floods and fires. Finally, we anticipate that the future of hive monitoring lies in the application of Predictive monitoring, such that a hive's anticipated future state can be preemptively managed by beekeepers working iteratively with novel hive monitoring technologies.

show abstract

“…Pengataman ini biasanya dilakukan secara manual dengan bantuan manusia secara langsung. Pengawasan ini dilakukan biasanya pada lokasi pemeliharaan lebah untuk mendukung produksi madu yang berkualitas dari lebah yang ada [1], [8]- [10].…”

Section: Pendahuluanunclassified

Perbandingan Algoritma Xception dan VGG16 Untuk Pengenalan Lebah Pollen-Bearing

Noprisson¹,

Nurhaida

Purba

2022

JSAI

View full text Add to dashboard Cite

Dengan adanya pengamatan yang terjadwal akan membantu pemelihara lebah dalam mengetahui penyakit lebah, kesehatan sarang lebah dan racun yang mungkin terbawa oleh lebah. Jika ini dapat dilakukan dengan bantuan komputer, maka ini akan mengurangi waktu dan biaya pemeliharaan lebah. Selain itu, produksi madu dan sarang akan akan meningkat baik dari sisi kualitas maupun kuantitas. Penelitian ini bertujuan membuat analisis performa kinerja algoritma Xception dan VGG16 untuk pengenalan lebah pollen-bearing. Pada hasil eksperimen diatas model VGG16 dengan fine_tuning memperoleh nilai akurasi testing terbaik yaitu 83.33%. Begitu juga dengan nilai Cohens kappa, F1_score, ROC AUC, Precision, dan Recall terbaik diperoleh model VGG16 dengan fine_tuning. Untuk model Xception terbaik diperoleh dengan tanpa fine tuning yaitu sebesar 72.22%. pada hasil eksperimen ini diperoleh kesimpulan pre-trained model VGG16 dengan fine_tuning lebih cocok digunakan pada dataset bee_pollen dibandingkan dengan model Xception baik dengan fine_tuning ataupun tanpa fine_tuning.

show abstract

Automated monitoring and analyses of honey bee pollen foraging behavior using a deep learning-based imaging system

Cited by 46 publications

References 34 publications

FPGA Implementation of a Convolutional Neural Network and Its Application for Pollen Detection upon Entrance to the Beehive

FPGA Implementation of a Convolutional Neural Network and Its Application for Pollen Detection upon Entrance to the Beehive

A Framework for Better Sensor-Based Beehive Health Monitoring

Perbandingan Algoritma Xception dan VGG16 Untuk Pengenalan Lebah Pollen-Bearing

Contact Info

Product

Resources

About