Monitoring insect activity at hive entrances is essential for advancing precision beekeeping practices by enabling non-invasive, real-time assessment of the colony’s health and early detection of potential threats. This study evaluates deep learning models for detecting worker bees, pollen-bearing bees, drones, and wasps, comparing different YOLO-based architectures optimized for real-time inference on an RTX 4080 Super and Jetson AGX Orin. A new publicly available dataset with diverse environmental conditions was used for training and validation. Performance comparisons showed that modified YOLOv8 models achieved a better precision–speed trade-off relative to other YOLO-based architectures, enabling efficient deployment on embedded platforms. Results indicate that model modifications enhance detection accuracy while reducing inference time, particularly for small object classes such as pollen. The study explores the impact of different annotation strategies on classification performance and tracking consistency. The findings demonstrate the feasibility of deploying AI-powered hive monitoring systems on embedded platforms, with potential applications in precision beekeeping and pollination surveillance.

This study presents a novel method for automatically recognizing honeybee behavior patterns at the hive entrance, significantly contributing to beekeeping and hive management. Utilizing advanced YOLOv8 models for detection and segmentation, our approach analyzes various aspects of bee behavior, including location, direction, path trajectory, and movement speed within a designated area on the hive’s landing board. The system effectively detects multiple bee activities such as foraging, fanning, washboarding, and defense, achieving a mean detection accuracy of 98% and operating at speeds of up to 36 fps, surpassing state-of-the-art methods in both speed and accuracy. Key contributions include the development of a comprehensive dataset with 7200 frames from eight beehives, the introduction of the first known research focused on recognizing bee behavior patterns through visual analysis at the hive entrance, and a comparative evaluation of various object detection and tracking algorithms tailored for bee detection and behavior recognition. Our findings indicate that this method enhances monitoring capabilities for beekeepers while reducing the need for manual inspections, thereby minimizing disturbances to the bees. By analyzing spatial trajectories and occurrence density maps, the proposed framework provides robust identification of overlapping behaviors, facilitating timely interventions when necessary. This work lays the groundwork for future automated monitoring systems aimed at improving hive health and productivity.

Trophallaxis, a fundamental social behavior observed among honeybees, involves the redistribution of food and chemical signals. The automation of its detection under field-realistic conditions poses a significant challenge due to the presence of crowding, occlusions, and brief, fine-scale motions. In this study, we propose a markerless, deep learning-based approach that injects short- and mid-range temporal features into single-frame You Only Look Once (YOLO) detectors via temporal-to-RGB encodings. A new dataset for trophallaxis detection, captured under diverse illumination and density conditions, has been released. On an NVIDIA RTX 4080 graphics processing unit (GPU), temporal-to-RGB inputs consistently outperformed RGB-only baselines across YOLO families. The YOLOv8m model improved from 84.7% mean average precision (mAP50) with RGB inputs to 91.9% with stacked-grayscale encoding and to 95.5% with temporally encoded motion and averaging over a 1 s window (TEMA-1s). Similar improvements were observed for larger models, with best mAP50 values approaching 94–95%. On an NVIDIA Jetson AGX Orin embedded platform, TensorRT-optimized YOLO models sustained real-time throughput, reaching 30 frames per second (fps) for small and 23–25 fps for medium models with temporal-to-RGB inputs. The results showed that the TEMA-1s encoded YOLOv8m model has achieved the highest mAP50 of 95.5% with real-time inference on both workstation and edge hardware. These findings indicate that temporal-to-RGB encodings provide an accurate and computationally efficient solution for markerless trophallaxis detection in field-realistic conditions. This approach can be further extended to multi-behavior recognition or integration of additional sensing modalities in precision beekeeping.

This study investigates efficient thermal-image human pose estimation under edge deployment constraints for smart home activity recognition. A single-person thermal dataset of 2500 images was collected and annotated with 17 body keypoints. YOLO11-pose and YOLOv8-pose models were trained and evaluated across all five model scales (n–x) at three input resolutions 640 × 512, 320 × 256, and 160 × 128 px. The accuracy was evaluated using box mean Average Precision (mAP50–95), pose mAP50–95, and Object Keypoint Similarity (OKS) metrics. Runtime performance was assessed using per-image latency and power measurements on three NVIDIA Jetson platforms: Orin Nano 4 GB, Orin Nano 8 GB and AGX Orin 64 GB, using PyTorch and TensorRT at FP32, FP16, INT8 precision. Human detection remained consistently high across model variants, whereas pose accuracy decreased as the input resolution was reduced. TensorRT FP16 preserved pose accuracy relative to PyTorch and TensorRT FP32, with minimal changes in OKS and pose mAP50–95, while notably reducing per-image latency and power consumption. INT8 further reduced power consumption and in some configurations improved latency, but caused configuration-dependent losses in OKS and pose mAP50–95. The findings indicate that FP16 offers the best accuracy–efficiency balance for thermal pose estimation on edge devices, while practical feasibility depends on device capabilities and memory limitations.

The application of machine learning algorithms has become widespread particularly in fields such as medicine, business, and commerce. However, achieving accurate classification results with these algorithms often relies on large-scale training datasets, making data collection a lengthy and complex process. This paper reviews the current utilization of generative adversarial network (GAN) architectures and discusses recent scientific research on their practical applications. The study emphasizes the significance of addressing data scarcity in the process of training the machine learning algorithms and highlights the potential of advanced GAN architectures, in particular StyleGAN2-ADA, to mitigate this challenge. The findings contribute to ongoing efforts aimed at enhancing the efficiency and applicability of artificial intelligence across diverse domains by presenting a viable solution to the constraint of limited training data for image classification tasks.

Convolutional neural networks (CNNs) are powerful models of deep learning that are widely used in computer vision classification tasks. The purpose of this study is to investigate the impact of datasets on CNN performance, employing original datasets and expanded datasets with synthetically generated images. The Generative Adversarial Network (GAN) is an unsupervised deep learning method used for synthetic data generation and can address the limitations of image augmentations. In this study, a new GAN architecture is used to synthesize high-resolution images when dealing with limited training data. The StyleGAN2-ADA model is specifically designed to generate high-quality images using limited datasets. Adaptive Discriminator Augmentation (ADA) dynamically adjusts data augmentation, enhancing discriminator efficiency and stability. The findings indicate a reduction in the likelihood of overfitting, enhancement in network generalization, mitigation of class imbalance concerns, and a concurrent increase in the accuracy and stability of network classification.