Classification of Garden Chrysanthemum Flowering Period Using Digital Imagery from Unmanned Aerial Vehicle (UAV)

Agronomy, Journal Year: 2025, Volume and Issue: 15(2), P. 421 - 421

Published: Feb. 7, 2025

Monitoring the flowering period is essential for evaluating garden chrysanthemum cultivars and their landscaping use. However, traditional field observation methods are labor-intensive. This study proposes a classification method based on color information from canopy digital images. In this study, an unmanned aerial vehicle (UAV) with red-green-blue (RGB) sensor was utilized to capture orthophotos of chrysanthemums. A mask region-convolutional neural network (Mask R-CNN) employed remove backgrounds categorize growth stages into vegetative, bud, periods. Images were then converted hue-saturation-value (HSV) space calculate eight indices: R_ratio, Y_ratio, G_ratio, Pink_ratio, Purple_ratio, W_ratio, D_ratio, Fsum_ratio, representing various proportions. ratio decision tree random forest model developed further subdivide initial, peak, late The results showed that performed better F1-scores 0.9040 0.8697 two validation datasets, requiring less manual involvement. provides rapid detailed assessment periods, aiding in evaluation new cultivars.

Language: Английский

---

Simultaneous Learning Knowledge Distillation for Image Restoration: Efficient Model Compression for Drones

Drones, Journal Year: 2025, Volume and Issue: 9(3), P. 209 - 209

Published: March 14, 2025

Deploying high-performance image restoration models on drones is critical for applications like autonomous navigation, surveillance, and environmental monitoring. However, the computational memory limitations of pose significant challenges to utilizing complex in real-world scenarios. To address this issue, we propose Simultaneous Learning Knowledge Distillation (SLKD) framework, specifically designed compress resource-constrained drones. SLKD introduces a dual-teacher, single-student architecture that integrates two complementary learning strategies: Degradation Removal (DRL) Image Reconstruction (IRL). In DRL, student encoder learns eliminate degradation factors by mimicking Teacher A, which processes degraded images BRISQUE-based extractor capture degradation-sensitive natural scene statistics. Concurrently, IRL, decoder reconstructs clean from B, images, guided PIQE-based emphasizes preservation edge texture features essential high-quality reconstruction. This dual-teacher approach enables model learn both simultaneously, achieving robust while significantly reducing complexity. Experimental evaluations across five benchmark datasets three tasks—deraining, deblurring, dehazing—demonstrate that, compared teacher models, achieve an average reduction 85.4% FLOPs 85.8% parameters, with only slight decrease 2.6% PSNR 0.9% SSIM. These results highlight practicality integrating SLKD-compressed into systems, offering efficient real-time aerial platforms operating challenging environments.

Language: Английский

---

Two-Dimensional Real-Time Direction-Finding System for UAV RF Signals Based on Uniform Circular Array and MUSIC-WAA

Drones, Journal Year: 2025, Volume and Issue: 9(4), P. 278 - 278

Published: April 7, 2025

To address the growing security risks posed by unauthorized unmanned aerial vehicle (UAV) activities, this paper proposes a real-time two-dimensional direction-finding (DF) system for UAVs based on radio frequency (RF) signals. This employs six-element uniform circular array (UCA), synchronized HackRF One receivers, and hybrid algorithm integrating multiple signal classification (MUSIC) method with novel weighted average (WAA). By optimizing MUSIC spectrum search process, WAA reduces computational complexity over 99.9% at resolution of 0.1° (from 3,240,000 to 1200 spectral function calculations), enabling estimation azimuth elevation angles. The experimental results demonstrate an error 7.0° 7.7° UAV hovering distances 30–200 m heights 20–90 m. Real-time flight tracking further validates system’s dynamic monitoring capabilities. hardware platform, featuring omnidirectional coverage (0–360° azimuth, 0–90° elevation) dual-band operation (2.4 GHz/5.8 GHz), offers scalability cost-effectiveness low-altitude applications. Despite limitations in sensitivity due UCA’s geometry, work establishes practical foundation monitoring, emphasizing efficiency, performance, adaptability environments.

Language: Английский

---

Reducing the Maximum Amplitudes of Forced Vibrations of a Quadcopter Arm Using an Aerodynamic Profile Adapter

Drones, Journal Year: 2024, Volume and Issue: 8(12), P. 754 - 754

Published: Dec. 13, 2024

This research focuses on the dynamic response analysis of a quadcopter arm without an adapter mounted and with aerodynamic profile adapters to enhance drone performance. Nine different were simulated assess their impact arm’s behavior during various motor operating regimes. The pressure force distribution from airflow around was analyzed determine optimal configuration. Numerical simulations revealed best geometry for adapter, which significantly reduced maximum displacement amplitudes compared non-adapter arm. study also examined effects static imbalance rotor-propeller assembly, leading calculation eccentricity value 0.022 mm inertial application. Experimental tests validated numerical findings, laser vibrometer measurements confirming improved responses Adapter 8 across most Overall, shows advantages using better designs in arms improve stability performance, contributing advancements technology through structural designs.

Language: Английский

---