Bioinspired tailless FWMAV design for agricultural plant protection in greenhouses

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 231, P. 110021 - 110021

Published: Jan. 30, 2025

Language: Английский

---

Framework for Smartphone-based Grape Detection and Vineyard Management using UAV-Trained AI

Heliyon, Journal Year: 2025, Volume and Issue: 11(4), P. e42525 - e42525

Published: Feb. 1, 2025

Viticulture benefits significantly from rapid grape bunch identification and counting, enhancing yield quality. Recent technological machine learning advancements, particularly in deep learning, have provided the tools necessary to create more efficient, automated processes that reduce time effort required for these tasks. On one hand, drone, or Unmanned Aerial Vehicles (UAV) imagery combined with algorithms has revolutionised agriculture by automating plant health classification, disease identification, fruit detection. However, advancements often remain inaccessible farmers due their reliance on specialized hardware like ground robots UAVs. other most access smartphones. This article proposes a novel approach combining UAVs smartphone technologies. An AI-based framework is introduced, integrating 5-stage AI pipeline object detection pixel-level segmentation automatically detect bunches images of commercial vineyard vertical trellis training. By leveraging UAV-captured data training, proposed model not only accelerates process but also enhances accuracy adaptability across different devices, surpassing efficiency traditional purely UAV-based methods. To this end, using dataset UAV videos recorded during early growth stages July (BBCH77-BBCH79), X-Decoder segments vegetation front frames background surroundings. advantageous because it can be seamlessly integrated into without requiring changes how captured, making versatile than Then, YOLO trained further applied taken common smartphones (Xiaomi Poco X3 Pro iPhone X). In addition, web app was developed connect system mobile technology easily. The achieved precision 0.92 recall 0.735, an F1 score 0.82 Average Precision (AP) 0.802 under operation conditions, indicating high reliability detecting bunches. AI-detected were compared actual truth, achieving R2 value as 0.84, showing robustness system. study highlights potential imaging applications together, integrate models real platform farmers, offering practical, affordable, accessible, scalable solution. While smartphone-based image collection training labour-intensive costly, incorporating process, facilitating creation generalise diverse sources platforms. blend cuts monitoring effort.

Language: Английский

---

Improved Detection and Location of Small Crop Organs by Fusing UAV Orthophoto Maps and Raw Images

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(5), P. 906 - 906

Published: March 4, 2025

Extracting the quantity and geolocation data of small objects at organ level via large-scale aerial drone monitoring is both essential challenging for precision agriculture. The quality reconstructed digital orthophoto maps (DOMs) often suffers from seamline distortion ghost effects, making it difficult to meet requirements organ-level detection. While raw images do not exhibit these issues, they pose challenges in accurately obtaining detected objects. detection was improved this study through fusion with using EasyIDP tool, thereby establishing a mapping relationship data. Small object conducted by Slicing-Aided Hyper Inference (SAHI) framework YOLOv10n on accelerate inferencing speed farmland. As result, comparing directly DOM, accelerated accuracy improved. proposed SAHI-YOLOv10n achieved mean average (mAP) scores 0.825 0.864, respectively. It also processing latency 1.84 milliseconds 640×640 resolution frames application. Subsequently, novel crop canopy dataset (CCOD-Dataset) created interactive annotation SAHI-YOLOv10n, featuring 3986 410,910 annotated boxes. method demonstrated feasibility detecting three in-field farmlands, potentially benefiting future wide-range applications.

Language: Английский

---

Canopy extraction of mango trees in hilly and plain orchards using UAV images: Performance of machine learning vs deep learning

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103101 - 103101

Published: March 1, 2025

Language: Английский

---

Effectiveness of drone-based thermal sensors in optimizing controlled environment agriculture performance under arid conditions

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 16, 2025

Abstract Controlled environmental agriculture (CEA), integrated with internet of things and wireless sensor network (WSN) technologies, offers advanced tools for real-time monitoring assessment microclimate plant health/stress. Drone applications have emerged as transformative technology significant potential CEA. However, adoption practical implementation such technologies remain limited, particularly in arid regions. Despite their advantages agriculture, drones yet to gain widespread utilization CEA systems. This study investigates the effectiveness drone-based thermal imaging (DBTI) optimizing performance health under conditions. Several WSN sensors were deployed track microclimatic variations within environment. A novel method was developed assessing canopy temperature (Tc) using thermocouples DBTI. The crop water stress index (CWSI) computed based on Tc extracted from Findings revealed that DBTI effectively distinguished between all treatments, detection exhibiting a strong correlation (R 2 = 0.959) sensor-based measurements. Results confirmed direct relationship CWSI Tc, well association soil moisture content CWSI. research demonstrates can enhance irrigation scheduling accuracy provide precise evapotranspiration (ETc) estimates at specific spatiotemporal scales, contributing improved food security.

Language: Английский

---