The Detection and Counting of Olive Tree Fruits Using Deep Learning Models in Tacna, Perú

AI, Journal Year: 2025, Volume and Issue: 6(2), P. 25 - 25

Published: Feb. 1, 2025

Predicting crop performance is key to decision making for farmers and business owners. Tacna the main olive-producing region in Perú, with an annual yield of 6.4 t/ha, mainly Sevillana variety. Recently, olive production levels have fluctuated due severe weather conditions disease outbreaks. These climatic phenomena are expected continue coming years. The objective study was evaluate model natural specific environments grove counting fruits using CNNs from images. Among models evaluated, YOLOv8m proved be most effective (94.960), followed by YOLOv8s, Faster R-CNN RetinaNet. For mAP50-95 metric, also (0.775). achieved best RMSE 402.458 a coefficient determination R2 (0.944), indicating high correlation actual fruit count. As part this study, novel dataset developed capture variability under different conditions. Concluded that predicting images requires consideration field imaging conditions, color tones, similarity between olives leaves.

Language: Английский

---

Research on Swarm Control Based on Complementary Collaboration of Unmanned Aerial Vehicle Swarms Under Complex Conditions

Drones, Journal Year: 2025, Volume and Issue: 9(2), P. 119 - 119

Published: Feb. 6, 2025

Under complex conditions, the collaborative control capability of UAV swarms is considered to be key ensuring stability and safety swarm flights. However, in environments such as forest firefighting, traditional methods struggle meet differentiated needs UAVs with differences behavior characteristics mutually coupled constraints, which gives rise problem that adjustments feedback policy during training are prone erroneous judgments, leading decision-making dissonance. This study proposed a method for complementary collaboration under conditions. The first generates data through interaction between environment; then it captures potential patterns behaviors, extracts their characteristics, explores diversified combination scenarios advantages; accordingly, dynamic allocations made according perception accuracy action achieve cooperation; finally, optimizes neural network parameters learning improve policy. According experimental results, this demonstrates high formation integrity when dealing missions multiple types UAVs.

Language: Английский

---

A review of deep learning applications in weed detection: UAV and robotic approaches for precision agriculture

European Journal of Agronomy, Journal Year: 2025, Volume and Issue: 168, P. 127652 - 127652

Published: April 24, 2025

Language: Английский

---

Research on Soybean Seedling Stage Recognition Based on Swin Transformer

Agronomy, Journal Year: 2024, Volume and Issue: 14(11), P. 2614 - 2614

Published: Nov. 6, 2024

Accurate identification of the second and third compound leaf periods soybean seedlings is a prerequisite to ensure that soybeans are chemically weeded after seedling at optimal application period. period susceptible natural light complex field background factors. A transfer learning-based Swin-T (Swin Transformer) network proposed recognize different stages stage. drone was used collect images true stage, first data enhancement methods such as image rotation brightness were expand dataset, simulate drone’s collection shooting angles weather conditions, enhance adaptability model. The environment equipment directly affect quality captured images, in order test anti-interference ability models, Gaussian blur method set degrees. model optimized by introducing learning combining hyperparameter combination experiments optimizer selection experiments. performance compared with MobileNetV2, ResNet50, AlexNet, GoogleNet, VGG16Net models. results show has an average accuracy 98.38% set, which improvement 11.25%, 12.62%, 10.75%, 1.00%, 0.63% respectively. best terms recall F1 score. In degradation motion level model, maximum accuracy, overall index, index 87.77%, 6.54%, 2.18%, 7.02%, 7.48%, 10.15%, 3.56%, 2.5% higher than fuzzy 94.3%, 3.85%, 1.285%, Compared 12.13%, 15.98%, 16.7%, 2.2%, 1.5% higher, Taking into account various indicators, can still maintain high recognition demonstrate good even when inputting blurry caused interference shooting. It meet growth environments, providing basis for post-seedling chemical weed control during soybeans.

Language: Английский

---

Drone imagery dataset for early-season weed classification in maize and tomato crops

Data in Brief, Journal Year: 2024, Volume and Issue: 58, P. 111203 - 111203

Published: Dec. 6, 2024

Identifying weed species at early-growth stages is critical for precision agriculture. Accurate classification the species-level enables targeted control measures, significantly reducing pesticide use. This paper presents a dataset of RGB images captured with Sony ILCE-6300L camera mounted on an unmanned aerial vehicle (UAV) flying altitude 11 m above ground level. The covers various agricultural fields in Spain, focusing two summer crops: maize and tomato. It designed to enhance early-season accuracy by including from phenological stages. Specifically, contains 31,002 labeled stage-maize four unfolded leaves (BBCH14) tomato first flower bud visible (BBCH501)-as well as 36,556 more advanced-growth seven (BBCH17) ninth (BBCH509). In maize, include

Language: Английский

---