The accurate detection and identification of plant diseases is an essential step in the development intelligent modernized agricultural production. This study proposes a deep learning model (PPLC-Net) incorporating dilated convolution, multi-level attention mechanism, GAP layers. uses novel weather data augmentation to expand sample size enhance generalization robustness feature extraction. extraction network extends perceptual field convolutional domain using sawtooth convolution with...

Detecting and eliminating sprouted potatoes is a basic measure before potato storage, which can effectively improve the quality of storage reduce economic losses due to spoilage decay. In this paper, we propose an improved YOLOV5-based detection model for detecting grading in complex scenarios. By replacing Conv with CrossConv C3 module, feature similarity loss problem fusion process improved, representation enhanced. SPP using fast spatial pyramid pooling parameters speed up fusion. The...

Crop leaf diseases can reflect the current health status of crop, and rapid automatic detection field has become one difficulties in process industrialization agriculture. In widespread application various machine learning techniques, recognition time consumption accuracy remain main challenges moving agriculture toward industrialization. This article proposes a novel network architecture called YOLO V5-CAcT to identify crop diseases. The fast efficient lightweight V5 is chosen as base...

To solve the problems of weak generalization potato early and late blight recognition models in real complex scenarios, susceptibility to interference from crop varieties, colour characteristics, leaf spot shapes, disease cycles environmental factors, strong dependence on storage computational resources, an improved YOLO v5 model (DA-ActNN-YOLOV5) is proposed study diseases different multiple regional scenarios. Thirteen data augmentation techniques were used expand improve prevent...

Under the new demand model of Agriculture 4.0, automated spraying is a very complex task in precision agriculture, which needs to be combined with computerized vision perception system distinguish plant leaf density and execute operation real-time accordingly. Aiming at accurate determination grape density, an image method based on lightweight Vision Transformer (ViT) architecture proposed, designs fusion data augmentation containing dual spatial extension weather method, where former adopts...

In the realm of agriculture, crop yields fundamental cereals such as rice, wheat, maize, soybeans, and sugarcane are adversely impacted by insect pest invasions, leading to significant reductions in agricultural output. Traditional manual identification these pests is labor-intensive time-consuming, underscoring necessity for an automated early detection classification system. Recent advancements machine learning, particularly deep have provided robust methodologies a diverse array...

As global carbon reduction initiatives progress and the new energy sector rapidly develops, photovoltaic (PV) power generation is playing an increasingly significant role in renewable energy. Accurate PV output forecasting, influenced by meteorological factors, essential for efficient management. This paper presents optimal hybrid forecasting strategy, integrating bidirectional temporal convolutional networks (BiTCN), dynamic convolution (DC), long short-term memory (BiLSTM), a novel...

The act of fruit identification entails the discernment and classification various varieties, predicated upon their visual attributes. This task can be accomplished through methods, including manual inspection, traditional computer vision techniques, more advanced approaches using machine learning deep learning. Our work recognized 15 types fruit. experiment used imagery dataset, consisting class Avocado, Banana, Cherry, Apple Braeburn, golden 1, Apricot, Grape, Kiwi, Mango, Orange, Papaya,...

Accurate potato sprout detection is the key to automatic seed cutting, which important for quality and yield. In this paper, a lightweight DAS-YOLOv8 model proposed task. By embedding DAS deformable attention in feature extraction network fusion network, global context can be efficiently represented increased relevant pixel image region; then, C2f_Atten module fusing Shuffle designed based on C2f satisfy information of high-level abstract semantics network. At same time, ghost convolution...

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Accurate diagnosis of plant diseases is crucial for crop health. This study introduces the EDA–ViT model, a Vision Transformer (ViT)-based approach that integrates adaptive entropy-based data augmentation diagnosing custard apple (Annona squamosa) diseases. Traditional models like convolutional neural network and ViT face challenges with local feature extraction large dataset requirements. overcomes these by using multi-scale weighted aggregation interaction module, enhancing both global...

Tomato harvesting in intelligent greenhouses is crucial for reducing costs and optimizing management. Agricultural robots, as an automated solution, require advanced visual perception. This study proposes a tomato detection counting algorithm based on YOLOv8 (TCAttn-YOLOv8). To handle small, occluded targets images, new layer (NDL) added to the Neck Head decoupled structure, improving small object recognition. The ColBlock, dual-branch structure leveraging Transformer advantages, enhances...