A5049189767- Smart Agriculture and AI
- Spectroscopy and Chemometric Analyses
- Leaf Properties and Growth Measurement
- Insect Resistance and Genetics
- Advanced Chemical Sensor Technologies
- Plant Disease Management Techniques
- IoT and Edge/Fog Computing
- Insect symbiosis and bacterial influences
- Remote Sensing and Land Use
- Smart Systems and Machine Learning
- CRISPR and Genetic Engineering
- Insect and Pesticide Research
- Mosquito-borne diseases and control
- Food Supply Chain Traceability
- Remote Sensing and LiDAR Applications
China Agricultural University
2023-2025
Tsinghua University
2024
In this study, a deep-learning-based intelligent detection model was designed and implemented to rapidly detect cotton pests diseases. The integrates cutting-edge Transformer technology knowledge graphs, effectively enhancing pest disease feature recognition precision. With the application of edge computing technology, efficient data processing inference analysis on mobile platforms are facilitated. Experimental results indicate that proposed method achieved an accuracy rate 0.94, mean...
This study addresses the problem of maize disease detection in agricultural production, proposing a high-accuracy method based on Attention Generative Adversarial Network (Attention-GAN) and few-shot learning. The introduces an attention mechanism, enabling model to focus more significant parts image, thereby enhancing performance. Concurrently, data augmentation is performed through (GAN) generate training samples, overcoming difficulties Experimental results demonstrate that this surpasses...
The development of smart agriculture has created an urgent demand for efficient and accurate weed recognition detection technologies. However, the diverse complex morphology weeds, coupled with scarcity labeled data in agricultural scenarios, poses significant challenges to traditional supervised learning methods. To address these issues, a model based on semi-supervised diffusion generative network is proposed. This integrates attention mechanism semi-diffusion loss enable utilization both...
This study proposes a model for leafy vegetable disease detection and segmentation based on few-shot learning framework prototype attention mechanism, with the aim of addressing challenges complex backgrounds problems. Experimental results show that proposed method performs excellently in both object semantic tasks. In task, achieves precision 0.93, recall 0.90, accuracy 0.91, mAP@50 mAP@75 0.90. is 0.95, 0.92, 0.92. These significantly outperforms traditional methods, such as YOLOv10...
A novel deep learning model, DiffuCNN, is introduced in this paper, specifically designed for counting tobacco lesions complex agricultural settings. By integrating advanced image processing techniques with methodologies, the model significantly enhances accuracy of detecting under low-resolution conditions. After lesions, grading disease severity achieved through counting. The key features DiffuCNN include a resolution enhancement module based on diffusion, an object detection network...
With the rapid development of artificial intelligence and deep learning technologies, their applications in field agriculture, particularly plant disease detection, have become increasingly extensive. This study focuses on high-precision detection tomato diseases, which is paramount importance for agricultural economic benefits food safety. To achieve this aim, a image dataset was first constructed, NanoSegmenter model based Transformer structure proposed. Additionally, lightweight such as...
An innovative framework for peach tree disease recognition and segmentation is proposed in this paper, with the aim of significantly enhancing model performance complex agricultural settings through deep learning techniques data fusion strategies. The core innovations include a tiny feature attention mechanism backbone network, an aligned-head module, Transformer-based semantic specially designed alignment loss function. integration these technologies not only optimizes model’s ability to...
This study introduces a novel high-accuracy fruit fly detection model based on the Transformer structure, specifically aimed at addressing unique challenges in such as identification of small targets and accurate localization against complex backgrounds. By integrating step attention mechanism cross-loss function, this significantly enhances recognition flies within backgrounds, particularly improving model’s effectiveness handling small-sized its adaptability under varying environmental...