A5013019306- Smart Agriculture and AI
- Advanced Neural Network Applications
- Advanced Computational Techniques and Applications
- Spectroscopy and Chemometric Analyses
- Remote Sensing in Agriculture
- Distributed and Parallel Computing Systems
- Advanced Image and Video Retrieval Techniques
- Domain Adaptation and Few-Shot Learning
- Energy Harvesting in Wireless Networks
- Remote Sensing and Land Use
- Food Supply Chain Traceability
- Advanced Image Fusion Techniques
- Soil Moisture and Remote Sensing
- Advanced Algorithms and Applications
- Leaf Properties and Growth Measurement
- Embedded Systems and FPGA Design
- Technology and Security Systems
- Plant Surface Properties and Treatments
- Image and Signal Denoising Methods
- RFID technology advancements
- Wireless Sensor Networks and IoT
- Advanced Text Analysis Techniques
- Advanced Image Processing Techniques
- Image Enhancement Techniques
- Visual Attention and Saliency Detection
China Agricultural University
2014-2024
Ministry of Agriculture and Rural Affairs
2018-2024
Puer University
2024
Analogic (United States)
2021
Analysis Group (United States)
2017-2019
Shanghai Key Laboratory of Trustworthy Computing
2013
Soil moisture is directly related to the amount of irrigation in agriculture and influences yield crops. Accordingly, a soil sensor an important tool for measuring content. In this study, previous research conducted recent 2-3 decades on sensors was reviewed principles commonly used their various applications were summarized. Furthermore, advantages, disadvantages, influencing factors measurement methods employed compared analyzed. The improvements presented by several scholars have...
Fine-grained image classification methods often suffer from the challenge that subordinate categories within an entry-level category can only be distinguished by subtle differences. Crop disease is affected various visual interferences, including uneven illumination, dew, and equipment jitter. It demands effective algorithm to accurately discriminate one others. Thus, representational ability of needs strengthened learn a robust domain-specific discrimination through way. To address this...
Maturity level-based classification system plays an essential role in the design of tomato harvesting robot. Traditional knowledge-based systems are unable to meet current production management requirements precision picking, because they time-consuming and have low accuracy. Our research proposes improved deep learning-based method that improves accuracy scalability ripeness with a small amount training data. This study was on relationship between different dataset augmentation methods...
China's soybean supply and demand are seriously imbalanced. It is crucial to improve the level of breeding. Hundred-grain weight one most essential phenotypic parameters for crop Accurate seed counting a key step 100-grain weight. There several methods, which have their own limitations way or other. Among these, manual time-consuming, electronic automatic counter devices expensive speed very slow, traditional digital image processing techniques not suitable based on individual pod images....
Effective and efficient fruit detection is considered crucial for designing automated robot (AuRo) yield estimation, disease control, harvesting, sorting, grading. Several schemes AuRo have been developed during the last decades. However, conventional methods are deficient in real-time response, accuracy, extensibility. This paper proposes an improved multi-task cascaded convolutional network-based intelligent method. method has capability to make work real time with high accuracy. Moreover,...
Abstract Currently, there is a growing demand for water treatment technologies considering global environmental challenges such as degradation and depletion of resources. Micro- nanobubble (MNB) technology its application wastewater has emerged problem-solving alternative challenges. This paper reviews the important studies on in areas MNBs discusses their fundamental properties, bubble stability (as tiny entities solutions), generation methods, various chemical physical features. The...
Since the 2010s, unmanned aerial vehicle (UAV) sprayer was applied more and widely for low-volume pesticides spraying operations in China. However, droplets from UAV have a higher drift risk due to fine sprayed flight height than ground sprayers. Study on spray has been new hot spot within field of pesticide application technology. Most previous studies used direct methods drift, but meteorological conditions were unstable uncontrollable, research under an actual operation state wind tunnel...
The consequent and accurate monitoring of the seasonal dynamics crop leaf area index (LAI) is critical to yield estimation agriculture policy development. It difficult for a single sensor balance spatial temporal resolution. Spatiotemporal fusion an effective way meet need high applications. Among methods, regression model Fitting, Filtering residual Compensation (Fit-FC) may be recommended vegetation dynamic because its outperformance cases with considerable phenological changes. However,...
Deep learning architecture has achieved amazing success in many areas with the recent advancements convolutional neural networks (CNNs). However, real-time applications of CNNs are seriously hindered by significant storage and computational costs. Structured pruning is a promising method to compress accelerate does not need special hardware or software for an auxiliary calculation. Here simple strategy structured approach proposed crop unimportant filters neurons automatically during...
Plant height and leaf area are important morphological properties of leafy vegetable seedlings, they can be particularly useful for plant growth health research. The traditional measurement scheme is time-consuming not suitable continuously monitoring health. Individual seedling quick segmentation the prerequisite high-throughput phenotype data extraction at individual level. This paper proposes an efficient learning- model-free 3D point cloud processing pipeline to measure every single in a...
Accurate and continuous monitoring of crop growth is vital for the development precision agriculture. Unmanned aerial vehicle (UAV) satellite platforms have considerable complementarity in high spatial resolution (centimeter-scale) fixed revisit cycle. It meaningful to optimize cross-platform synergy agricultural applications. Considering characteristics UAV platforms, a spatio-temporal fusion (STF) framework imagery developed. includes registration, radiometric normalization, preliminary...