A5090143866- Smart Agriculture and AI
- Date Palm Research Studies
- Remote Sensing in Agriculture
- Remote-Sensing Image Classification
- Remote Sensing and LiDAR Applications
- Plant Virus Research Studies
- Hydrology and Watershed Management Studies
- Plant Disease Management Techniques
- Flood Risk Assessment and Management
- Water Quality Monitoring Technologies
- Hydrology and Drought Analysis
- Fire Detection and Safety Systems
- Advanced Neural Network Applications
Hefei Institutes of Physical Science
2015-2024
Chinese Academy of Sciences
2015-2024
Institute of Intelligent Machines
2022-2024
Effective maize and weed detection plays an important role in farmland management, which helps to improve yield save herbicide resources. Due their convenience high resolution, Unmanned Aerial Vehicles (UAVs) are widely used detection. However, there some challenging problems detection: (i) the cost of labeling is high, image contains many plants, annotation time-consuming labor-intensive; (ii) number much larger than field, this imbalance samples leads decreased recognition accuracy; (iii)...
Light traps have been widely used for automatic monitoring of pests in the field as an alternative to time-consuming and labor-intensive manual investigations. However, scale variation, complex background dense distribution light-trap images bring challenges rapid accurate detection when utilizing vision technology. To overcome these challenges, this paper, we put forward a lightweight pest model, AgriPest-YOLO, achieving well-balanced between efficiency, accuracy model size detection....
The Danjiangkou Reservoir (DJKR) is the freshwater source for Middle Route of South-to-North Water Diversion Project (MRSNWDP) in China. It important to characterize dam water level (DWL) and surface area (SWA) DJKR MRSNWDP. In this study, 81 phases time-series Landsat images are used estimate SWA from 1993 2015. situ-observed DWL data employed investigate relationship between DJKR. results show that polynomial functions can describe relationship, quantitative assessment qualitative analysis...
In precision agriculture, effective monitoring of corn pest regions is crucial to developing early scientific prevention strategies and reducing yield losses. However, complex backgrounds small objects in real farmland bring challenges accurate detection. this paper, we propose an improved model based on YOLOv4 that uses contextual information attention mechanism. Firstly, a context priming module with simple architecture designed, where features different layers are fused as additional...
Effectively monitoring pest-infested areas by computer vision is essential in precision agriculture order to minimize yield losses and create early scientific preventative solutions. However, the scale variation, complex background, dense distribution of pests bring challenges accurate detection when utilizing technology. Simultaneously, supervised learning-based object heavily depends on abundant labeled data, which poses practical difficulties. To overcome these obstacles, this paper, we...
Cropland extraction has great significance in crop area statistics, intelligent farm machinery operations, agricultural yield estimates, and so on. Semantic segmentation is widely applied to remote sensing image cropland extraction. Traditional semantic methods using convolutional networks result a lack of contextual boundary information when extracting large areas cropland. In this paper, we propose enhancement network for high-resolution images (HBRNet). HBRNet uses Swin Transformer with...
With the rapid progress of object detection, intelligent and effective crop pest region detection becomes possible. However, supervised learning-based relies significantly on a large amount labeled data, which presents challenges in real-world applications. Meanwhile, using vision technology to accurately detect insect infested regions is challenging due their dense distribution small target. To overcome these obstacles, this paper, we put forward an innovative semi-supervised framework,...
In recent years, remote sensing analysis has gained significant attention in visual applications, particularly segmenting and recognizing images. However, the existing research predominantly focused on single-period RGB image analysis, thus overlooking complexities of capture, especially highly vegetated land parcels. this paper, we provide a large-scale vegetation (VRS) dataset introduce VRS-Seg task for multi-modal multi-temporal segmentation. The VRS incorporates diverse modalities...