A5075227581- Remote Sensing and Land Use
- Remote-Sensing Image Classification
- Remote Sensing in Agriculture
- Smart Agriculture and AI
- Remote Sensing and LiDAR Applications
- Automated Road and Building Extraction
- Advanced Image Fusion Techniques
- Medical Image Segmentation Techniques
- Species Distribution and Climate Change
- Industrial Vision Systems and Defect Detection
- Video Surveillance and Tracking Methods
- Environmental and Agricultural Sciences
Anhui University
2022-2025
Crop mapping is vital in ensuring food production security and informing governmental decision-making. The satellite-normalized difference vegetation index (NDVI) obtained during periods of vigorous crop growth important for species identification. Sentinel-2 images with spatial resolutions 10, 20, 60 m are widely used mapping. However, the often covered by clouds. In contrast, time-series moderate-resolution imaging spectrometer (MODIS) can usually capture phenology but coarse resolution....
Obtaining accurate and timely crop area information is crucial for yield estimates food security. Because most existing mapping models based on remote sensing data have poor generalizability, they cannot be rapidly deployed identification tasks in different regions. Based a priori knowledge of phenology, we designed an off-center Bayesian deep learning classification method that can highlight phenological features, combined with attention mechanism residual connectivity. In this paper, first...
Semantic segmentation of high-resolution remote sensing images is vital for various applications, including environmental monitoring, urban planning, and land resource management. Nonetheless, these frequently pose challenges owing to substantial intra-class similarity considerable inter-class variation, which often result in the misclassification small target objects. To address issues, we introduce an innovative deep learning network model that employs pixel memory sharing improve feature...
The complex remote sensing image acquisition conditions and the differences in crop growth create many classification challenges. Frequency decomposition enables capture of feature information an that is difficult to discern. domain filters can strengthen or weaken specific frequency components enhance interclass among different crops reduce intraclass variations within same crops, thereby improving accuracy. In concurrence with Fourier learning strategy, we propose a convolutional neural...
Obtaining accurate and timely crop mapping is essential for refined agricultural refinement food security. Due to the spectral similarity between different crops, influence of image resolution, boundary blur spatial inconsistency that often occur in remotely sensed mapping, still faces great challenges. In this article, we propose extend a neighborhood window centered on target pixel enhance receptive field our model extract features sizes through multiscale network. addition, also designed...
High-resolution remote sensing image-based vegetation monitoring is a hot topic in technology and applications. However, when facing large-scale across different sensors broad areas, the current methods suffer from fragmentation weak generalization capabilities. To address this issue, paper proposes multisource high-resolution extraction method that considers comprehensive perception of multiple features. First, utilizes random forest model to perform feature selection for index, selecting...
Remote sensing road extraction based on deep learning is an important method for extraction. However, in complex remote images, different information often exhibits varying frequency distributions and texture characteristics, it usually difficult to express the comprehensive characteristics of roads effectively from a single spatial domain perspective. To address aforementioned issues, this article proposes that couples global with Fourier learning. This first utilizes transformer capture...