yanyue li

Dr. yanyue li

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 October 2023 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
Tianhua ChenTianhua Chen
Tianhua Chen
YLyanyue li
yanyue li
QQQinghua Qiao
Qinghua Qiao

22 July 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
QQQinghua Qiao
Qinghua Qiao
YLyanyue li
yanyue li
HLHuaquan Lv
Huaquan Lv
In the era of remote sensing big data, the intelligent interpretation of remote sensing images is a key technology for mining the value of remote sensing big data and promoting a number of major applications, mainly including land cover classification and extraction. Among these, the rapid extraction of open-pit mining areas plays a vital role in current practices for refined mineral resources development and management and ecological–environmental protection in China. However, existing methods are not accurate enough for classification, not fine enough for boundary extraction, and poor in terms of multi-scale adaptation. To address these issues, we propose a new semantic segmentation model based on Transformer, which is called Segmentation for Mine—SegMine—and consists of a Vision Transformer-based encoder and a lightweight attention mask decoder. The experimental results show that SegMine enhances the network’s ability to obtain local spatial detail information and improves the problem of disappearing small-scale object features and insufficient information expression. It also better preserves the boundary details of open-pit mining areas. Using the metrics of mIoU, precision, recall, and dice, experimental areas were selected for comparative analysis, and the results show that the new method is significantly better than six other existing major Transformer variants.

21 March 2023 in Research Square
Verified
Preprint
Open access
PDF file
Tianhua ChenTianhua Chen
Tianhua Chen
YLyanyue li
yanyue li
QQQinghua Qiao
Qinghua Qiao
Identifying bird targets, especially scarce birds, is essential to reflect the level of ecological protection and diversity. A fine-grained bird identification model with hierarchical feature fusion and counterfactual feature selection is proposed due to the problems of similar features, slight differences, and difficulty of identification among different birds. The model comprises a feature extraction network, a hierarchical feature fusion module, and a counterfactual feature selection module. The feature extractor extracts local area image features and global image features. The hierarchical feature fusion module fuses fine-grained information from the shallow layers of the network and semantic information from the current layer. The counterfactual feature enhancement module sifts out the distinguishing features fed to the classifier by counterfactual intervention. The experimental results show that the method can achieve 91.9% and 91.4% accuracy on two available datasets, CUB-200-2011 and NABirds, respectively, which is higher than the current mainstream fine-grained bird recognition algorithms and shows excellent classification performance.