Hu Yijun

Hu Yijun

Auto-generated profile, based on publicly available information

Hu Yijun

School of Software, Shandong University, Jinan, China

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
1 August 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
XZXiangyu Zeng
Xiangyu Zeng
MXMingzhu Xu
Mingzhu Xu
YHYijun Hu
Yijun Hu
HTHaoyu Tang
Haoyu Tang
YHYupeng Hu
Yupeng Hu
LNLiqiang Nie
Liqiang Nie
In recent years, the task of salient object detection in optical remote sensing images (RSI-SOD) has received extensive attention. Benefiting from the development of deep learning, much progress has been made in RSI-SOD field. However, existing methods still face challenges in addressing various issues present in optical RSI, including uncertain numbers of salient objects, cluttered backgrounds, and interference from shadows. To address these challenges, we propose a novel approach, Adaptive Edge-aware Semantic Interaction Network (AESINet) for efficient salient object detection. Specifically, to improve the extraction of complex edge information, we design a Local Detail Aggregation Module (LDAM). This module can adaptively enhance the edge information of salient objects by leveraging our proposed difference perception mechanism. Notably, our difference perception mechanism is a novel edge enhancement method without the supervision of edge groundtruth. Additionally, to accurately locate salient objects of varying numbers and scales, we design a Multi-scale Feature Enhancement Module (MFEM), which effectively captures and utilizes multi-scale information. Moreover, we design the Deep Semantic Interaction Module (DSIM) to identify salient objects amidst cluttered backgrounds and effectively mitigate the interference of shadows. We conduct extensive experiments on three well-established optical RSI datasets and the results demonstrate that our proposed model outperforms 14 state-of-the-art methods. All codes and detection results are available at https://github.com/xumingzhu989/AESINet-TGRS.

1 July 2009
Verified
Conference Paper
Closed access
HYHu Yijun
Hu Yijun
GWGuirong Weng
Guirong Weng
Complementary DNA microarray technology is a powerful tool in many areas. Usually a two channel microarray red-green (RG) image is obtained. Due to the nature of cDNA microarray technology, a number of impairments affect the cDNA microarray image before the analysis such as identification of differentially expressed genes. Microarray image processing plays a crucial role in the extraction and quantitative analysis of the relative abundance of the DNA product. In this paper, a method combined K-means clustering algorithm and mathematical morphology is presented. Mathematical morphology is a useful tool for extracting image components. K-means clustering algorithm has a good performance in the segmentation of microarray image processing. The result of the experiment shows that the method presented in this paper is accurate, automatic and robust.