Yanyan Liu

Dr. Yanyan Liu


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
24 April 2024 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
XXXiaoyu Xu
Xiaoyu Xu
WZweida zhan
weida zhan
YJYichun Jiang
Yichun Jiang
DZDepeng Zhu
Depeng Zhu
YCYu Chen
Yu Chen
YLYanyan Liu
Yanyan Liu
Single-frame infrared small target detection is affected by the low image resolution and small target size, and is prone to the problems of small target feature loss and positional offset during continuous downsampling; at the same time, the sparse features of the small targets do not correlate well with the global-local linkage of the background features. To solve the above problems, this paper proposes an efficient infrared small target detection method. First, this paper incorporates BlurPool in the feature extraction part, which reduces the loss and positional offset of small target features in the process of convolution and pooling. Second, this paper designs an interactive attention deep feature fusion module, which acquires the correlation information between the target and the background from a global perspective, and designs a compression mechanism based on deep a priori knowledge, which reduces the computational difficulty of the self-attention mechanism. Then, this paper designs the context local feature enhancement and fusion module, which uses deep semantic features to dynamically guide shallow local features to realize enhancement and fusion. Finally, this paper proposes an edge feature extraction module for shallow features, which utilizes the complete texture and location information in the shallow features to assist the network to initially locate the target position and edge shape. Numerous experiments show that the method in this paper significantly improves nIoU, F1-Measure and AUC on IRSTD-1k Datasets and NUAA-SIRST Datasets.

31 January 2020 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
JLJin Li
Jin Li
Fei XingFei Xing
Fei Xing
YLYanyan Liu
Yanyan Liu
Zilong LiuZilong Liu
Zilong Liu

16 December 2020 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JLJin Li
Jin Li
YLYanyan Liu
Yanyan Liu
Remote sensing images are easily degraded because the imaging process is influenced by the camera itself link (CIL), such as optical systems, electronic systems, and image sensors. The invariant modulation transfer function (IMTF) of a remote sensing camera can represent the degeneration produced by the CIL. Thus, the IMTF compensation can remove the degeneration of the CIL to improve the image quality. However, conventional IMTF measurement methods using a single feature (e.g., edge or pulse) have low measurement accuracy due to the influence of noises, resulting in low image compensation quality. Here, we propose an efficient measurement method of the IMTF in conjunction with a learning approach to compensate for the imaging degeneration. The IMTF from the CIL is measured using multiple diffractive grids, which are generated by two 1-D gratings. A learning approach is proposed to estimate the IMTF from the diffractive grids, where diffractive grids are not directly used as a point spread function (PSF) because grids are easily affected by various noises and result in low reconstruction accuracy of the IMTF. We experimentally confirm that the proposed method is useful for the IMTF estimations and compensation for image quality degeneration of remote sensing cameras under noise conditions. The proposed methods can double the MTF reconstruction accuracy and yield higher image compensation quality compared with traditional methods.