Liang Wu

Dr. Liang Wu

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
19 January 2018 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Yongyang XuYongyang Xu
Yongyang Xu
LWLiang Wu
Liang Wu
Zhong XieZhong Xie
Zhong Xie
ZCZhanlong Chen
Zhanlong Chen
Very high resolution (VHR) remote sensing imagery has been used for land cover classification, and it tends to a transition from land-use classification to pixel-level semantic segmentation. Inspired by the recent success of deep learning and the filter method in computer vision, this work provides a segmentation model, which designs an image segmentation neural network based on the deep residual networks and uses a guided filter to extract buildings in remote sensing imagery. Our method includes the following steps: first, the VHR remote sensing imagery is preprocessed and some hand-crafted features are calculated. Second, a designed deep network architecture is trained with the urban district remote sensing image to extract buildings at the pixel level. Third, a guided filter is employed to optimize the classification map produced by deep learning; at the same time, some salt-and-pepper noise is removed. Experimental results based on the Vaihingen and Potsdam datasets demonstrate that our method, which benefits from neural networks and guided filtering, achieves a higher overall accuracy when compared with other machine learning and deep learning methods. The method proposed shows outstanding performance in terms of the building extraction from diversified objects in the urban district.

16 August 2019 in Earth Science Informatics
Verified
Journal Article
Closed access
PDF file
QQQinjun Qiu
Qinjun Qiu
ZXZhong Xie
Zhong Xie
LWLiang Wu
Liang Wu
LTLiufeng Tao
Liufeng Tao
WLWenjia Li
Wenjia Li

DLDan Liu
Dan Liu
CGCheng guirong
Cheng guirong
LALina An
Lina An
XGXuguang Gan
Xuguang Gan
YWYulian Wu
Yulian Wu
LWLiang Wu
Liang Wu
Dementia is a serious public health problem. The more extensive dementia knowledge is, the more conducive it is to early prevention and treatment of dementia. However, no assessment of the general population’s dementia awareness has been conducted so far in China. Thus, this study assessed the national public knowledge of dementia based on mobile internet in China. We assessed 10,562 national respondents recruited based on the most popular social networking service in China, WeChat and analyzed the data using quantitative methods. The overall correct rate of total dementia knowledge was 63.14%. Only half of the participants (50.84%) could identify risk factors accurately. The level of dementia knowledge was positively associated with high education, city residency, and experience of exposure to information on dementia. The sandwich generation (aged 20–60 years) had the highest level of dementia knowledge. Chinese people were found to have a low level of knowledge about dementia, especially those aged over 60 years, with low education and living in rural areas. Further educational programs and campaigns are needed to improve dementia knowledge, with greater focus on the older population as the target audience, emphasis on dementia risk factors as educational content, correcting misconceptions about dementia, and providing more experience of exposure to dementia.

14 June 2019 in Earth and Space Science
Verified
Journal Article
Open access
PDF file
QQQinjun Qiu
Qinjun Qiu
ZXZhong Xie
Zhong Xie
LWLiang Wu
Liang Wu
LTLiufeng Tao
Liufeng Tao
A variety of detailed data about geological topics and geoscience knowledge are buried in the geoscience literature and rarely used. Named entity recognition (NER) provides both opportunities and challenges to leverage this wealth of data in the geoscience literature for data analysis and further information extraction. Existing NER models and techniques are mainly based on rule‐based and supervised approaches, and developing such systems requires a costly manual effort. In this paper, we first design a generic stepwise framework for domain‐specific NER. Following this framework, domain‐specific entities and domain‐general words are collected and selected as seed terms. Normalization and grouping processes are then applied to these seed terms for further analysis. A random extraction algorithm based on a unigram language model is used to generate a large‐scale training data set consisting of probabilistically labeled pseudosentences. Each generated sentence is then used as input to the self‐training and learning algorithm. Experimental results on two constructed data sets demonstrate that the proposed model effectively recognizes and identifies geological named entities.

11 March 2022 in Earth Science Informatics
Verified
Journal Article
Closed access
PDF file
HLHao Liu
Hao Liu
QQQinjun Qiu
Qinjun Qiu
LWLiang Wu
Liang Wu
WLWenjia Li
Wenjia Li
BWBin Wang
Bin Wang
YZYuan Zhou
Yuan Zhou

19 December 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Anna HuAnna Hu
Anna Hu
Zhong XieZhong Xie
Zhong Xie
Yongyang XuYongyang Xu
Yongyang Xu
MXMingyu Xie
Mingyu Xie
LWLiang Wu
Liang Wu
QQQinjun Qiu
Qinjun Qiu
One major limitation of remote-sensing images is bad weather conditions, such as haze. Haze significantly reduces the accuracy of satellite image interpretation. To solve this problem, this paper proposes a novel unsupervised method to remove haze from high-resolution optical remote-sensing images. The proposed method, based on cycle generative adversarial networks, is called the edge-sharpening cycle-consistent adversarial network (ES-CCGAN). Most importantly, unlike existing methods, this approach does not require prior information; the training data are unsupervised, which mitigates the pressure of preparing the training data set. To enhance the ability to extract ground-object information, the generative network replaces a residual neural network (ResNet) with a dense convolutional network (DenseNet). The edge-sharpening loss function of the deep-learning model is designed to recover clear ground-object edges and obtain more detailed information from hazy images. In the high-frequency information extraction model, this study re-trained the Visual Geometry Group (VGG) network using remote-sensing images. Experimental results reveal that the proposed method can recover different kinds of scenes from hazy images successfully and obtain excellent color consistency. Moreover, the ability of the proposed method to obtain clear edges and rich texture feature information makes it superior to the existing methods.