Lianzi Tong

Dr. Lianzi Tong

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
26 August 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FGFan Ge
Fan Ge
GWGuizhou Wang
Guizhou Wang
GHGuojin He
Guojin He
Dengji ZhouDengji Zhou
Dengji Zhou
RYRanyu Yin
Ranyu Yin
LTLianzi Tong
Lianzi Tong
In the context of global sustainable development, solar energy is very widely used. The installed capacity of photovoltaic panels in countries around the world, especially in China, is increasing steadily and rapidly. In order to obtain accurate information about photovoltaic panels and provide data support for the macro-control of the photovoltaic industry, this paper proposed a hierarchical information extraction method, including positioning information and shape information, and carried out photovoltaic panel distribution mapping. This method is suitable for large-scale centralized photovoltaic power plants based on multi-source satellite remote sensing images. This experiment takes the three northwest provinces of China as the research area. First, a deep learning scene classification model, the EfficientNet-B5 model, is used to locate the photovoltaic power plants on 16-m spatial resolution images. This step obtains the area that contains or may contain photovoltaic panels, greatly reducing the study area with an accuracy of 99.97%. Second, a deep learning semantic segmentation model, the U2-Net model, is used to precisely locate photovoltaic panels on 2-m spatial resolution images. This step achieves the exact extraction results of the photovoltaic panels from the area obtained in the previous step, with an accuracy of 97.686%. This paper verifies the superiority of a hierarchical information extraction method in terms of accuracy and efficiency through comparative experiments with DeepLabV3+, U-Net, SegNet, and FCN8s. This meaningful work identified 180 centralized photovoltaic power plants in the study area. Additionally, this method makes full use of the characteristics of different remote sensing data sources. This method can be applied to the rapid extraction of global photovoltaic panels.

2 August 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Qing GuoQing Guo
Qing Guo
LTLianzi Tong
Lianzi Tong
XYXudong Yao
Xudong Yao
YWYewei Wu
Yewei Wu
GWGuangtong WAN
Guangtong WAN
Clouds in optical remote sensing images are an unavoidable existence that greatly affect the utilization of these images. Therefore, accurate and effective cloud detection is an indispensable step in image preprocessing. To date, most researchers have tried to use deep-learning methods for cloud detection. However, these studies generally use computer vision technology to improve the performances of the models, without considering the unique spectral feature information in remote sensing images. Moreover, due to the complex and changeable shapes of clouds, accurate cloud-edge detection is also a difficult problem. In order to solve these problems, we propose a deep-learning cloud detection network that uses the haze-optimized transformation (HOT) index and the edge feature extraction module for optical remote sensing images (CD_HIEFNet). In our model, the HOT index feature image is used to add the unique spectral feature information from clouds into the network for accurate detection, and the edge feature extraction (EFE) module is employed to refine cloud edges. In addition, we use ConvNeXt as the backbone network, and we improved the decoder to enhance the details of the detection results. We validated CD_HIEFNet using the Landsat-8 (L8) Biome dataset and compared it with the Fmask, FCN8s, U-Net, SegNet, DeepLabv3+ and CloudNet methods. The experimental results showed that our model has excellent performance, even in complex cloud scenarios. Moreover, according to the extended experimental results for the other L8 dataset and the Gaofen-1 data, CD_HIEFNet has strong performance in terms of robustness and generalization, thus helping to provide new ideas for cloud detection-related work.

8 November 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Qing GuoQing Guo
Qing Guo
LTLianzi Tong
Lianzi Tong
HWHua Wang
Hua Wang
Landslides are one of the most dangerous natural disasters, which have affected national economic development and social stability. This paper proposes a method to indirectly monitor the deformation characteristics of landslides by extracting the abnormal vegetation information, especially for the inaccessible high-mountain landslides in southwestern China. This paper extracts the vegetation anomaly information in the Jizong Shed-Tunnel landslide which is located on the main traffic road to Tibet by the optical remote sensing Gaofen-1 (GF-1) data, and analyzes the temporal and spatial characteristics of the vegetation anomaly information through a time series. Then, we use the small baseline subsets interferometry synthetic aperture radar (SBAS-InSAR) technology to process Sentinel-1 data to obtain the time-series surface deformation information. Finally, we analyze and verify the results of the two methods. The results show that there is obvious vegetation coverage (VC) decline, with a maximum increasing percentage of 8.77% for the low and medium VC, and obvious surface deformation around the landslide, with the highest settlement rate of between 0 mm/year and 30 mm/year. Through the time-series analysis, we find that the change trends of the two methods are basically the same. This paper shows that the method of using abnormal vegetation information to monitor the Jizong Shed-Tunnel landslide has a certain degree of reliability and practicability. It can provide a new idea and effective supplement for landslide monitoring.