Kai Ding

Dr. Kai Ding

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
27 November 2017 in Remote Sensing
Verified
Journal Article
Open access
PDF file
CYChao Yang
Chao Yang
GWGuofeng Wu
Guofeng Wu
KDKai Ding
Kai Ding
TSTiezhu Shi
Tiezhu Shi
QLQingquan Li
Qingquan Li
JWJinliang Wang
Jinliang Wang
Decision tree classification is one of the most efficient methods for obtaining land use/land cover (LULC) information from remotely sensed imageries. However, traditional decision tree classification methods cannot effectively eliminate the influence of mixed pixels. This study aimed to integrate pixel unmixing and decision tree to improve LULC classification by removing mixed pixel influence. The abundance and minimum noise fraction (MNF) results that were obtained from mixed pixel decomposition were added to decision tree multi-features using a three-dimensional (3D) Terrain model, which was created using an image fusion digital elevation model (DEM), to select training samples (ROIs), and improve ROI separability. A Landsat-8 OLI image of the Yunlong Reservoir Basin in Kunming was used to test this proposed method. Study results showed that the Kappa coefficient and the overall accuracy of integrated pixel unmixing and decision tree method increased by 0.093% and 10%, respectively, as compared with the original decision tree method. This proposed method could effectively eliminate the influence of mixed pixels and improve the accuracy in complex LULC classifications.

11 February 2018 in Sensors
Verified
Journal Article
Open access
PDF file
KDKai Ding
Kai Ding
QLQingquan Li
Qingquan Li
JZJiasong Zhu
Jiasong Zhu
CWChisheng Wang
Chisheng Wang
MGMinglei Guan
Minglei Guan
JLJianghai Liao
Jianghai Liao
In this paper, an improved method based on a mixture of Gaussian and quadrilateral functions is presented to process airborne bathymetric LiDAR waveforms. In the presented method, the LiDAR waveform is fitted to a combination of three functions: one Gaussian function for the water surface contribution, another Gaussian function for the water bottom contribution, and a new quadrilateral function to fit the water column contribution. The proposed method was tested on a simulated dataset and a real dataset, with the focus being mainly on the performance of retrieving bottom response and water depths. We also investigated the influence of the parameter settings on the accuracy of the bathymetry estimates. The results demonstrate that the improved quadrilateral fitting algorithm shows a superior performance in terms of low RMSE and a high detection rate in the water depth and magnitude retrieval. What’s more, compared with the use of a triangular function or the existing quadrilateral function to fit the water column contribution, the presented method retrieved the least noise and the least number of unidentified waveforms, showed the best performance in fitting the return waveforms, and had consistent fitting goodness for all different water depths.

Verified
Journal Article
Open access
PDF file
YCYang Cui
Yang Cui
QLQingquan Li
Qingquan Li
QLQingyuan Li
Qingyuan Li
JZJiasong Zhu
Jiasong Zhu
CWChisheng Wang
Chisheng Wang
BYBisheng Yang
Bisheng Yang
: The spatial interpolation of property fields in 3D, such as the temperature, salinity, and organic content of ocean water, is an active area of research in the applied geosciences. Conventional interpolation methods have not adequately addressed anisotropy in these data. Thus, in our research we considered two interpolation methods based on a triangular prism volume element, as a triangular prism structure best represents directivity, to express the anisotropy inherent in geological property fields. A linear triangular prism interpolation is proposed for layered stratum that achieves a complete continuity based on the volume coordinates of the triangular prism. A triangular prism quadric interpolation (a unit function of a triangular prism spline with 15 nodes) is designed for a smooth transition between adjacent triangular prisms with approximately continuity, expressing the continuity of the entire model. We designed a specific model which accounts for the different spatial correlations in three dimensions. We evaluated the accuracy of our proposed linear and triangular prism quadric interpolation methods with traditional inverse distance weighting (IDW) and kriging interpolation approaches in comparative experiments. The results show that, in 3D geological modeling, the linear and quadric triangular prism interpolations more accurately represent the changes in the property values of the layered strata than the IDW and kriging interpolation methods. Furthermore, the triangular prism quadric interpolation algorithm with 15 nodes outperforms the other methods. This study of triangular prism interpolation algorithms has implications for the expression of data fields with 3D properties. Moreover, our novel approach will contribute to spatial attribute prediction and representation and is applicable to all 3D geographic information; for example, in studies of atmospheric circulation, ocean circulation, water temperature, salinity, and three-dimensional pollutant diffusion.

11 November 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
KDKai Ding
Kai Ding
YHYidu Huang
Yidu Huang
CWChisheng Wang
Chisheng Wang
QLQingquan Li
Qingquan Li
CYChao Yang
Chao Yang
MDMing Dai
Ming Dai
Shenzhen has experienced rapid urbanization since the establishment of the Special Economic Zone in 1978. However, it is rare to witness high-speed urbanization in Shenzhen. It is important to study the LUCC progress in Shenzhen (regarding refusing multisource data), which can provide a reference for governments to solve the problems of land resource shortages and urban expansion spaces. In this paper, nine Landsat images were used to retrieve land cover maps in Shenzhen, China, from 1979 to 2022. The classification method is based on support vector machines with assistance from visual interpretation. The results show that the urban area increased by 756.84 km2, the vegetation area decreased by 546.27 km2, the water area decreased by 132.95 km2, and the bare area decreased by 77.62 km2 in the last 43 years of our research region. Urban sprawl starts from the Luohu district, then propagates to Futian, Nanshan, and Yantian districts, and finally expands to other outlying districts (Baoan, Longgang, Guangming, Dapeng, and Pingshan). The spatial–temporal characteristics and the impact factors of urbanization were further analyzed. The visualization of land cover changes based on a complex network approach reveals that the velocity of urban expansion is growing. The coastline distributions were retrieved from nine observation times from 1979 to 2022; the results show that the west coastline changed more dramatically than the east and most of the east coastline remained stable, except for the parts near Yantian port and Mirs Bay, which experienced some changes. The impact factors of coastline changes are further discussed. Through a correlation analysis using urban data, such as transportation and socioeconomic factors, it was found that elevation and roads have strong constraints on the spatial patterns of a city’s expansion. There is exponential decay in the urban land increase against the distance to the roads, implying that traffic factors greatly determine urban land expansion. The turning point of the exponential decay is a distance of around 150 m. Time and population are highly correlated with land use development, indicating that urban land grows linearly with time and the population, which are important driving forces of urban land development. Compared with secondary and tertiary industries, the primary industry is less related to urban land use in Shenzhen.

12 April 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XFXu Fang
Xu Fang
QLQing Li
Qing Li
QLQingquan Li
Qingquan Li
KDKai Ding
Kai Ding
JZJiasong Zhu
Jiasong Zhu
Visual odometry is the task of estimating the trajectory of the moving agents from consecutive images. It is a hot research topic both in robotic and computer vision communities and facilitates many applications, such as autonomous driving and virtual reality. The conventional odometry methods predict the trajectory by utilizing the multiple view geometry between consecutive overlapping images. However, these methods need to be carefully designed and fine-tuned to work well in different environments. Deep learning has been explored to alleviate the challenge by directly predicting the relative pose from the paired images. Deep learning-based methods usually focus on the consecutive images that are feasible to propagate the error over time. In this paper, graph loss and geodesic rotation loss are proposed to enhance deep learning-based visual odometry methods based on graph constraints and geodesic distance, respectively. The graph loss not only considers the relative pose loss of consecutive images, but also the relative pose of non-consecutive images. The relative pose of non-consecutive images is not directly predicted but computed from the relative pose of consecutive ones. The geodesic rotation loss is constructed by the geodesic distance and the model regresses a Lie algebra so(3) (3D vector). This allows a robust and stable convergence. To increase the efficiency, a random strategy is adopted to select the edges of the graph instead of using all of the edges. This strategy provides additional regularization for training the networks. Extensive experiments are conducted on visual odometry benchmarks, and the obtained results demonstrate that the proposed method has comparable performance to other supervised learning-based methods, as well as monocular camera-based methods. The source code and the weight are made publicly available.