Qinghua Qiao

Prof. Dr. Qinghua Qiao

Chinese Academy of Surveying and Mapping, Beijing, China
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
TZTong Zhang
Tong Zhang
JWJianlong Wang
Jianlong Wang
CCChenrong Cui
Chenrong Cui
YLYicong Li
Yicong Li
WHWei He
Wei He
QQQinghua Qiao
Qinghua Qiao
Understanding human movement patterns is of fundamental importance in transportation planning and management. We propose to examine complex public transit travel patterns over a large-scale transit network, which is challenging since it involves thousands of transit passengers and massive data from heterogeneous sources. Additionally, efficient representation and visualization of discovered travel patterns is difficult given a large number of transit trips. To address these challenges, this study leverages advanced machine learning methods to identify time-varying mobility patterns based on smart card data and other urban data. The proposed approach delivers a comprehensive solution to pre-process, analyze, and visualize complex public transit travel patterns. This approach first fuses smart card data with other urban data to reconstruct original transit trips. We use two machine learning methods, including a clustering algorithm to extract transit corridors to represent primary mobility connections between different regions and a graph-embedding algorithm to discover hierarchical mobility community structures. We also devise compact and effective multi-scale visualization forms to represent the discovered travel behavior dynamics. An interactive web-based mapping prototype is developed to integrate advanced machine learning methods with specific visualizations to characterize transit travel behavior patterns and to enable visual exploration of transit mobility patterns at different scales and resolutions over space and time. The proposed approach is evaluated using multi-source big transit data (e.g., smart card data, transit network data, and bus trajectory data) collected in Shenzhen City, China. Evaluation of our prototype demonstrates that the proposed visual analytics approach offers a scalable and effective solution for discovering meaningful travel patterns across large metropolitan areas.

18 October 2023 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
Tianhua ChenTianhua Chen
Tianhua Chen
YLyanyue li
yanyue li
QQQinghua Qiao
Qinghua Qiao

26 June 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
DDDehui Dong
Dehui Dong
Dongping MingDongping Ming
Dongping Ming
LXLu Xu
Lu Xu
QQQinghua Qiao
Qinghua Qiao
YZYu Zhang
Yu Zhang
Quickly obtaining fine-scale mining area types information in large-scale scenes is significant for dynamically detecting mineral resources. Currently, mining area types recognition methods encounter challenges such as low recognition accuracy and difficulty detecting small mining areas. To address these issues, this paper proposes a stepwise top-down mining area types recognition framework. The framework consists of two steps. Firstly, a GF-5 spectral index named the Normalized Difference Mining Area Index (NDMAI) is constructed to obtain the rough position of the mining area quickly. Then, the identification network of Mine Types with Transformer (Mitformer) is proposed for accurate type recognition of the candidate mining area regions. Mitformer combines a multi-scale feature enhancement module and a decoder based on multi-level skip connections, which achieves a sufficient fusion of features at each layer of deep feature maps and adds the skip connections between low-level and high-level feature maps, thus can improve the accuracy of types identification and the detection rate of small-scale mining areas. Moreover, this framework can effectively avoid misclassification caused by different objects with similar spectra to the maximum extent possible. This paper selects two independent study areas with a large spatial extent respectively in Hebei Province and Anhui Province. The imagery utilized for these regions is obtained from Chinese GF-2 and GF-5 satellites. Multiple experiments are conducted to verify the superiority of NDMAI and Mitformer and the effectiveness of this framework. The experimental results illustrate that this framework can provide adequate technical support for the dynamic detection of mineral resources.

5 July 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
QQQinghua Qiao
Qinghua Qiao
YZYing Zhang
Ying Zhang
JLJia Liu
Jia Liu
HXHao Xu
Hao Xu
LGLin Gan
Lin Gan
Research on the potential accessibility of medical services has made great progress, but there is a large gap between the analysis results and the actual feelings of residents. With the refinement of urban management, the need for actual accessibility calculations reflecting the current status of medical service levels is becoming stronger. In modern society, as people work and live at an increasingly fast pace, people increasingly focus on time saving. However, in addition to travel time and distance, personal perceptions of medical facilities and access habits also influence residents’ choice of specific hospitals for medical treatment. With the combined effect of these factors, the actual status of accessibility of medical facility services is formed. In order to improve estimates of the actual accessibility and narrow the gap with residents’ subjective perceptions, this study leverages realistic data, such as real-time navigation prediction data that approximates residents’ actual travel time to hospitals and information on residents’ subjective behaviors in choosing specific hospitals for medical treatment. Finally, a new approach is proposed to further improve the existing Gaussian two-step floating catchment area (Ga2SFCA) method by fully respecting the important effects of distance cost and time cost, and combining them by using a weighted mean.

22 July 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
QQQinghua Qiao
Qinghua Qiao
YLyanyue li
yanyue li
HLHuaquan Lv
Huaquan Lv
In the era of remote sensing big data, the intelligent interpretation of remote sensing images is a key technology for mining the value of remote sensing big data and promoting a number of major applications, mainly including land cover classification and extraction. Among these, the rapid extraction of open-pit mining areas plays a vital role in current practices for refined mineral resources development and management and ecological–environmental protection in China. However, existing methods are not accurate enough for classification, not fine enough for boundary extraction, and poor in terms of multi-scale adaptation. To address these issues, we propose a new semantic segmentation model based on Transformer, which is called Segmentation for Mine—SegMine—and consists of a Vision Transformer-based encoder and a lightweight attention mask decoder. The experimental results show that SegMine enhances the network’s ability to obtain local spatial detail information and improves the problem of disappearing small-scale object features and insufficient information expression. It also better preserves the boundary details of open-pit mining areas. Using the metrics of mIoU, precision, recall, and dice, experimental areas were selected for comparative analysis, and the results show that the new method is significantly better than six other existing major Transformer variants.

5 September 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
ZLZhangmai Li
Zhangmai Li
QQQinghua Qiao
Qinghua Qiao
ZHZibin Han
Zibin Han
XLXinyi Liu
Xinyi Liu
YWYueyang Wang
Yueyang Wang
Lei DengLei Deng
Lei Deng
With the growing global emphasis on forest resource monitoring, evaluating the accuracy of retrieving key individual tree parameters-such as tree position, tree height, and diameter at breast height (DBH)-using Terrestrial Laser Scanning (TLS) has become an important research focus. TLS has been widely applied in forest surveys due to its significant advantages in data acquisition efficiency and measurement precision. However, studies on the accuracy of extracting forest parameters from single-station, single-scan TLS data remain limited, underscoring the need for systematic evaluation and validation. This paper analyzes the accuracy and effectiveness of TLS in extracting structural parameters (tree height and DBH) and its position using Poplar and Styphnolobium as examples by using TLS, Airborne laser Scanning (ALS), and combining with field measurements. Results show that tree height estimates from single-scan TLS is limited in accuracy: the RMSE of 11.61 m in the Populus plot and 2.13 m in the Styphnolobium plot. Within a 50 m radius, single-scan TLS achieves a tree detection rate of 55.96–64.26% and a DBH RMSE of 1.60 cm (RRMSE: 9.03%). In addition, the point root mean square error of individual tree measurements remains at 0.11 m. These findings highlight the potential of TLS as an effective tool for forest inventory and provide a basis for evaluating the reliability of TLS-based plot measurements.