Xiaoli Liang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xiaoli Liang has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
Cancong Dai
Henan Univ
2 shared publicationsHaoxue Jia
Master’s Student, School of Software, Henan Univ., Kaifeng 475004, China
2 shared publicationsJiayao Wang
2 shared publications- Ke Liu
School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan 430023, China
2 shared publications Yuanwei Yang
Yangtze University
2 shared publications- Yunxiang Liu
School of Software, Henan University, Kaifeng, China
2 shared publications
Latest Publications
- 2 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 330
Direction-aware and boundary-enhanced hybrid Mamba-CNN network for building footprint extraction
- 2 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 330
Direction-aware and boundary-enhanced hybrid Mamba-CNN network for building footprint extraction
- 16 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-18
Point Cloud Semantic Segmentation Based on Boundary Awareness and Multiscale Spatial Descriptors
3D point cloud semantic segmentation is essential for 3D environment perception and scene understanding. A key challenge lies in enhancing object boundary segmentation accuracy and capturing global contextual features efficiently. However, most existing methods optimize boundaries only through local feature enhancement or explicit boundary optimization, and struggle to comprehensively capture global information. Therefore, we propose BAMS-Net, a novel point cloud semantic segmentation network, integrating boundary awareness and multi-scale spatial descriptors. Our model innovatively fuses local feature enhancement with explicit boundary optimization in depth, enabling improvement in boundary delineation. Specifically, candidate boundary points are first determined through a boundary prediction module based on local neighborhood semantic consistency, and an adaptive weight learning mechanism is adopted to suppress the feature interference from boundary points in their neighborhoods. Then the boundary segmentation performance is further improved through a boundary optimization aggregation loss that combines local semantic boundary loss and adaptive aggregation loss. To effectively capture global context, an adaptive calibration module is used to reweight the multi-level local features and strengthen the critical information, then the enhanced local features of each layer are converted into multi-scale global descriptor through cross-level fusion, thereby efficiently capturing global contextual information. Experimental results on the S3DIS and SensatUrban datasets demonstrate that BAMS-Net extracts richer point cloud features, delivers precise object boundary segmentation, and achieves superior overall performance in point cloud semantic segmentation.
- 16 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-18
Point Cloud Semantic Segmentation Based on Boundary Awareness and Multiscale Spatial Descriptors
3D point cloud semantic segmentation is essential for 3D environment perception and scene understanding. A key challenge lies in enhancing object boundary segmentation accuracy and capturing global contextual features efficiently. However, most existing methods optimize boundaries only through local feature enhancement or explicit boundary optimization, and struggle to comprehensively capture global information. Therefore, we propose BAMS-Net, a novel point cloud semantic segmentation network, integrating boundary awareness and multi-scale spatial descriptors. Our model innovatively fuses local feature enhancement with explicit boundary optimization in depth, enabling improvement in boundary delineation. Specifically, candidate boundary points are first determined through a boundary prediction module based on local neighborhood semantic consistency, and an adaptive weight learning mechanism is adopted to suppress the feature interference from boundary points in their neighborhoods. Then the boundary segmentation performance is further improved through a boundary optimization aggregation loss that combines local semantic boundary loss and adaptive aggregation loss. To effectively capture global context, an adaptive calibration module is used to reweight the multi-level local features and strengthen the critical information, then the enhanced local features of each layer are converted into multi-scale global descriptor through cross-level fusion, thereby efficiently capturing global contextual information. Experimental results on the S3DIS and SensatUrban datasets demonstrate that BAMS-Net extracts richer point cloud features, delivers precise object boundary segmentation, and achieves superior overall performance in point cloud semantic segmentation.
- 14 November 2025
- Published by Emerald Publishing in Engineering, Construction and Architectural Management
- Vol. 33 (13) , 10327-10351
Indoor building structure segmentation in unorganized point clouds based on corner feature
Purpose: Indoor structure segmentation is a key step in the scan-to-BIM, but current point cloud segmentation methods focus on point cloud geometry or semantic segmentation. Therefore, this study proposes a point cloud segmentation method specifically for indoor building structures, identifying and segmenting indoor structures from indoor point clouds without segmenting indoor objects, which reduces the waste of computational resources, improves the degree of automation, and the efficiency and accuracy of scan-to-BIM. Design/methodology/approach: This study proposes a geometry-driven segmentation framework specifically designed for indoor structural point clouds. The method introduces a novel corner feature (CF) to capture critical geometric transitions, enabling robust segment of vertical structures such as walls. Instead of relying on object semantics, the approach leverages ceiling geometry and elevation cues to differentiate structural elements (walls, floors, ceilings) from non-structural clutter. The overall design emphasizes lightweight computation, spatial reasoning and generalizability across diverse indoor environments. Findings: Experimental results on the Stanford Large-Scale 3D Indoor Spaces (S3DIS) and Matterport3D datasets confirm that ceiling boundary geometry, combined with elevation-based filtering, can robustly delineate architectural structures in cluttered indoor environments. The CF proves effective in detecting corner points and enabling the segmentation of both planar and curved vertical surfaces with high accuracy. Originality/value: This study focuses on the structural segmentation step within the scan-to-BIM process and proposes a lightweight, generalizable method based on contour features (CF) and elevation data. The method simplifies the workflow of indoor structural segmentation, enhances accuracy, improves BIM generation automation and supports the digital transformation of indoor building practices.
- 14 November 2025
- Published by Emerald Publishing in Engineering, Construction and Architectural Management
- Vol. 33 (13) , 10327-10351
Indoor building structure segmentation in unorganized point clouds based on corner feature
Purpose: Indoor structure segmentation is a key step in the scan-to-BIM, but current point cloud segmentation methods focus on point cloud geometry or semantic segmentation. Therefore, this study proposes a point cloud segmentation method specifically for indoor building structures, identifying and segmenting indoor structures from indoor point clouds without segmenting indoor objects, which reduces the waste of computational resources, improves the degree of automation, and the efficiency and accuracy of scan-to-BIM. Design/methodology/approach: This study proposes a geometry-driven segmentation framework specifically designed for indoor structural point clouds. The method introduces a novel corner feature (CF) to capture critical geometric transitions, enabling robust segment of vertical structures such as walls. Instead of relying on object semantics, the approach leverages ceiling geometry and elevation cues to differentiate structural elements (walls, floors, ceilings) from non-structural clutter. The overall design emphasizes lightweight computation, spatial reasoning and generalizability across diverse indoor environments. Findings: Experimental results on the Stanford Large-Scale 3D Indoor Spaces (S3DIS) and Matterport3D datasets confirm that ceiling boundary geometry, combined with elevation-based filtering, can robustly delineate architectural structures in cluttered indoor environments. The CF proves effective in detecting corner points and enabling the segmentation of both planar and curved vertical surfaces with high accuracy. Originality/value: This study focuses on the structural segmentation step within the scan-to-BIM process and proposes a lightweight, generalizable method based on contour features (CF) and elevation data. The method simplifies the workflow of indoor structural segmentation, enhances accuracy, improves BIM generation automation and supports the digital transformation of indoor building practices.
- 30 April 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
Missing Traffic Data Imputation based on Tensor Completion and Graph Network Fusion
During traffic data acquisition, missing data often arise owing to equipment failures and network disruptions. Despite extensive research on traffic data imputation, two primary limitations persist: First, existing methods struggle to fully integrate the spatiotemporal correlations and low-rank structures inherent in traffic data. Second, current research has mostly focused on missing completely at random (MCAR), with limited attention on other missing data patterns. We propose an innovative method, tensor completion and graph network fusion (TCGNF), to address these challenges for missing traffic data imputation. This method initially utilizes tensor completion for the preliminary imputation of missing data. Subsequently, it constructs the road network by leveraging the Pearson correlation coefficient from historical road data and the physical distances between detectors. The method then uses graph sampling and aggregation (GraphSAGE) to extract spatiotemporal data features from the two road networks and fuse them. Finally, these features are trained in generative adversarial networks (GANs) for accurate data imputation. Extensive experiments were conducted on two publicly accessible traffic datasets to validate the efficacy of the TCGNF model. The outcomes of these experiments indicate that the TCGNF model demonstrates superior generalization capabilities, significantly outperforming other state-of-the-art data imputation models concerning overall performance.
- 30 April 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
Missing Traffic Data Imputation based on Tensor Completion and Graph Network Fusion
During traffic data acquisition, missing data often arise owing to equipment failures and network disruptions. Despite extensive research on traffic data imputation, two primary limitations persist: First, existing methods struggle to fully integrate the spatiotemporal correlations and low-rank structures inherent in traffic data. Second, current research has mostly focused on missing completely at random (MCAR), with limited attention on other missing data patterns. We propose an innovative method, tensor completion and graph network fusion (TCGNF), to address these challenges for missing traffic data imputation. This method initially utilizes tensor completion for the preliminary imputation of missing data. Subsequently, it constructs the road network by leveraging the Pearson correlation coefficient from historical road data and the physical distances between detectors. The method then uses graph sampling and aggregation (GraphSAGE) to extract spatiotemporal data features from the two road networks and fuse them. Finally, these features are trained in generative adversarial networks (GANs) for accurate data imputation. Extensive experiments were conducted on two publicly accessible traffic datasets to validate the efficacy of the TCGNF model. The outcomes of these experiments indicate that the TCGNF model demonstrates superior generalization capabilities, significantly outperforming other state-of-the-art data imputation models concerning overall performance.
- 4 June 2024
- Published by Wiley in ChemSusChem
- Vol. 17 (19) , e202400472
Progress and Opportunities in Photocatalytic, Electrocatalytic, and Photoelectrocatalytic Production of Hydrogen Peroxide Coupled with Biomass Valorization
Hydrogen peroxide (H2O2) has been considered an energy carrier (fuel) and oxidizer for various chemical synthesis and environmental remediation processes. Biomass valorization can generate high‐value‐added products in a green and pollution‐free way to solve the energy and environmental crisis. The biomass valorization coupled with H2O2 generation via photo‐, electro‐, and photoelectrocatalysis plays a positive role in sustainable targets, which can maximize energy utilization and realize the production of value‐added products and fuel synthesis. Recently, catalyst design and mechanism studies in H2O2 generation coupled with biomass valorization are in the infancy stage. Herein, this review begins with a background on photo‐, electro‐, and photoelectrocatalytic techniques for H2O2 generation, biomass valorization, and the H2O2 generation couples with biomass valorization. Meanwhile, the progress and reaction mechanism are reviewed. Finally, the prospects and challenges of a synergistic coupled system of H2O2 synthesis and value‐added biomass in achieving high conversion, selectivity, and reaction efficiency are envisioned.
- 4 June 2024
- Published by Wiley in ChemSusChem
- Vol. 17 (19) , e202400472
Progress and Opportunities in Photocatalytic, Electrocatalytic, and Photoelectrocatalytic Production of Hydrogen Peroxide Coupled with Biomass Valorization
Hydrogen peroxide (H2O2) has been considered an energy carrier (fuel) and oxidizer for various chemical synthesis and environmental remediation processes. Biomass valorization can generate high‐value‐added products in a green and pollution‐free way to solve the energy and environmental crisis. The biomass valorization coupled with H2O2 generation via photo‐, electro‐, and photoelectrocatalysis plays a positive role in sustainable targets, which can maximize energy utilization and realize the production of value‐added products and fuel synthesis. Recently, catalyst design and mechanism studies in H2O2 generation coupled with biomass valorization are in the infancy stage. Herein, this review begins with a background on photo‐, electro‐, and photoelectrocatalytic techniques for H2O2 generation, biomass valorization, and the H2O2 generation couples with biomass valorization. Meanwhile, the progress and reaction mechanism are reviewed. Finally, the prospects and challenges of a synergistic coupled system of H2O2 synthesis and value‐added biomass in achieving high conversion, selectivity, and reaction efficiency are envisioned.
- 26 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-14
Robust Extraction of Multiple-Type Support Positioning Devices in the Catenary System of Railway Dataset Based on MLS Point Clouds
Due to the external environment, the support positioning device (SPD) of the railway catenary is prone to break down. Therefore, the automatic detection of SPDs is of great research significance to ensure the safe operation of the railway system. However, the small-scale SPD expresses weak features due to the complexity of railway scenes. Therefore, we propose a new algorithm for automatically extracting multiple-type SPDs quickly. Firstly, a preprocessing approach of equidistant scene segmentation is proposed based on trajectory points to divide the whole scene into several independent region units for batch processing. Then, a new point spacing-based spatial clustering of applications with noise (PSBSCAN) algorithm is proposed for the extraction of pillars in the pillar corridor of each region unit. Adopting point spacing as the core standard and the parallel iteration mode with only accessing edge points can reduce the influence of the uneven point cloud density and the large-scale point clouds. Next, to locate SPDs, the spatial relationship between the trajectory point, the pillar, and the SPD in the scene is introduced into the corresponding objects to build the spatial index with semantic information. Finally, contact wires installed on the SPD are filtered through multiple-level voxel segmentation based on octree to extract SPD accurately. Through the test of 10km railway datasets, the average F 1 by the proposed method is 98.61%, and the average recognition rate of SPD is 99.65%, which shows that this method can achieve efficient extraction of multiple-type SPDs in railway scenes with different point densities.
- 26 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-14
Robust Extraction of Multiple-Type Support Positioning Devices in the Catenary System of Railway Dataset Based on MLS Point Clouds
Due to the external environment, the support positioning device (SPD) of the railway catenary is prone to break down. Therefore, the automatic detection of SPDs is of great research significance to ensure the safe operation of the railway system. However, the small-scale SPD expresses weak features due to the complexity of railway scenes. Therefore, we propose a new algorithm for automatically extracting multiple-type SPDs quickly. Firstly, a preprocessing approach of equidistant scene segmentation is proposed based on trajectory points to divide the whole scene into several independent region units for batch processing. Then, a new point spacing-based spatial clustering of applications with noise (PSBSCAN) algorithm is proposed for the extraction of pillars in the pillar corridor of each region unit. Adopting point spacing as the core standard and the parallel iteration mode with only accessing edge points can reduce the influence of the uneven point cloud density and the large-scale point clouds. Next, to locate SPDs, the spatial relationship between the trajectory point, the pillar, and the SPD in the scene is introduced into the corresponding objects to build the spatial index with semantic information. Finally, contact wires installed on the SPD are filtered through multiple-level voxel segmentation based on octree to extract SPD accurately. Through the test of 10km railway datasets, the average F 1 by the proposed method is 98.61%, and the average recognition rate of SPD is 99.65%, which shows that this method can achieve efficient extraction of multiple-type SPDs in railway scenes with different point densities.
- Open Access
- 13 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 2134-2146
Roof Segmentation From Airborne LiDAR Using Octree-Based Hybrid Region Growing and Boundary Neighborhood Verification Voting
Building roof segmentation is a key step in the process of three-dimensional (3D) building reconstruction using airborne Light Detection and Ranging (LiDAR) point cloud data. Voxel-based region growing is one of the most widely used methods to segment planes because of its high efficiency and easy implementation, but it is easy to omit roof planes due to the unreasonable voxel size and the complex roof structures. In addition, boundaries between adjacent roof planes are inaccurate. To solve the issues, a roof segmentation method using octree-based hybrid region growing and boundary neighborhood verification voting is proposed. First, an octree-based voxelization is performed on the raw building points to generate two basic units: planar voxels and individual points (i.e., points that are not in the planar voxels). Then, the hybrid region growing is conducted on these two basic units to segment coarse roof planes. A parameter-free boundary neighborhood verification voting strategy is used to assign the boundary points to the correct roof planes by verifying the neighborhoods of the boundary points and using reliable neighborhood information. Experimental results of four datasets, including two datasets provided by the International Society for Photogrammetry and Remote Sensing (ISPRS), and two high-density datasets provided by OpenTopography, verify that roof planes can be successfully segmented by the proposed method with over 96.8% completeness and a minimum 93.2% correctness. In addition, boundary points are assigned to the correct roof planes by the neighborhood verification voting strategy. Thus, the segmented roof planes can be used in various applications.
- 13 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 2134-2146
Open AccessRoof Segmentation From Airborne LiDAR Using Octree-Based Hybrid Region Growing and Boundary Neighborhood Verification Voting
Building roof segmentation is a key step in the process of three-dimensional (3D) building reconstruction using airborne Light Detection and Ranging (LiDAR) point cloud data. Voxel-based region growing is one of the most widely used methods to segment planes because of its high efficiency and easy implementation, but it is easy to omit roof planes due to the unreasonable voxel size and the complex roof structures. In addition, boundaries between adjacent roof planes are inaccurate. To solve the issues, a roof segmentation method using octree-based hybrid region growing and boundary neighborhood verification voting is proposed. First, an octree-based voxelization is performed on the raw building points to generate two basic units: planar voxels and individual points (i.e., points that are not in the planar voxels). Then, the hybrid region growing is conducted on these two basic units to segment coarse roof planes. A parameter-free boundary neighborhood verification voting strategy is used to assign the boundary points to the correct roof planes by verifying the neighborhoods of the boundary points and using reliable neighborhood information. Experimental results of four datasets, including two datasets provided by the International Society for Photogrammetry and Remote Sensing (ISPRS), and two high-density datasets provided by OpenTopography, verify that roof planes can be successfully segmented by the proposed method with over 96.8% completeness and a minimum 93.2% correctness. In addition, boundary points are assigned to the correct roof planes by the neighborhood verification voting strategy. Thus, the segmented roof planes can be used in various applications.
- Open Access
- 1 October 2021
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 102, 102449
MHIBS-Net: Multiscale hierarchical network for indoor building structure point clouds semantic segmentation
- 1 October 2021
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 102, 102449
Open AccessMHIBS-Net: Multiscale hierarchical network for indoor building structure point clouds semantic segmentation
- Open Access
- 2 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 173999-174012
MHNet: Multiscale Hierarchical Network for 3D Point Cloud Semantic Segmentation
- 2 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 173999-174012
Open AccessMHNet: Multiscale Hierarchical Network for 3D Point Cloud Semantic Segmentation