WZWenpeng Zong

Wenpeng Zong

*This is an algorithmically generated author record based on publicly available information.

Wenpeng Zong has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Image-salient line extraction from terrestrial laser point clouds via multi-view geometric mapping

    by Wenpeng Zong, Minglei Li, Xueyong Xiang, Haolong Luo

    As canonical geometric primitives in man-made environments, line features play a pivotal role in terrestrial laser scanner (TLS) point cloud processing and applications. Existing state-of-the-art line extraction methods mainly focus on geometric crease line detection, which fail to capture decorative linear structures without surface geometric discontinuities. To address this gap, this paper proposes a robust high-precision extraction pipeline for image-salient line segments based on unified geometric mapping between 3D TLS point clouds and synchronous digital imagery. First, a decoupled calibration workflow is constructed to realize high-precision alignment between the scanner and external cameras: camera intrinsic parameters are solved via the V-STARS system, and multi-view extrinsic parameters are sequentially estimated using the direct linear transformation (DLT) algorithm. With accurate sensor alignment completed, we derive a closed-form unified mapping model for multi-view images and co-located TLS point clouds. Next, 2D line support regions are detected from optical images, and corresponding 3D supporting point sets are screened through the established mapping relation, followed by robust 3D line fitting to reconstruct image-salient line primitives. Moreover, a 3D point-based normalized cut strategy is introduced to eliminate false line primitives generated in foreground-background overlapping areas. Indoor laboratory and outdoor datasets are adopted for comprehensive verification. Experimental results demonstrate that our method can stably extract image-salient line segments undetectable by pure geometric methods, achieving centimeter-level accuracy (mean deviation below 1 cm) relative to geometric reference lines in both indoor and outdoor scenes.

  • Automatic Registration of Urban Scene Point Clouds Based on Semantic Structure Matching

    by Wenpeng Zong, Minglei Li, Xueyong Xiang, Rengui Ruan, Yue Mao

    Point cloud based 3D reconstruction is a critical technique for urban digitalization. Traditional marker-based methods involve deploying targets, which are time-consuming, inefficient, and sometimes fail to ensure accurate registration. Given the abundance of linear features in urban environments, leveraging line features for automatic registration of urban point clouds offers a promising solution. However, individual linear features lack sufficient information to support robust correspondence establishment. Therefore, we propose a Semantic Structure Based Registration (SSBR) method that utilizes line segment tuples as semantic structures. The method first extracts line features from point clouds using edge line detection algorithms, yielding a set of line segments along with their endpoints and support regions. It then identifies semantic structures from building facades and extracts their semantic attributes. Next, semantic structures are matched pairwise based on similarity measurements, and corresponding transformations are computed. The result with the highest number of common line segments is selected as the initial registration outcome. Finally, registration refinement is achieved through alignment of common line segments. Experimental results on three urban point cloud datasets demonstrate that the proposed SSBR method enables efficient and automatic registration of large-scale urban point clouds with centimeter-level accuracy. Compared with baseline approaches, the SSBR method shows superior overall performance across different datasets.

  • Open Access

    Adaptive Covariance Matrix for UAV-Based Visual–Inertial Navigation Systems Using Gaussian Formulas

    by Yangzi Cong, Wenbin Su, Nan Jiang, Wenpeng Zong, Long Li, Yan Xu, Tianhe Xu, Paipai Wu

    In a variety of UAV applications, visual–inertial navigation systems (VINSs) play a crucial role in providing accurate positioning and navigation solutions. However, traditional VINS struggle to adapt flexibly to varying environmental conditions due to fixed covariance matrix settings. This limitation becomes especially acute during high-speed drone operations, where motion blur and fluctuating image clarity can significantly compromise navigation accuracy and system robustness. To address these issues, we propose an innovative adaptive covariance matrix estimation method for UAV-based VINS using Gaussian formulas. Our approach enhances the accuracy and robustness of the navigation system by dynamically adjusting the covariance matrix according to the quality of the images. Leveraging the advanced Laplacian operator, detailed assessments of image blur are performed, thereby achieving precise perception of image quality. Based on these assessments, a novel mechanism is introduced for dynamically adjusting the visual covariance matrix using a Gaussian model according to the clarity of images in the current environment. Extensive simulation experiments across the EuRoC and TUM VI datasets, as well as the field tests, have validated our method, demonstrating significant improvements in navigation accuracy of drones in scenarios with motion blur. Our algorithm has shown significantly higher accuracy compared to the famous VINS-Mono framework, outperforming it by 18.18% on average, as well as the optimization rate of RMS, which reaches 65.66% for the F1 dataset and 41.74% for F2 in the field tests outdoors.


  • Open Access

    High-Precision Multi-Source Fusion Navigation Solutions for Complex and Dynamic Urban Environments

    by Long Li, Wenfeng Nie, Wenpeng Zong, Tianhe Xu, Mowen Li, Nan Jiang, Wei Zhang

    With the rapid advancement of artificial intelligence, particularly in fields such as autonomous driving, drone delivery, and logistics automation, the demand for high-precision and robust navigation services has become critical. In complex and dynamic urban environments, the navigation capabilities of single-sensor systems struggle to meet the practical requirements of autonomous driving technology. To address this issue, we propose a multi-source fusion navigation algorithm tailored for dynamic urban canyon scenarios, aiming to achieve reliable and continuous state estimation in complex environments. In our proposed method, we utilize independent threads on a graphics processing unit (GPU) to perform real-time detection and removal of dynamic objects in visual images, thereby enhancing the visual accuracy of multi-source fusion navigation in dynamic scenes. To tackle the challenges of significant Global Navigation Satellite System (GNSS) positioning errors and limited satellite availability in urban canyon environments, we introduce a specialized GNSS Real-Time Kinematic (RTK) stochastic model for such settings. The navigation performance of the proposed algorithm was evaluated using public datasets. The results demonstrate that our RTK/INS/Vision integrated navigation algorithm effectively improves both accuracy and availability in dynamic urban canyon environments.


  • Toward Efficient and Complete Line Segment Extraction for Large-Scale Point Clouds via Plane Segmentation and Projection

    by Wenpeng Zong, Minglei Li, Guangyun Li, Li Wang, Long Wang, Fen Zhang

    An efficient method based on plane segmentation and projection is proposed to extract as complete boundary (straight) line segments as possible. To efficiently detect boundary points, 3D planar point clouds (patches) generated by plane segmentation are converted into 2D images by graphical projection to avoid point-based nearest neighbors searching. To preserve boundary details, the projection resolution for each plane is determined through accurate statistics of average local intervals between points in voxels composing corresponding planar point clouds. To alleviate erroneous line segmentation extraction caused by uneven densities of planar point clouds, improved mathematical morphological operation, whose structural element order is self-adaptive to local point density, is proposed for crack inpainting of projected images. As for extraction of 3D boundary line segments, the back-projection results of 2D boundary line segments detected from images are utilized as references for clustering of boundary points, and a 3D straight line fitting algorithm based on recursive weighted least squares is employed to reduce the effect of boundary noise. A series of refinement strategies are further presented to control the quality of extracted 3D line segments. Experimental results demonstrate that the proposed line segment extraction method can provide efficient and fine processing results as well as automatic processing ability, which satisfies the efficient processing demand for large-scale point clouds.


  • A Fast and Accurate Planar-Feature-Based Global Scan Registration Method

    by Wenpeng Zong, Minglei Li, Yanglin Zhou, Li Wang, Fengzhuo Xiang, Guangyun Lia

    Scan registration is the basis of LiDAR-based mapping and localization. When a good initial guess is available, classical local registration algorithms such as iterative closet point (ICP) and normal distributions transform (NDT) can be utilized. However, scan registration without odometer or inertial measurement unit (IMU) is still an open problem. After reviewing the existing methods, we summarize a modular planar-feature-based registration framework. Based on the idea of modular design, we present a novel global scan registration method based on planar features. A modified renormalization-based algorithm considering the sensor noise model is derived and used for accurate plane fitting and covariance computing. An efficient adaptive plane segmentation algorithm is employed to extract planar patches which is based on voxel growing. A novel projected-image-based method is utilized for fast plane attribute calculation. The attributes of individual planes and relation constrains between the planes are employed to robustly build plane correspondences. The plane-plane singular value decomposition (SVD) method is used to estimate the transform, and normalization of the point coordinates is adopted to further improve accuracy. A consensus metric is introduced to determine plane correspondences and transform solution updating, and to select the optimal solution using the distance from the centroid of one plane to its conjugate plane. Extensive comparative experiments were performed on four datasets covering different structured scenarios to evaluate the performance of the proposed registration method. The experimental results demonstrate that the proposed method achieves a better balance between accuracy and efficiency, and has more stable and robust performance across different scenarios compared to all tested state-of-the-art algorithms.