WCWen Chen

Wen Chen

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wen Chen has a total of 3 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    3D Point Cloud Fusion Method Based on EMD Auto-Evolution and Local Parametric Network

    by Wen Chen, Hao Chen, Shuting Yang

    Although the development of high-resolution remote sensing satellite technology has made it possible to reconstruct the 3D structure of object-level features using satellite imagery, the results from a single reconstruction are often insufficient to comprehensively describe the 3D structure of the target. Therefore, developing an effective 3D point cloud fusion method can fully utilize information from multiple observations to improve the accuracy of 3D reconstruction. To this end, this paper addresses the problems of shape distortion and sparse point cloud density in existing 3D point cloud fusion methods by proposing a 3D point cloud fusion method based on Earth mover’s distance (EMD) auto-evolution and local parameterization network. Our method is divided into two stages. In the first stage, EMD is introduced as a key metric for evaluating the fusion results, and a point cloud fusion method based on EMD auto-evolution is constructed. The method uses an alternating iterative technique to sequentially update the variables and produce an initial fusion result. The second stage focuses on point cloud optimization by constructing a local parameterization network for the point cloud, mapping the upsampled point cloud in the 2D parameter domain back to the 3D space to complete the optimization. Through these two steps, the method achieves the fusion of two sets of non-uniform point cloud data obtained from satellite stereo images into a single, denser 3D point cloud that more closely resembles the true target shape. Experimental results demonstrate that our fusion method outperforms other classical comparison algorithms for targets such as buildings, planes, and ships, and achieves a fused RMSE of approximately 2 m and an EMD accuracy better than 0.5.


  • Open Access

    Generalized Stereo Matching Method Based on Iterative Optimization of Hierarchical Graph Structure Consistency Cost for Urban 3D Reconstruction

    by Shuting Yang, Hao Chen, Wen Chen

    Generalized stereo matching faces the radiation difference and small ground feature difference brought by different satellites and different time phases, while the texture-less and disparity discontinuity phenomenon seriously affects the correspondence between matching points. To address the above problems, a novel generalized stereo matching method based on the iterative optimization of hierarchical graph structure consistency cost is proposed for urban 3D scene reconstruction. First, the self-similarity of images is used to construct k-nearest neighbor graphs. The left-view and right-view graph structures are mapped to the same neighborhood, and the graph structure consistency (GSC) cost is proposed to evaluate the similarity of the graph structures. Then, cross-scale cost aggregation is used to adaptively weight and combine multi-scale GSC costs. Next, object-based iterative optimization is proposed to optimize outliers in pixel-wise matching and mismatches in disparity discontinuity regions. The visibility term and the disparity discontinuity term are iterated to continuously detect occlusions and optimize the boundary disparity. Finally, fractal net evolution is used to optimize the disparity map. This paper verifies the effectiveness of the proposed method on a public US3D dataset and a self-made dataset, and compares it with state-of-the-art stereo matching methods.


  • Open Access

    Self-Supervised Stereo Matching Method Based on SRWP and PCAM for Urban Satellite Images

    by Wen Chen, Hao Chen, Shuting Yang

    In this paper, we propose a self-supervised stereo matching method based on superpixel random walk pre-matching (SRWP) and parallax-channel attention mechanism (PCAM). Our method is divided into two stages, training and testing. First, in the training stage, we obtain pre-matching results of stereo images based on superpixel random walk, and some matching points with high confidence are selected as labeled samples. Then, a stereo matching network is constructed to describe the matching correlation by calculating the attention scores of any two points between different images through the parallax-channel attention mechanism, superimposing the scores of each layer to calculate the disparity. The network is trained using the labeled samples and some unsupervised constraint criteria. Finally, in the testing stage, the trained network is used to obtain stereo matching relations of stereo images. The proposed method does not need manually labeled training samples and is more suitable for 3D reconstruction under mass satellite remote sensing data. Comparative experiments on multiple datasets show that our method has a stereo matching EPE of 2.44 and a 3D reconstruction RMSE of 2.36 m. Especially in the weak texture and parallax abrupt change regions, we can achieve more advanced performance than other methods.


  • Open Access

    MCMS-STM: An Extension of Support Tensor Machine for Multiclass Multiscale Object Recognition in Remote Sensing Images

    by Tong Gao, Hao Chen, Wen Chen

    The support tensor machine (STM) extended from support vector machine (SVM) can maintain the inherent information of remote sensing image (RSI) represented as tensor and obtain effective recognition results using a few training samples. However, the conventional STM is binary and fails to handle multiclass classification directly. In addition, the existing STMs cannot process objects with different sizes represented as multiscale tensors and have to resize object slices to a fixed size, causing excessive background interferences or loss of object’s scale information. Therefore, the multiclass multiscale support tensor machine (MCMS-STM) is proposed to recognize effectively multiclass objects with different sizes in RSIs. To achieve multiclass classification, by embedding one-versus-rest and one-versus-one mechanisms, multiple hyperplanes described by rank-R tensors are built simultaneously instead of single hyperplane described by rank-1 tensor in STM to separate input with different classes. To handle multiscale objects, multiple slices of different sizes are extracted to cover the object with an unknown class and expressed as multiscale tensors. Then, M-dimensional hyperplanes are established to project the input of multiscale tensors into class space. To ensure an efficient training of MCMS-STM, a decomposition algorithm is presented to break the complex dual problem of MCMS-STM into a series of analytic sub-optimizations. Using publicly available RSIs, the experimental results demonstrate that the MCMS-STM achieves 89.5% and 91.4% accuracy for classifying airplanes and ships with different classes and sizes, which outperforms typical SVM and STM methods.