XCXin Chen

Xin 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


Xin Chen has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Road Extraction Network for Remote Sensing Images Based on Multiscale Feature Fusion and Edge-Guided Attention

    by Ke Zhang, Wenyue Guo, Anzhu Yu, Xin Chen, Junming Chen, Zheng Zhang

    With the rapid advancement of geospatial technology, automatic road extraction has become an increasingly important and impactful task. However, the results of existing methods often suffer from incomplete road connectivity and poor topology due to complex background interference, diverse road morphology and occlusion. In this study, we propose a novel convolutional neural network that integrates classical edge detection techniques with attention mechanisms. These techniques effectively preserve high-frequency information, particularly edges and boundaries. Additionally, we introduce a new weighted bi-directional feature pyramid network (BiFPN) designed to capture multi-scale semantic information across different layers, thereby bridging the semantic gaps between low-level features and high-level feature maps. We conduct experiments on two distinct road datasets: the DeepGlobe dataset and the Massachusetts dataset. The results demonstrate that our model enhances overall performance compared to several state-of-the-art (SOTA) algorithms, with Intersection over Union (IoU) metrics improving by 2.32% and 1.37% over Unet34 on the two datasets, respectively.


  • Open Access

    PolyReg: Autoregressive Building Outline Regularization via Masked Attention Sequence Generation

    by Longfei Cui, Chao Li, Xin Chen, Xiao Wang, Haizhong Qian

    High-resolution remote sensing imagery has become the primary data source for obtaining building information. Automatically extracting regularized building outline polygon vectors is crucial for improving vector mapping efficiency and geographic information system applications, but existing deep learning methods struggle to simultaneously achieve accurate detection, high pixel-level coverage, and geometric regularity. This paper proposes a novel two-stage building outline extraction method. In the first stage, the SegFormer model is used to extract image features, effectively capturing global context information. In the second stage, a polygon outline regularization model (PolyReg) based on a Masked Attention Encoder is innovatively introduced. The PolyReg model draws on the sequence generation idea from natural language processing, transforming the outline regularization task into a sequence generation problem. Through a cleverly designed self-attention mask matrix, it achieves an autoregressive output of regularized building outline coordinates, eliminating the need for cumbersome post-processing steps. Experimental results show that on the Inria Aerial Image Labeling Dataset, compared with traditional methods and existing deep learning methods, the proposed method demonstrates significant advantages in metrics such as IoU, C-IoU, and Hausdorff distance. It effectively improves the regularity and geometric accuracy of building outlines while maintaining high pixel-level coverage.

  • Automatic Building Aggregation Supported by Knowledge Graph

    by Youneng Su, Qing Xu, Xinming Zhu, Fubing Zhang, Xin Chen, Yi Liu

    Large‐scale building aggregation presents a significant challenge in cartographic generalization. Current methods have limitations in detecting building proximity relations efficiently and considering spatial structural characteristics. These limitations result in suboptimal aggregation efficiency and the lack of spatial structural characteristics in the final results. To address these shortcomings, we proposed a knowledge graph‐supported building aggregation method. First, we delineated the building spatial structural relations and identified building proximity edges. Second, we constructed a knowledge graph that expressed building proximity relations, spatial structure relations, and other relevant information. Third, considering the cartographic requirements, we designed reasoning rules to efficiently infer the relation between proximity edges and spatial structure. Finally, based on the reasoning results, we employed the proximity edges interaction projection method and the proximity edges angle bisector method to construct the aggregation polygons. To validate the effectiveness of our method, we conducted experiments using Shanghai building data. The results demonstrated the superiority of our approach in terms of both efficiency and quality. Specifically, our method exhibited higher efficiency compared to traditional proximity graph‐based approaches and demonstrated adaptability to large‐scale data. Moreover, it effectively achieved accurate aggregation of buildings under different structural relations and aggregation thresholds.


  • Updating Road Maps at City Scale With Remote Sensed Images and Existing Vector Maps

    by Xin Chen, Anzhu Yu, Qun Sun, Wenyue Guo, Qing Xu, Bowei Wen

    Currently, many countries have built geo-information databases and gathered large amounts of geographic data. However, with the extensive construction of infrastructure and rapid expansion of cities, road updating process is imperative to maintain the high quality of current basic geographic information. Currently, road extraction and change detection are two commonly used methods to solve road updating problems. Most of the existing methods rely on a large number of accurate road labels to generate road information, while ignoring the use of quantities of available but incomplete road maps. In our work, we proposed a semi-supervised road extraction method specifically for road-updating applications (SRUNet). In this approach, historical road maps are fused with the latest remote sensing images, and state of the roads are updated directly. A multi-branch network is the core of the method, which consists of three noteworthy parts: Map Encoding Branch (MEB) proposed for representation learning, Boundary Enhancement Module (BEM) for improving the accuracy of boundary prediction, and Residual Refinement Module (RRM) for further optimizing the prediction results. We applied our method to two datasets: the DeepGlobe public dataset and our self-constructed dataset from Zhengzhou and Nanjing. Experimental results shows that our method achievs an improvement of 14.37% over the baseline approach. Notably, the addition of historical maps improved the model’s performance by 12.4%. Promising results were obtained on two cities’ large-scale road networks. With the reliable prediction results and improved performance, we believe SRUNet is meaningful for a wide range of road renewal applications.


  • Open Access

    Multi-Task Learning for Building Extraction and Change Detection from Remote Sensing Images

    by Danyang Hong, Chunping Qiu, Anzhu Yu, Yujun Quan, Bing Liu, Xin Chen

    Building extraction (BE) and change detection (CD) from remote sensing (RS) imagery are significant yet highly challenging tasks with substantial application potential in urban management. Learning representative multi-scale features from RS images is a crucial step toward practical BE and CD solutions, as in other DL-based applications. To better exploit the available labeled training data for representation learning, we propose a multi-task learning (MTL) network for simultaneous BE and CD, comprising the state-of-the-art (SOTA) powerful Swin transformer as a shared backbone network and multiple heads for predicting building labels and changes. Using the popular CD dataset the Wuhan University building change detection dataset (WHU-CD), we benchmarked detailed designs of the MTL network, including backbone and pre-training choices. With a selected optimal setting, the intersection over union (IoU) score was improved from 70 to 81 for the WHU-CD. The experimental results of different settings demonstrated the effectiveness of the proposed MTL method. In particular, we achieved top scores in BE and CD from optical images in the 2021 Gaofen Challenge. Our method also shows transferable performance on an unseen CD dataset, indicating high label efficiency.


  • Open Access

    Transferring Transformer-Based Models for Cross-Area Building Extraction From Remote Sensing Images

    by Chunping Qiu, He Li, Wenyue Guo, Xin Chen, Anzhu Yu, Xiaochong Tong, Michael Schmitt

    Extracting buildings from remote sensing (RS) images is an important task with a variety of applications. Considerable attention has focused on achieving new state-of-the-art (SOTA) accuracy with more and more advanced deep learning (DL) models. However, the developed models still hardly generalize across geographical areas, hindering the practical use of SOTA approaches. To attack this problem, we established a baseline for model cross-area generalization ability using available datasets for building extraction (BE). In addition to two popular fully convolutional neural network (FCN) based models, we first adapted two novel transformer-based models, shifted windows (Swin) transformer and SegFormer, which are all able to output SOTA accuracy with no big difference when tested within one area. However, experimental results show that all models fail to generalize to a different area. We then propose to fine-tune pretrained models from one area on a small subset of an unseen area, the effectiveness of which depends on the model choice and the data size for tuning. By jointly taking advantage of the transfer learning idea and the multiscale feature learning ability of SegFormer, a distinct improvement has been achieved compared to results from Swin transformer and FCN-based models trained on the same amount of data. Commonly used metric, Intersection over Union, can be increased from 38.97% to 70.86%, and from 48.36% to 74.51%, when using 10% and 30% subset of the targeting area, respectively. The influence of model choice and data size for tuning has also been investigated. Our work contributes to complementing the algorithm development and within-area model evaluation in the hot field of BE from RS images.


  • Multiscale Feature Learning by Transformer for Building Extraction From Satellite Images

    by Xin Chen, Chunping Qiu, Wenyue Guo, Anzhu Yu, Xiaochong Tong, Michael Schmitt

    Extracting buildings from very high-resolution satellite images is a challenging yet important task for applications such as urban monitoring. Multiscale feature learning proves to be a potential solution toward accurate extraction of buildings. This study exploits a powerful multiscale feature learning module, a hierarchical vision transformer by shifted windows (swin), as a backbone within a building extraction network. To this end, we first designed a general structure for building extraction, consisting of a backbone to extract multiscale features and a head network to fuse and refine features. Then, we integrated swin into the structure as a backbone and utilized channel-wise and spatial-wise enhancement in a head network. Experimental results show that our method achieves improvements regarding both F1-score and intersection over union (IoU) compared to the multiple attending path neural network (MAP-Net), which is the current state-of-the-art (SOTA) algorithm for building extraction from remote sensing images. Our study thus confirms the potential of swin transformers as backbones for semantic segmentation tasks based on satellite images.


  • Open Access

    Predicting User Activity Intensity Using Geographic Interactions Based on Social Media Check-In Data

    by Jing Li, Wenyue Guo, Haiyan Liu, Xin Chen, Anzhu Yu, Jia Li

    Predicting user activity intensity is crucial for various applications. However, existing studies have two main problems. First, as user activity intensity is nonstationary and nonlinear, traditional methods can hardly fit the nonlinear spatio-temporal relationships that characterize user mobility. Second, user movements between different areas are valuable, but have not been utilized for the construction of spatial relationships. Therefore, we propose a deep learning model, the geographical interactions-weighted graph convolutional network-gated recurrent unit (GGCN-GRU), which is good at fitting nonlinear spatio-temporal relationships and incorporates users’ geographic interactions to construct spatial relationships in the form of graphs as the input. The model consists of a graph convolutional network (GCN) and a gated recurrent unit (GRU). The GCN, which is efficient at processing graphs, extracts spatial features. These features are then input into the GRU, which extracts their temporal features. Finally, the GRU output is passed through a fully connected layer to obtain the predictions. We validated this model using a social media check-in dataset and found that the geographical interactions graph construction method performs better than the baselines. This indicates that our model is appropriate for fitting the complex nonlinear spatio-temporal relationships that characterize user mobility and helps improve prediction accuracy when considering geographic flows.


  • Open Access

    Attention Aware Cost Volume Pyramid Based Multi-view Stereo Network for 3D Reconstruction

    by Anzhu Yu, Wenyue Guo, Bing Liu, Xin Chen, Xin Wang, Xuefeng Cao, Bingchuan Jiang, A Yu

    We present an efficient multi-view stereo (MVS) network for 3D reconstruction from multiview images. While previous learning based reconstruction approaches performed quite well, most of them estimate depth maps at a fixed resolution using plane sweep volumes with a fixed depth hypothesis at each plane, which requires densely sampled planes for desired accuracy and therefore is difficult to achieve high resolution depth maps. In this paper we introduce a coarseto-fine depth inference strategy to achieve high resolution depth. This strategy estimates the depth map at coarsest level, while the depth maps at finer levels are considered as the upsampled depth map from previous level with pixel-wise depth residual. Thus, we narrow the depth searching range with priori information from previous level and construct new cost volumes from the pixel-wise depth residual to perform depth map refinement. Then the final depth map could be achieved iteratively since all the parameters are shared between different levels. At each level, the self-attention layer is introduced to the feature extraction block for capturing the long range dependencies for depth inference task, and the cost volume is generated using similarity measurement instead of the variance based methods used in previous work. Experiments were conducted on both the DTU benchmark dataset and recently released BlendedMVS dataset. The results demonstrated that our model could outperform most state-of-the-arts (SOTA) methods. The codebase of this project is at https://github.com/ArthasMil/AACVP-MVSNet.