WZWenlin Zhou

Wenlin Zhou

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wenlin Zhou has a total of 14 co-authors. Here are the top co-authors by number of shared publications:

  • Guanzhou Chen

    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China

    3 shared publications
  • Tong Wang

    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China

    3 shared publications
  • Xiaodong Zhang

    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China

    3 shared publications
  • Haobo Yang

    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan, China

    2 shared publications
  • Puyun Liao

    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China

    2 shared publications
  • Xianwei Li

    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan, China

    2 shared publications

Latest Publications

  • INVITATION: A Framework for Enhancing UAV Image Semantic Segmentation Accuracy Through Depth Information Fusion

    by Xiaodong Zhang, Wenlin Zhou, Guanzhou Chen, Jiaqi Wang, Qingyuan Yang, Xiaoliang Tan, Tong Wang, Yifei Chen

    With the increasing use of Unmanned Aerial Vehicles (UAVs), improving the accuracy of semantic segmentation is becoming critical. Depth information preserves geometric structure, serving as an invaluable supplement to color-rich UAV imagery. Inspired by this, we proposed a novel framework named INVITATION, which exclusively takes original UAV imagery as input, yet is capable of obtaining complemented depth information and fusing into RGB semantic segmentation models effectively, thereby enhancing UAV semantic segmentation accuracy. Concretely, this framework supports two distinct depth generation approaches: high-precision Multi-View Stereo (MVS) depth reconstruction using multiple views or video sequences via Structure from Motion (SfM), and monocular depth estimation using individual images. Our empirical evaluations conducted on the UAVid dataset showed that mIoU metric of INVITATION utilized precise reconstructed depth maps via MVS improved from 66.02% to 70.57%, while utilized depth predictions from pre-trained models reached 69.69%, which supports the effectiveness of extracting and fusing depth information from original imagery in enhancing UAV semantic segmentation. This study explores a novel approach to acquire UAV multi-modal information at low data cost, highlights the advantages of incorporating depth information into UAV semantic analysis, and paves the way for further studies on the integration of multi-modal UAV information. Our code is available at https://github.com/CVEO/INVITATION.


  • S2Net: A Multitask Learning Network for Semantic Stereo of Satellite Image Pairs

    by Puyun Liao, Xiaodong Zhang, Guanzhou Chen, Tong Wang, Xianwei Li, Haobo Yang, Wenlin Zhou, Chanjuan He, Qing Wang

    Stereo matching and semantic segmentation are two significant tasks in remote sensing. Recently, deep learning approaches have been applied to these tasks separately. However, the lack of semantic supervision makes the training of stereo matching model susceptible to data disturbance, resulting in inferior generalization ability; foreground objects are sometimes confused with background pixels in RGB images, limiting the classification accuracy. By exploring the relationship between these two tasks, semantic stereo solves these problems simultaneously with multitask learning. Previous methods took semantic stereo as two parallel processing tasks, so they did not take full advantages of the additional information from both tasks and only obtained slight improvement. In this work, we designed a multitask learning framework semantic stereo network (S2Net). The proposed network generates cost volumes with feature maps supervised by semantic information to estimate disparity maps and fuses RGB-D feature maps to predict classification maps, therefore gathering multitask learning information. To enhance the performance of trained model, we also considered the continuity of disparity values and the duality of stereo image pairs in data augmentation. When applied in datasets without training, S2Net obtained 2.937% D1-Error in the WHU dataset, lower than 4.297% of the previous best method, depicting the generalization ability improvement from semantic supervision. In terms of semantic segmentation, the introduction of disparity maps increases the mean intersection over union (mIoU) from 61.375% to 69.096% in the US3D datasets. The experiments on the KITTI semantics benchmark show that our proposed method obtains 60.76% mIoU, achieving state-of-the-art among multitask learning methods.


  • A Deep Transfer Learning Framework Using Teacher–Student Structure for Land Cover Classification of Remote-Sensing Imagery

    by Xiaodong Zhang, Xianwei Li, Guanzhou Chen, Puyun Liao, Tong Wang, Haobo Yang, Chanjuan He, Wenlin Zhou, Yufeng Sun

    Deep learning techniques are widely used for land cover classification in remote sensing, primarily because they can effectively extract complex features from imagery data, which is essential for accurate land cover classification. However, the heterogeneity of data can pose a challenge to the generalizability of deep models. To address this issue, we propose a novel transfer learning framework for land cover classification using teacher-student structure. The proposed framework utilizes the knowledge acquired by the teacher model from large datasets to facilitate fine-tuning of the student model on small datasets, which prevents problems such as overfitting resulting from training large models on small datasets and inferior performance arising from the limited learning capacity of small models. To achieve this goal, we design a loss function base on central moment discrepancy and high-temperature softmax. In addition, we conducted experiments on three distinct pairs of datasets and found that our proposed framework outperforms both training the student model from scratch on the target domain and simply fine-tuning the teacher and student models from the source domain to the target domain. Specifically, we observed an average increase in mIoU of 9.9%, 2.1%, and 4.3%. These results demonstrate the effectiveness and generalizability of our proposed framework for remote sensing land cover classification.