WHWei Huang

Wei Huang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


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

  • Hong Tang

    State Key Laboratory of Remote Sensing and Digital Earth, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

    2 shared publications
  • Jiayi Ge

    State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

    1 shared publication
  • Xuejun Zhai

    Beijing Key Laboratory of Environmental Remote Sensing and Digital Cities, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

    1 shared publication

Latest Publications

  • Open Access

    Sequentially Delineation of Rooftops with Holes from VHR Aerial Images Using a Convolutional Recurrent Neural Network

    by Wei Huang, Zeping Liu, Hong Tang, Jiayi Ge

    Semantic and instance segmentation methods are commonly used to build extraction from high-resolution images. The semantic segmentation method involves assigning a class label to each pixel in the image, thus ignoring the geometry of the building rooftop, which results in irregular shapes of the rooftop edges. As for instance segmentation, there is a strong assumption within this method that there exists only one outline polygon along the rooftop boundary. In this paper, we present a novel method to sequentially delineate exterior and interior contours of rooftops with holes from VHR aerial images, where most of the buildings have holes, by integrating semantic segmentation and polygon delineation. Specifically, semantic segmentation from the Mask R-CNN is used as a prior for hole detection. Then, the holes are used as objects for generating the internal contours of the rooftop. The external and internal contours of the rooftop are inferred separately using a convolutional recurrent neural network. Experimental results showed that the proposed method can effectively delineate the rooftops with both one and multiple polygons and outperform state-of-the-art methods in terms of the visual results and six statistical indicators, including IoU, OA, F1, BoundF, RE and Hd.


  • Open Access

    Edge Dependent Chinese Restaurant Process for Very High Resolution (VHR) Satellite Image Over-Segmentation

    by Hong Tang, Xuejun Zhai, Wei Huang

    Image over-segmentation aims to partition an image into spatially adjacent and spectrally homogeneous regions. It could reduce the complexity of image representation and enhance the efficiency of subsequent image processing. Previously, many methods for image over-segmentation have been proposed, but almost of them need to assign model parameters in advance, e.g., the number of segments. In this paper, a nonparametric clustering model is employed to the over-segmentation of Very High Resolution (VHR) satellite images, in which the number of segments can automatically be inferred from the observed data. The proposed model is called the Edge Dependent Chinese restaurant process (EDCRP), which extends the distance dependent Chinese restaurant process to make full use of local image structure information, i.e., edges. Experimental results show that the presented methods outperform state of the art methods for image over-segmentation in terms of both metrics based direct evaluation and classification based indirect evaluation.