A Boundary Regulated Network for Accurate Roof Segmentation and Outline Extraction

Abstract

The automatic extraction of building outlines from aerial imagery for the purposes of navigation and urban planning is a long-standing problem in the field of remote sensing. Currently, most methods utilize variants of fully convolutional networks (FCNs), which have significantly improved model performance for this task. However, pursuing more accurate segmentation results is still critical for additional applications, such as automatic mapping and building change detection. In this study, we propose a boundary regulated network called BR-Net, which utilizes both local and global information, to perform roof segmentation and outline extraction. The BR-Net method consists of a shared backend utilizing a modified U-Net and a multitask framework to generate predictions for segmentation maps and building outlines based on a consistent feature representation from the shared backend. Because of the restriction and regulation of additional boundary information, the proposed model can achieve superior performance compared to existing methods. Experiments on an aerial image dataset covering 32 km2 and containing more than 58,000 buildings indicate that our method performs well at both roof segmentation and outline extraction. The proposed BR-Net method significantly outperforms the classic FCN8s model. Compared to the state-of-the-art U-Net model, our BR-Net achieves 6.2% (0.869 vs. 0.818), 10.6% (0.772 vs. 0.698), and 8.7% (0.840 vs. 0.773) improvements in F1 score, Jaccard index, and kappa coefficient, respectively.

GEOSEG: A Computer Vision Package for Automatic Building Segmentation and Outline Extraction

“…Facing this problem, we introduce Geoseg (https://github.com/ huster-wgm/geoseg), a computer vision package that is focus on implementing the state-of-the-art methods for automatic and accurate building segmentation and outline extraction. The Geoseg package implements more than 9 FCN-based models including FCNs [9], U-Net [10], SegNet [11], FPN [12], ResUNet [13], MC-FCN [14], and BR-Net [15]. For in-depth comparison, balanced and unbalanced evaluation metrics, such as precision, recall, overall accuracy, f1score, Jaccard index or intersection over union (IoU) [16] and kappa coefficient [17], are implemented.…”

Building Extraction from Very High Resolution Aerial Imagery Using Joint Attention Deep Neural Network

“…Though FCN-based methods can produce dense pixel-wise output directly, the pixel-wise classification derived from the final score map is quite coarse because of the sequential sub-sampling operations in the FCN.To address the problem of coarse predictions, recent research [21][22][23][24][25][26] have further improved FCN-based methods for semantic labeling of remote sensing images. There is a growing body of literature that many studies [27][28][29][30][31] employ the encoder-decoder architecture with skip connection. UNet [32], a typical model in the style of encoder-decoder, reuses low-level information to refine the output, and results in better performance.…”

Building Extraction from UAV Images Jointly Using 6D-SLIC and Multiscale Siamese Convolutional Networks

“…The experimental results based on the qualitative and quantitative measures confirm the effectiveness and high accuracy of the proposed framework relative to the digitized results. The proposed framework performs better than state-of-the-art building extraction methods, given its higher values of recall, precision, and intersection over Union (IoU).2 of 33 remote sensing, and is extensively used in various applications, including urban planning, cartographic mapping, and land use analysis [1,2]. The significant progress in sensors and operating platforms has enabled us to acquire remote sensing images and 3D point clouds from cameras or Light Detection And Ranging (LiDAR) equipped in various platforms (e.g., satellite, aerial, and Unmanned Aerial Vehicle (UAV) platforms); thus, the methods based on images and point clouds are commonly used to extract buildings [3][4][5].Building extraction can be broadly divided into three categories according to data source: 2D image-based methods, 3D point cloud-based methods, and 2D and 3D information hybrid methods.…”

“…2D image-based building extraction consists of two stages, namely, building segmentation and regularization. Many approaches have been proposed in recent years to extract buildings through very-high-resolution 2D imagery, including the active contour model-based method [6], multidirectional and multiscale morphological index-based method [7], combined binary filtering and region growing method [8], object-based method [9], dense attention network-based method [10], and boundary-regulated network-based method [2]. Although these methods have achieved important advancements, a single cue from 2D images remains insufficient to extract buildings under the complex backgrounds of images (e.g., illumination, shadow, occlusion, geometric deformation, and quality degradation), which cause inevitable obstacles in the identification and delineation of building outlines under different circumstances.…”

“…2 of 33 remote sensing, and is extensively used in various applications, including urban planning, cartographic mapping, and land use analysis [1,2]. The significant progress in sensors and operating platforms has enabled us to acquire remote sensing images and 3D point clouds from cameras or Light Detection And Ranging (LiDAR) equipped in various platforms (e.g., satellite, aerial, and Unmanned Aerial Vehicle (UAV) platforms); thus, the methods based on images and point clouds are commonly used to extract buildings [3][4][5].…”