SERNet: Spatially Enhanced Recalibration Network for Building Extraction in Dense Remote Sensing Scenes
The rapid development of urban and rural construction has accelerated the demand for segmentation in dense building scenes. However, the issue of inaccurate building localization in such scenes still lacks effective solutions. One of the causes of this problem is the loss of high-frequency informati...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11002701/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The rapid development of urban and rural construction has accelerated the demand for segmentation in dense building scenes. However, the issue of inaccurate building localization in such scenes still lacks effective solutions. One of the causes of this problem is the loss of high-frequency information and spatial misalignment caused by repeated sampling. To address this, this article proposes the spatial enhancement and recalibration network (SERNet). SERNet divides the feature extraction process into three stages: spatial retention, enhancement, and recalibration. In the first stage, the designed parallel path feature extraction architecture is used to acquire deep semantic features by the spatial path to retain spatial information and contextual path to acquire deep semantic features. In the second stage, a spatial reinforcement module based on perceptual kernel is proposed. This module predicts the grouping kernel using spatial path features, obtains the local perceptual kernel by intrakernel similarity computation, and uses the kernel weights to strengthen the local detail information after grouping. In the third phase, the group bootstrap space calibration module was designed. Set the grouping according to the difference in scale variation. Provide guidance information for bias prediction by calculating the difference degree of direction and distance between features, and finally realize high-resolution reconstruction of building features through level-by-level calibration. Tested on three building datasets, Massachusetts, WHU Aerial, and WHU Satellite I, the IoU of this article's method reaches 75.42%, 91.42%, and 67.24%, respectively. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |