LCMorph: Exploiting Frequency Cues and Morphological Perception for Low-Contrast Road Extraction in Remote Sensing Images
Road extraction in remote sensing images is crucial for urban planning, traffic navigation, and mapping. However, certain lighting conditions and compositional materials often cause roads to exhibit colors and textures similar to the background, leading to incomplete extraction. Additionally, the el...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/257 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Road extraction in remote sensing images is crucial for urban planning, traffic navigation, and mapping. However, certain lighting conditions and compositional materials often cause roads to exhibit colors and textures similar to the background, leading to incomplete extraction. Additionally, the elongated and curved road morphology conflicts with the rectangular receptive field of traditional convolution. These challenges significantly affect the accuracy of road extraction in remote sensing images. To address these issues, we propose an end-to-end low-contrast road extraction network called LCMorph, which leverages both frequency cues and morphological perception. First, Frequency-Aware Modules (FAMs) are introduced in the encoder to extract frequency cues, effectively distinguishing low-contrast roads from the background. Subsequently, Morphological Perception Blocks (MPBlocks) are employed in the decoder to adaptively adjust the receptive field to the elongated and curved nature of roads. MPBlock relies on snake convolution, which mimics snakes’ twisting behavior for accurate road extraction. Experiments demonstrate that our method achieves state-of-the-art performance in terms of F1 score and IoU on the self-constructed low-contrast road dataset (LC-Roads), as well as the public DeepGlobe and Massachusetts Roads datasets. |
|---|---|
| ISSN: | 2072-4292 |