Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Knowledge-Guided Modulation for Terrain-Aware Landslide Detection Using Deformable Transformers.

Yan-Chang Jia1, Shu-Yan Hua1, Hong-Fei Wang2

  • 1College of Geosciences and Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, China.

Sensors (Basel, Switzerland)
|May 13, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

L-SAINet: A Shape-Adaptive and Inner-Scale Interaction Network for Landslide Detection in Complex Remote Sensing Scenarios.

Sensors (Basel, Switzerland)·2026
Same author

Bulk nano-heterointerface secures molecular contacts in perovskite solar cells.

Nature materials·2026
Same author

Aberrant drainage of the right anterior sectional bile duct into the neck of the gallbladder: Intraoperative fluorescence-guided identification and functional reconstruction.

Hepatobiliary & pancreatic diseases international : HBPD INT·2025
Same author

Efficacy and safety of stem cell therapy in patients with chronic lower extremity ulcers: an umbrella review of systematic reviews and meta-analyses.

Stem cell research & therapy·2025
Same author

Triterpenoids and sterols from <i>Pseudocydonia sinensis</i> fruits and their anti-inflammatory activity.

Natural product research·2025
Same author

Sub-1 cm-1 high-resolution broadband sum-frequency generation vibrational spectroscopy (HR-BB-SFG-VS) with significantly improved sensitivity and signal-to-noise ratio (SNR).

The Journal of chemical physics·2025
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

This study introduces a novel terrain-aware transformer for landslide detection, enhancing accuracy in mountainous regions by integrating topographic data. The method improves landslide mapping by considering geological features alongside visual information.

Area of Science:

  • Geosciences
  • Computer Science
  • Remote Sensing

Background:

  • Landslide detection from medium-resolution optical remote sensing is challenging due to spectral ambiguity, vegetation, shadows, and background noise in complex mountainous terrains.
  • Existing deep learning methods often rely on appearance-based features, neglecting crucial terrain-related priors essential for understanding slope instability.

Purpose of the Study:

  • To develop a terrain-aware deformable transformer framework for improved landslide detection using multimodal remote sensing data.
  • To enhance feature learning by incorporating explicit topographic priors derived from Digital Elevation Models (DEM) and slope data.

Main Methods:

  • A unified five-channel representation integrating RGB imagery, DEM, and slope data.
  • A knowledge-guided modulation module to leverage terrain priors for feature enhancement.
Keywords:
deformable DETRknowledge-guided learninglandslide detectionmulti-channel data fusionremote sensingterrain informationtransformer-based object detection

Related Experiment Videos

  • A deformable transformer architecture adapted for landslide detection.

    • Main Results:

    • The proposed method achieved superior performance compared to baseline approaches on the Bijie landslide dataset.
    • Achieved 72.9% AP@[0.5:0.95] and 77.2% AP75, demonstrating high detection accuracy.
    • Showcased improved localization robustness in visually complex mountainous scenes.

    Conclusions:

    • Terrain-aware feature modulation significantly enhances geomorphological plausibility and detection accuracy in landslide inventory mapping.
    • The framework offers a promising approach for overcoming limitations of appearance-driven methods in challenging environments.
    • Further validation across diverse regions is recommended to assess the broader generalization capabilities of the proposed method.