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 Video

Updated: Jul 16, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

An adaptive feature extraction lightweight network for enhanced landslide detection.

Ruiyunfei Pan1, Haowei Pan2

  • 1School of the Environment, The University of Queensland, Brisbane, QLD, 4072, Australia.

Scientific Reports
|June 25, 2026
PubMed
Summary

This study introduces AFL-NET, a lightweight network for rapid landslide detection. It significantly improves accuracy and reduces computational load, enabling real-time disaster monitoring and early warning systems.

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

Association between stress hyperglycemia ratio with short-term and long-term mortality in critically ill patients with ischemic stroke.

Acta diabetologica·2024
Same author

Building Interior Layout Design Based on Building Information Model and Deep Learning Technology: Taking the Interior Renewal Design of the Fifth Floor of the Procuratorate of Dong Xi Hu District as an Example.

Computational intelligence and neuroscience·2022
See all related articles

Area of Science:

  • Geosciences
  • Computer Science
  • Artificial Intelligence

Background:

  • Landslide detection is critical for disaster management but challenged by irregular morphology, scale variations, and computational costs of deep learning models.
  • Existing methods struggle with real-time processing and on-device deployment for effective landslide monitoring.

Purpose of the Study:

  • To develop an efficient and accurate lightweight network, Adaptive Feature Extraction Lightweight Network for Landslide Detection (AFL-NET), for rapid landslide detection.
  • To enhance the model's ability to handle diverse landslide characteristics and complex terrains while minimizing computational resources.

Main Methods:

  • The AFL-NET utilizes the Ghostv2C2f module for efficient feature extraction with ghost features and spatial attention.
  • SimAM-Augmented Bi-directional Feature Pyramid Network (SBIFPN) is employed for enhanced multi-scale feature fusion.
Keywords:
Attention mechanismDeep learningFeature fusionLandslide detectionLightweight network

Related Experiment Videos

Last Updated: Jul 16, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • The Spatial Modeling and Context-aware C2f (SMC2f) module integrates contextual encoding and self-attention for robust detection in complex environments.

    • Main Results:

    • AFL-NET achieved a mean Average Precision (mAP) of 90.1%, a 3.9% improvement over the YOLOv11n baseline.
    • The model demonstrated a 15.3% reduction in parameters, indicating significant efficiency gains.
    • The network effectively handles landslides of varying shapes and scales while suppressing background noise.

    Conclusions:

    • AFL-NET offers a highly accurate and computationally efficient solution for landslide detection.
    • Its lightweight design makes it suitable for real-time, on-device deployment in disaster monitoring applications.
    • The proposed network provides reliable technical support for early warning and risk mitigation strategies.