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: Dec 3, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

855

CRPN-SFNet: A High-Performance Object Detector on Large-Scale Remote Sensing Images.

Qifeng Lin, Jianhui Zhao, Gang Fu

    IEEE Transactions on Neural Networks and Learning Systems
    |October 28, 2020
    PubMed
    Summary

    This study introduces a new object detection framework for large-scale remote sensing images. The cropping region proposal network-based scale folding network (CRPN-SFNet) improves speed and accuracy for detecting objects of various sizes.

    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

    <i>In vitro</i> transcribed circRNA as a therapeutic agent for cancer.

    Acta pharmaceutica Sinica. B·2026
    Same author

    Transient Overcoordination Unlocks C-H Bond Activation in Boron-Based Oxidative Dehydrogenation.

    Journal of the American Chemical Society·2026
    Same author

    Peri-Implant Tissue Stability Following Guided Bone Regeneration With Bioceramic: A Multicenter One-Year Cohort Study.

    Clinical implant dentistry and related research·2026
    Same author

    Soil nutrient stability outperforms microbial abundance stability as an early-warning indicator in a Tibetan alpine meadow under seasonal asymmetric warming.

    Journal of environmental management·2026
    Same author

    Correction: The Dynamics of Soil Organic Carbon in Alpine Grasslands Affected by Livestock Grazing Intensity.

    Environmental management·2026
    Same author

    Effects of a 12-Year Nitrogen Addition Experiment on Protist Communities in a Boreal Forest, Heilongjiang Province, China.

    Animals : an open access journal from MDPI·2026

    Area of Science:

    • Computer Vision
    • Remote Sensing
    • Artificial Intelligence

    Background:

    • Current object detection methods struggle with large-scale remote sensing images due to GPU memory limitations.
    • The wide range of object scales in remote sensing imagery poses a significant challenge for existing detectors.
    • Geospatial object detection requires methods that can handle both high computational demands and diverse object sizes.

    Purpose of the Study:

    • To propose a faster and more accurate object detection framework for large-scale remote sensing images.
    • To address the limitations of GPU memory and the wide scale variation of objects in remote sensing data.
    • To enhance the detection of geospatial objects across a broad spectrum of sizes, from very small to very large.

    Main Methods:

    More Related Videos

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
    08:25

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

    Published on: May 7, 2019

    9.4K

    Related Experiment Videos

    Last Updated: Dec 3, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    855
    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
    08:25

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

    Published on: May 7, 2019

    9.4K
  • Introduced the cropping region proposal network-based scale folding network (CRPN-SFNet) framework.
  • CRPN utilizes a weak semantic RPN and cropping region generation to reduce computational load.
  • SFNet employs scale folding-based training and testing to broaden the detection range for varied object scales.

    • Main Results:

    • The CRPN enables faster processing of large images with limited GPU memory.
    • The SFNet significantly improves the accuracy of detecting geospatial objects across a wide scale range.
    • The proposed CRPN-SFNet framework demonstrates superior performance in both accuracy and speed compared to state-of-the-art methods on aerial imagery datasets.

    Conclusions:

    • The CRPN-SFNet framework effectively overcomes the challenges of object detection in large-scale remote sensing images.
    • The method offers a practical solution for high-performance geospatial object detection with limited computational resources.
    • This approach advances the capabilities of object detection in remote sensing, particularly for diverse and challenging datasets.