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

YOLO-Faster: An efficient remote sensing object detection method based on AMFFN.

Yicheng Tong1, Guan Yue1, Longfei Fan1

  • 1R&D Department 4, Hangzhou Zhiyuan Research Institute Co.,Ltd, Hangzhou, China.

Science Progress
|October 3, 2024
PubMed
Summary

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

Pultrusion-Guided Biomimetic Wet Spinning Yields Tough, Ionically Conductive Silk Fibers for Integrated Ionotronics and Electroluminescent Textiles.

ACS applied materials & interfaces·2026
Same author

SpaLSTF: Diffusion-based generative model with BiLSTM and XCA-Transformer for spatial transcriptomics imputation.

PLoS computational biology·2026
Same author

Exosomal IGFALS as a prognostic biomarker in hepatocellular Carcinoma: Associations with immune infiltration and clinical outcomes.

Molecular and cellular probes·2026
Same author

Correction: SpaMWGDA: Identifying spatial domains of spatial transcriptomes using multi-view weighted fusion graph convolutional network and data augmentation.

PLoS computational biology·2026
Same author

<sup>131</sup>I/MTX-loaded engineered outer membrane vesicles for sequentially coordinated radio-metabolic-immunotherapy of glioma.

Journal of nanobiotechnology·2025
Same author

SpaMWGDA: Identifying spatial domains of spatial transcriptomes using multi-view weighted fusion graph convolutional network and data augmentation.

PLoS computational biology·2025
Same journal

Association between serum albumin-to-globulin ratio and diabetic retinopathy: A cross-sectional study based on the 2001-2020 NHANES database.

Science progress·2026
Same journal

Prognostic value of the triglyceride-glucose index combined with glycemic variability for all-cause mortality in patients with sepsis: A retrospective cohort study.

Science progress·2026
Same journal

Asynchronous federated learning with partial weights aggregation for energy consumption forecasting.

Science progress·2026
Same journal

Prediction of laser welding molten pool light intensity distribution based on an artificial neural network.

Science progress·2026
Same journal

Prognostic characteristics of disulfidptosis-related genes across cancers and their potential implications in osteosarcoma.

Science progress·2026
Same journal

Automated data processing and analysis method for shaking table tests of masonry structures based on python open-source toolchain.

Science progress·2026
See all related articles
This summary is machine-generated.

This study introduces YOLO-Faster, a lightweight object detection network for remote sensing. It achieves 71.4% mAP and 38 FPS, enabling real-time mobile deployment for challenging scenarios.

Area of Science:

  • Computer Vision
  • Remote Sensing Technology
  • Deep Learning

Background:

  • Object detection is crucial in computer vision but faces challenges in remote sensing due to complex backgrounds, scale variations, and noise.
  • Existing deep learning models offer high accuracy but are computationally expensive, limiting their use on mobile devices.

Purpose of the Study:

  • To develop an enhanced lightweight remote sensing object detection network (YOLO-Faster) for mobile deployment.
  • To improve detection accuracy and speed for remote sensing object detection tasks.

Main Methods:

  • The YOLO-Faster network is built upon YOLOv5, incorporating a lightweight backbone for enhanced speed and reduced computational load.
  • An adaptive multiscale feature fusion network is introduced to handle objects of varying scales in complex backgrounds.
Keywords:
Remote sensing object detectionYOLOdeep learninglightweight network

Related Experiment Videos

  • A decoupled detection head is employed to improve robustness against background noise by separating classification and regression.

    • Main Results:

    • The proposed YOLO-Faster network achieved a mean average precision (mAP) of 71.4% on the DOTA dataset.
    • The network demonstrated a detection speed of 38 frames per second (FPS).
    • The results indicate successful real-time detection capabilities for mobile devices.

    Conclusions:

    • YOLO-Faster effectively addresses the challenges of remote sensing object detection, including scale variation and background noise.
    • The lightweight design and improved performance make it suitable for real-time applications on resource-constrained mobile devices.