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: Mar 28, 2026

Electroantennography-based Bio-hybrid Odor-detecting Drone using Silkmoth Antennae for Odor Source Localization
06:00

Electroantennography-based Bio-hybrid Odor-detecting Drone using Silkmoth Antennae for Odor Source Localization

Published on: August 27, 2021

6.3K

SODNet: a scale-oriented detection network for efficient UAV-based sewage outfall detection.

Luping Zeng1, Xiaozhou Liu1, Bingyang Dai1

  • 1Business College, Southwest University, Chongqing, 402460, China.

Scientific Reports
|March 27, 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

Programmed Cell Death of Endothelial Cells in Ischemic Heart Disease: Mechanism and Potential Cell and Gene Therapeutic Prospects.

Bioengineering (Basel, Switzerland)·2026
Same author

Dual-Function Electrocatalytic Activity Unleashed by FeMo-Graphdiyne@Ni<sub>3</sub>S<sub>2</sub> with Engineered Heterointerfaces.

Precision chemistry·2026
Same author

Nano-to-macroscale dual core-shell structured bioartificial ligament improves outcomes of anterior cruciate ligament reconstruction in rats: A proof-of-concept study.

Bioactive materials·2026
Same author

Asymmetric Rolling-Up Induced Strong Polarization Electric Field for Ultrahigh Areal Electrochemical Capacitance.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

SARS-CoV-2 directly infects the inner ear and causes hearing dysfunction.

Cell reports·2026
Same author

In Vivo Target Drug Enrichment Based on Spatiotemporal Acoustic Node Modulation (STANM) for Bladder Cancer Treatment.

Advanced materials (Deerfield Beach, Fla.)·2026
Same journal

Turbulent flow in a vortex separator with a directed pipe inlet.

Scientific reports·2026
Same journal

Systematic characteristic evaluation of clay-based cementitious material derived from calcium carbide residue and waste tile powder.

Scientific reports·2026
Same journal

Retraction Note: Improvement of a rapid diagnostic application of monoclonal antibodies against avian influenza H7 subtype virus using Europium nanoparticles.

Scientific reports·2026
Same journal

Applying large language models to spam detection in the Kazakh low-resource language setting.

Scientific reports·2026
Same journal

An open-source 3D printing system enabling in-situ freeze-thaw processing of hydrogels.

Scientific reports·2026
Same journal

An enhanced EfficientNet framework for automated waste classification using cosine annealing and label smoothing.

Scientific reports·2026
See all related articles

This study introduces Scale-Oriented Detection Network (SODNet) for identifying river sewage outfalls using Unmanned Aerial Vehicles (UAVs). SODNet enhances detection accuracy and efficiency on edge devices for environmental monitoring.

Area of Science:

  • Environmental Science
  • Computer Science
  • Remote Sensing

Background:

  • Accurate identification of river sewage outfalls is critical for water pollution control.
  • Unmanned Aerial Vehicles (UAVs) are valuable for monitoring but face challenges in object detection and model deployment on limited platforms.

Purpose of the Study:

  • To develop an efficient deep learning method for robust multi-scale object detection in UAV-based river sewage outfall monitoring.
  • To address the trade-off between detection accuracy and computational efficiency for resource-constrained platforms.

Main Methods:

  • Proposed Scale-Oriented Detection Network (SODNet) featuring an Efficient Context Feature Pyramid Network (ECFPN) for enhanced multi-scale feature representation.
  • Implemented a shared decoupled head with a Multi-Scale Grouped Fusion (MSGF) module to strengthen feature extraction and reduce costs.
Keywords:
LightweightMulti-scale fusionObject detectionSewage outfallsYOLOv8

More Related Videos

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.6K

Related Experiment Videos

Last Updated: Mar 28, 2026

Electroantennography-based Bio-hybrid Odor-detecting Drone using Silkmoth Antennae for Odor Source Localization
06:00

Electroantennography-based Bio-hybrid Odor-detecting Drone using Silkmoth Antennae for Odor Source Localization

Published on: August 27, 2021

6.3K
Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.6K
  • Utilized a channel pruning strategy for model compression and improved inference speed.

    • Main Results:

    • SODNet achieved an AP@50 of 89.9% and 91.1% precision, outperforming the baseline model.
    • Reduced model parameters by 77.5% and GFLOPs by 73.6%, demonstrating significant computational efficiency.
    • Achieved 40.3 FPS on a deployed edge device, confirming its suitability for real-time applications.

    Conclusions:

    • SODNet offers a feasible solution for intelligent environmental supervision by balancing high detection performance with substantial computational efficiency.
    • The method is ideal for resource-constrained UAV scenarios, enabling effective water pollution control through advanced monitoring.