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: Jun 20, 2026

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

1.1K

MMDet-Edge: A Multi-Scale and Multi-Object Detection Framework for Safety-Critical Edge Deployment.

Tianyi Zhu1, Hong Liu1, Haoming Duan1

  • 1Shanghai Dahua Surveying and Mapping Technology Co., Ltd., Shanghai 201208, China.

Sensors (Basel, Switzerland)
|February 27, 2026
PubMed
Summary

Related Concept Videos

Effects of EDTA on End-Point Detection Methods01:18

Effects of EDTA on End-Point Detection Methods

Different methods, such as visual observance of metal-ion indicators, spectroscopic techniques, and potentiometric methods, can determine the endpoint of an EDTA titration.
In the visual method, metal-ion indicators (metallochromic dyes), which have distinct colors in their free and complex forms, are added to the mixture to signal the titration's end point. They form stable complexes with metal ions, but these complexes are weaker than the corresponding metal–EDTA complexes. As a result, EDTA...

You might also read

Related Articles

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

Sort by
Same author

Research on a Visually Assisted Efficient Blind-Guiding System and an Autonomous Shopping Guidance Robot Arm Adapted to the Complex Environment of Farmers' Markets.

Sensors (Basel, Switzerland)·2025
Same author

Design and Joint Position Control of Bionic Jumping Leg Driven by Pneumatic Artificial Muscles.

Micromachines·2022
Same author

Development and characterization of monoclonal antibodies to spring viraemia of carp virus.

Veterinary immunology and immunopathology·2008
Same author

Electrophysiological characterization of a novel Kv channel blocker N,N'-[oxybis(2,1-ethanediyloxy-2,1-ethanediyl) ]bis(4-methyl)-benzenesulfonamide found in virtual screening.

Acta pharmacologica Sinica·2008
Same author

Cloning and characterization of an rRNA methyltransferase from Sorangium cellulosum.

Biochemical and biophysical research communications·2008
Same author

Reconstruction of anophthalmic orbits and contracted eye sockets with microvascular radial forearm free flaps.

Ophthalmic plastic and reconstructive surgery·2008

MMDet-Edge enhances construction site safety with an AI framework that accurately detects hazards in real-time, even in challenging conditions. This edge AI system significantly reduces safety incidents by improving detection and minimizing critical errors.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Edge Computing

Background:

  • Construction site safety is a major global concern.
  • Current surveillance systems face limitations in accuracy, real-time performance, and robustness under edge constraints.
  • There is a need for advanced AI solutions for real-time safety monitoring in construction.

Purpose of the Study:

  • To introduce MMDet-Edge, an edge-optimized unified detection framework for construction site safety.
  • To improve multi-object detection accuracy, real-time efficiency, and environmental robustness on edge devices.
  • To reduce high-consequence false negatives by incorporating safety statistics.

Main Methods:

  • Developed an adaptive feature fusion architecture with spatial-channel attention for improved small-object detection.
Keywords:
adaptive feature fusionconstruction safetyedge computingmulti-class object detectionneural architecture searchrisk-aware optimization

Related Experiment Videos

Last Updated: Jun 20, 2026

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

1.1K
  • Employed a hardware-conscious neural architecture search (HC-NAS) for co-optimizing sparsity and quantization.
  • Integrated OSHA fatality statistics into a risk-weighted evaluation paradigm.

    • Main Results:

    • Achieved a 9.3% increase in small-object average precision (AP).
    • Reached 89.4% mAP@0.5 at 1.8 W power consumption, outperforming other edge detectors.
    • Reduced high-consequence false negatives by 34% and demonstrated a 22% reduction in safety incidents in field deployments.
    • Enabled real-time detection of personnel, helmets, flames, smoke, and vests under extreme conditions (e.g., >60% occlusion, >100 lux variance).

    Conclusions:

    • MMDet-Edge establishes a new architectural paradigm for safety-critical edge AI through hardware-algorithm co-design.
    • The framework offers a robust and efficient solution for real-time safety monitoring in demanding construction environments.
    • The system demonstrates significant improvements in safety incident reduction and detection capabilities.