Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Difference from Background: Limit of Detection

Difference from Background: Limit of Detection

The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...

You might also read

Related Articles

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

Sort by

Same author

Identification of differentially expressed immune-related genes in patients with systemic lupus erythematosus and the development of a hub gene-based diagnostic model.

European journal of medical research·2025

Same author

HLGNet: High-Light Guided Network for low-light instance segmentation with spatial-frequency domain enhancement.

Neural networks : the official journal of the International Neural Network Society·2025

Same author

Micrometer Groove Array Structures Inspired by Desert Grasses on Curved Substrates for Enhanced Surface Condensation Efficiency.

Langmuir : the ACS journal of surfaces and colloids·2024

Same author

Chirality identification of Ibuprofen enantiomers by a terahertz polarization-sensitive metasurface sensor.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2024

Same author

Single-cell sequencing reveals the immune landscape of breast cancer patients with brain metastasis.

Thoracic cancer·2024

Same author

Correction: Profiling the impact of the promoters on CRISPR-Cas12a system in human cells.

Cellular & molecular biology letters·2023

Search research articles

Related Experiment Video

Updated: Aug 30, 2025

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

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

Published on: December 15, 2023

Towards High Accuracy Pedestrian Detection on Edge GPUs.

Huaping Zhou¹, Tao Wu¹, Kelei Sun¹

¹School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China.

Sensors (Basel, Switzerland)

|August 26, 2022

Summary

This summary is machine-generated.

This study introduces YOLOv4-TP-Tiny, an efficient pedestrian detection model for edge devices. It achieves higher accuracy and speed compared to YOLOv4-tiny, improving pedestrian detection on low-power GPUs.

Keywords:

YOLOv4-tiny attention mechanism feature fusion lightweight

More Related Videos

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Published on: August 12, 2019

Related Experiment Videos

Last Updated: Aug 30, 2025

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

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

Published on: December 15, 2023

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Published on: August 12, 2019

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Edge GPUs' limited computing power hinders pedestrian detection model accuracy and efficiency.
Existing YOLOv4 models face challenges in balancing detection performance with resource constraints.

Purpose of the Study:

To develop an efficient pedestrian detection algorithm, YOLOv4-TP-Tiny, optimized for edge devices.
To enhance pedestrian detection accuracy and maintain high processing speed on low-power hardware.

Main Methods:

Integrated a two-dimensional attention (TA) mechanism into the backbone network for improved pedestrian focus.
Replaced the spatial pyramid pooling (SPP) with a pedestrian-based feature extraction module (PFM) for scale adaptability.
Utilized a ghost network with TA and a one-way multi-scale feature fusion structure to reduce parameters and maintain speed.

Main Results:

YOLOv4-TP-Tiny achieved 58.3% AP and 31 FPS on the winder person pedestrian dataset.
Outperformed YOLOv4-tiny (55.9% AP, 29 FPS) under identical hardware and dataset conditions.
Demonstrated improved accuracy and efficiency for pedestrian detection on edge GPUs.

Conclusions:

YOLOv4-TP-Tiny effectively addresses the accuracy-efficiency trade-off in edge-based pedestrian detection.
The proposed TA and PFM modules, along with architectural optimizations, significantly enhance model performance.
This model offers a viable solution for real-time pedestrian detection in resource-constrained environments.