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 Concept Videos

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

6.4K
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...
6.4K

You might also read

Related Articles

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

Sort by
Same author

ToggleMimic: A Two-Stage Policy for Text-Driven Humanoid Whole-Body Control.

Sensors (Basel, Switzerland)·2025
Same author

Drp1-Dependent Mitochondrial Fission Contributes to Lactic Acid-Induced Chicken Cardiomyocyte Damage.

Journal of biochemical and molecular toxicology·2025
Same author

W-VSLAM: A Visual Mapping Algorithm for Indoor Inspection Robots.

Sensors (Basel, Switzerland)·2024
Same author

Proteomic Analysis of the Mitochondrial Responses in P19 Embryonic Stem Cells Exposed to Florfenicol.

Toxics·2023
Same author

Autonomous motion and control of lower limb exoskeleton rehabilitation robot.

Frontiers in bioengineering and biotechnology·2023
Same author

Planning of Medical Flexible Needle Motion in Effective Area of Clinical Puncture.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Jul 15, 2025

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.6K

An H-GrabCut Image Segmentation Algorithm for Indoor Pedestrian Background Removal.

Xuchao Huang1,2, Shigang Wang1,2, Xueshan Gao1,2

  • 1School of Automation, Guangxi University of Science and Technology, Liuzhou 545000, China.

Sensors (Basel, Switzerland)
|September 28, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces an enhanced H-GrabCut algorithm for precise indoor pedestrian segmentation, improving robot navigation and trajectory prediction accuracy. The method achieves 97.13% accuracy, overcoming depth and lighting challenges.

Keywords:
H-GrabCut algorithmimage enhancementindoor pedestrian segmentation

More Related Videos

Substructure Analyzer: A User-Friendly Workflow for Rapid Exploration and Accurate Analysis of Cellular Bodies in Fluorescence Microscopy Images
14:28

Substructure Analyzer: A User-Friendly Workflow for Rapid Exploration and Accurate Analysis of Cellular Bodies in Fluorescence Microscopy Images

Published on: July 15, 2020

8.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Related Experiment Videos

Last Updated: Jul 15, 2025

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.6K
Substructure Analyzer: A User-Friendly Workflow for Rapid Exploration and Accurate Analysis of Cellular Bodies in Fluorescence Microscopy Images
14:28

Substructure Analyzer: A User-Friendly Workflow for Rapid Exploration and Accurate Analysis of Cellular Bodies in Fluorescence Microscopy Images

Published on: July 15, 2020

8.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Area of Science:

  • Robotics
  • Computer Vision
  • Artificial Intelligence

Background:

  • Accurate pedestrian detection and distance measurement are critical for indoor mobile robot navigation and trajectory prediction.
  • Existing methods struggle with depth camera inaccuracies and varying illumination conditions, impacting robot safety and efficiency.

Purpose of the Study:

  • To develop an improved image segmentation algorithm for accurate indoor pedestrian extraction and distance measurement.
  • To enhance the reliability of pedestrian data for mobile robot path planning and trajectory prediction.

Main Methods:

  • Leveraged YOLO-V5 for pedestrian detection node construction.
  • Applied an enhanced BIL-MSRCR algorithm to improve pedestrian edge detail.
  • Optimized GrabCut algorithm clustering with 2D entropy, UV component distance, and LBP texture features.

Main Results:

  • Achieved a segmentation accuracy of 97.13% on the INRIA dataset and in real-world tests.
  • Demonstrated superior performance over alternative methods in sensitivity, missegmentation rate, and intersection-over-union.
  • Confirmed the algorithm's feasibility and practicality for indoor robot applications.

Conclusions:

  • The proposed H-GrabCut algorithm effectively segments indoor pedestrians, addressing depth and illumination issues.
  • This improved segmentation enhances the preliminary processing for mobile robot pedestrian trajectory prediction.
  • The findings enable more reliable path planning for indoor mobile robots based on accurate pedestrian data.