Jove
Visualize
Contact Us

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

Correction: Javaid et al. WebGIS-Based Real-Time Surveillance and Response System for Vector-Borne Infectious Diseases. <i>Int. J. Environ. Res. Public Health</i> 2023, <i>20</i>, 3740.

International journal of environmental research and public health·2025
Same author

PMFSNet: Polarized multi-scale feature self-attention network for lightweight medical image segmentation.

Computer methods and programs in biomedicine·2025
Same author

Correction: Oluwasanmi et al. Multi-Head Spatiotemporal Attention Graph Convolutional Network for Traffic Prediction. <i>Sensors</i> 2023, <i>23</i>, 3836.

Sensors (Basel, Switzerland)·2025
Same author

Facial expression recognition (FER) survey: a vision, architectural elements, and future directions.

PeerJ. Computer science·2024
Same author

Multi-Head Spatiotemporal Attention Graph Convolutional Network for Traffic Prediction.

Sensors (Basel, Switzerland)·2023
Same author

Automatic Hybrid Access Control in SCADA-Enabled IIoT Networks Using Machine Learning.

Sensors (Basel, Switzerland)·2023
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: Aug 24, 2025

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

608

Small-Scale and Occluded Pedestrian Detection Using Multi Mapping Feature Extraction Function and Modified Soft-NMS.

Addis Abebe Assefa1, Wenhong Tian1, Kingsley Nketia Acheampong1

  • 1School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China.

Computational Intelligence and Neuroscience
|October 21, 2022
PubMed
Summary

This study enhances pedestrian detection for autonomous driving by improving feature extraction and non-maximum suppression. The new method effectively identifies small and occluded pedestrians, crucial for intelligent transportation systems.

More Related Videos

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

Related Experiment Videos

Last Updated: Aug 24, 2025

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

608
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Robotics

Background:

  • Pedestrian detection is critical for autonomous driving and intelligent transportation systems to prevent accidents.
  • Detecting small-scale and occluded pedestrians remains a significant challenge due to poor utilization of low-level features and limitations in standard detection algorithms.
  • Existing methods struggle with issues like stochastic weight initialization and greedy non-maximum suppression, leading to high miss rates.

Purpose of the Study:

  • To develop an improved pedestrian detection method capable of accurately identifying small and occluded pedestrians.
  • To address the challenges of ineffective feature utilization and the limitations of greedy non-maximum suppression in current systems.
  • To enhance the robustness and accuracy of pedestrian detection in complex scenarios.

Main Methods:

  • Proposed a multifocus feature extractor by fusing Gaussian and Xavier mapping feature maps to enlarge the effective receptive field.
  • Implemented focused attention feature selection on higher-layer feature maps of the Single Shot Detector (SSD) region proposal module, integrating them with low-layer features to preserve detail.
  • Introduced a decaying non-maximum suppression function that considers score and Intersection over Union (IOU) to mitigate high miss rates.

Main Results:

  • The proposed method demonstrated significant improvements in detecting small and occluded pedestrians on the Caltech pedestrian dataset.
  • Experimental results validated the effectiveness of the multifocus feature extractor and the decaying non-maximum suppression function.
  • The attention-based feature fusion successfully tackled the vanishing of feature details caused by convolutional and pooling operations.

Conclusions:

  • The developed approach effectively enhances pedestrian detection, particularly for challenging cases involving small and occluded individuals.
  • The novel feature extraction and suppression techniques offer a promising solution for improving the safety and reliability of autonomous driving systems.
  • This research contributes to advancing intelligent transportation systems by providing a more accurate and robust pedestrian detection framework.