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

Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device01:30

Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device

Surveyors use Global Positioning System (GPS) technology to measure the precise location and elevation of points on Earth. In a recent survey, GPS receivers were used to determine the coordinates and elevations of two park monuments. The process involved careful mission planning, data collection, and correction to ensure accuracy. The survey began with mission planning to identify optimal satellite visibility and minimize Position Dilution of Precision (PDOP). A geodetic control point served as...

You might also read

Related Articles

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

Sort by
Same author

Uncertainty-aware deep kernel learning: An end-to-end approach for crack localization in turbine blades.

Scientific reports·2026
Same author

Policy-driven municipal solid waste network optimization under carbon regulation: a risk-informed MILP framework for a post-conflict recovery city.

Scientific reports·2026
Same author

HybridViT for robust wheat leaf disease detection using CLAHE and attention-based feature fusion.

Scientific reports·2026
Same author

An optimized real-time qualitative HOG-based visual servoing system for autonomous wheelchair.

Scientific reports·2026
Same author

Direct video-based spatiotemporal deep learning for cattle lameness detection.

Scientific reports·2025
Same author

ANALYSIS OF PHENOLIC AND FLAVONOIDS OF WILD <i>EPHEDRA ALATA</i> PLANT EXTRACTS BY LC/PDA AND LC/MS AND THEIR ANTIOXIDANT ACTIVITY.

African journal of traditional, complementary, and alternative medicines : AJTCAM·2017

Related Experiment Video

Updated: Jun 11, 2026

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)

Published on: April 8, 2019

HOG-supervised compact CNNs for real-time visual place recognition.

A H Abdul Hafez1, Imad Odeh2

  • 1Department of Computer Science, College of Computer Sciences and Information Technology, King Faisal University, Al-Ahsa, 31982, Saudi Arabia. aabdulhafiz@kfu.edu.sa.

Scientific Reports
|June 9, 2026
PubMed
Summary
This summary is machine-generated.

HOGNet, a deep learning framework, enhances visual place recognition by combining handcrafted histogram of oriented gradients (HOG) features with convolutional neural networks (CNNs). This approach offers superior speed and accuracy compared to traditional models, making it ideal for real-time applications.

Keywords:
Deep LearningHOGNetHandcrafted FeaturesHistogram of Oriented GradientsLightweight ModelsVisual Place Recognition

More Related Videos

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

Related Experiment Videos

Last Updated: Jun 11, 2026

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)

Published on: April 8, 2019

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

Area of Science:

  • Computer Vision
  • Machine Learning
  • Deep Learning

Background:

  • Visual Place Recognition (VPR) traditionally relies on handcrafted features, while deep learning models offer powerful representations but require extensive data and computation.
  • Bridging this gap is crucial for efficient and interpretable VPR systems.

Purpose of the Study:

  • To introduce HOGNet, an efficient deep learning framework that integrates histogram of oriented gradients (HOG) features with convolutional neural networks (CNNs) for improved Visual Place Recognition (VPR).
  • To demonstrate HOGNet's effectiveness in balancing accuracy, interpretability, and computational efficiency.

Main Methods:

  • Developed HOGNet with two variants (HOGNet_441, HOGNet_1764) to predict HOG descriptors using CNNs.
  • Evaluated HOGNet on the Nordland and India Driving Dataset (IDD-VPR) datasets.
  • Compared HOGNet against established architectures like VGG16, ResNet101, and MobileNet.

Main Results:

  • HOGNet_441 achieved 67.7% validation accuracy and 90.76% Recall@20, outperforming VGG16 in Recall@20 while being 36x faster.
  • HOG supervision improved accuracy by +5.55% over a baseline CNN.
  • HOGNet demonstrated approximately 290 FPS performance.

Conclusions:

  • HOGNet offers a computationally efficient and accurate solution for VPR by synergizing handcrafted features and deep learning.
  • The framework's performance makes it suitable for real-time and resource-constrained VPR applications.
  • Incorporating handcrafted descriptors into deep learning models is a promising direction for optimizing VPR systems.