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

Aggregates Classification01:29

Aggregates Classification

326
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
326
Brick Classifications01:16

Brick Classifications

119
Bricks, a fundamental component of construction, are categorized based on their application and structural characteristics into several types. These include facing bricks, building bricks, hollow bricks, paving bricks, and firebricks. Facing bricks, also referred to as face bricks, are primarily used for both structural support and visual appeal, making their appearance a crucial aspect. In contrast, building bricks are typically used in concealed sections of a structure, such as behind the...
119

You might also read

Related Articles

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

Sort by
Same author

Vision-Based Localization in Urban Areas for Mobile Robots.

Sensors (Basel, Switzerland)·2025
Same author

AI-driven aerial robots advance whale research.

Science robotics·2024
Same author

Force transmission analysis of surface coating materials for multi-fingered robotic grippers.

PeerJ. Computer science·2021
Same author

How do older age, gender and risk groups affect protective behaviours and mental health in the COVID-19 pandemic?

International journal of clinical practice·2021

Related Experiment Video

Updated: Jul 5, 2025

Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect
09:00

Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect

Published on: December 19, 2016

14.7K

Indoor surface classification for mobile robots.

Asiye Demirtaş1,2, Gökhan Erdemir3, Haluk Bayram2

  • 1Department of Electrical and Electronics Engineering, Istanbul Sabahattin Zaim University, Istanbul, Turkiye.

Peerj. Computer Science
|January 23, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a lightweight deep learning model for mobile robot surface recognition, achieving 99.52% accuracy. The efficient model is ideal for robots with limited computational power, enabling safer navigation.

Keywords:
Convolutional neural network, CNNIndoor surface classificationMobile robotsMobileNetV2

More Related Videos

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

11.6K
Manufacturing, Control, and Performance Evaluation of a Gecko-Inspired Soft Robot
07:40

Manufacturing, Control, and Performance Evaluation of a Gecko-Inspired Soft Robot

Published on: June 10, 2020

13.9K

Related Experiment Videos

Last Updated: Jul 5, 2025

Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect
09:00

Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect

Published on: December 19, 2016

14.7K
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

11.6K
Manufacturing, Control, and Performance Evaluation of a Gecko-Inspired Soft Robot
07:40

Manufacturing, Control, and Performance Evaluation of a Gecko-Inspired Soft Robot

Published on: June 10, 2020

13.9K

Area of Science:

  • Robotics
  • Computer Vision
  • Machine Learning

Background:

  • Surface type recognition is vital for mobile robot navigation and safety.
  • Vision-based surface classification faces challenges due to variations in appearance (e.g., carpets).

Purpose of the Study:

  • To develop an accurate and efficient deep learning model for indoor surface classification (carpet, tiles, wood).
  • To create a lightweight model suitable for resource-constrained robotic systems.

Main Methods:

  • A new dataset of 2,081 indoor surface images was created.
  • Several pre-trained deep learning models (InceptionV3, VGG16, etc.) were evaluated.
  • A modified, lightweight MobileNetV2 model was proposed and optimized using various optimizers.

Main Results:

  • The proposed lightweight model achieved 99.52% accuracy and 99.66% in precision, recall, and F1-score.
  • The model's size was reduced from 42 MB to 11 MB.
  • Real-time testing on a mobile robot yielded 99.25% accuracy.
  • The proposed model demonstrated reduced loading and processing times.

Conclusions:

  • The proposed lightweight model offers superior performance and efficiency for surface classification in mobile robotics.
  • This model is well-suited for embedded systems and robots with limited computational capacity.
  • The research contributes a valuable dataset and an optimized model for advancing robotic perception.