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

Classification of Signals01:30

Classification of Signals

1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K
Methods of Classification and Identification01:28

Methods of Classification and Identification

863
Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...
863
Force Classification01:22

Force Classification

2.2K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.2K
Classification of Systems-I01:26

Classification of Systems-I

505
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
505
Classification of Systems-II01:31

Classification of Systems-II

432
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
432

You might also read

Related Articles

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

Sort by
Same author

Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models.

Sensors (Basel, Switzerland)·2023
Same author

Co-Training for Deep Object Detection: Comparing Single-Modal and Multi-Modal Approaches.

Sensors (Basel, Switzerland)·2021
Same author

On-Board Detection of Pedestrian Intentions.

Sensors (Basel, Switzerland)·2017
See all related articles

Related Experiment Video

Updated: Dec 30, 2025

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

9.5K

Recognizing New Classes with Synthetic Data in the Loop: Application to Traffic Sign Recognition.

Gabriel Villalonga1,2, Joost Van de Weijer1,2, Antonio M López1,2

  • 1Computer Vision Center (CVC), Universitat Autònoma de Barcelona (UAB), 08193 Bellaterra, Spain.

Sensors (Basel, Switzerland)
|January 25, 2020
PubMed
Summary

Generating new traffic sign classes for on-board vision systems is challenging. This study uses Generative Adversarial Networks (GANs) to create synthetic training data, improving recognition accuracy for novel traffic signs.

Keywords:
CNNstraffic sign recognitiontraining with synthetic data

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.1K
Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.5K

Related Experiment Videos

Last Updated: Dec 30, 2025

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

9.5K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.1K
Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.5K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • On-board vision systems require rapid adaptation to recognize new object classes, such as novel traffic signs.
  • Acquiring and annotating sufficient real-world data for uncommon classes is time-consuming and often impractical.

Purpose of the Study:

  • To develop and evaluate a method for generating synthetic training samples for new traffic sign classes.
  • To leverage Generative Adversarial Network (GAN) technology for synthetic-to-real domain adaptation in traffic sign recognition.

Main Methods:

  • The proposed method combines synthetic image generation with GAN-based domain adaptation.
  • Generative Adversarial Networks (GANs) were trained on both synthetic and real-world data from known classes.
  • The trained GAN was then applied to synthetic samples of new classes to adapt them to the real-world domain.
  • Experiments utilized the Tsinghua dataset and its synthetic counterpart, SYNTHIA-TS, employing a ResNet101 classifier and CycleGAN for domain adaptation.

Main Results:

  • The proposed method demonstrated effectiveness in generating useful synthetic samples for new traffic sign classes.
  • Performance was particularly strong with a ResNet101 classifier and CycleGAN for domain adaptation, especially at a new/known class ratio of approximately 1/4.
  • Positive results were also achieved even with more challenging ratios, such as 4/1 new/known classes.

Conclusions:

  • Combining synthetic data generation with GAN-based domain adaptation is a viable strategy for expanding the recognition capabilities of on-board vision systems.
  • The choice of Convolutional Neural Network (CNN) classifier and GAN architecture is crucial for the success of the proposed method.
  • This approach offers a practical solution for rapidly incorporating new classes into systems like traffic sign recognition.