Recognizing New Classes with Synthetic Data in the Loop: Application to Traffic Sign Recognition
On-board vision systems may need to increase the number of classes that can be recognized in a relatively short period. For instance, a traffic sign recognition system may suddenly be required to recognize new signs. Since collecting and annotating samples of such new classes may need more time than...
Main Authors: | Gabriel Villalonga, Joost Van de Weijer, Antonio M. López |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/3/583 |
Similar Items
-
Partially Connected Neural Networks for an Efficient Classification of Traffic Signs
by: Bousarhane Btissam, et al.
Published: (2021-10-01) -
Road images augmentation with synthetic traffic signs using neural networks
by: A.S. Konushin, et al.
Published: (2021-09-01) -
Implementation of traffic sign recognition on the scaled vehicle model
by: Mitrović Miloš, et al.
Published: (2022-01-01) -
CR-YOLOv8: Multiscale Object Detection in Traffic Sign Images
by: Lu Jia Zhang, et al.
Published: (2024-01-01) -
Detection and Recognition of Obscured Traffic Signs During Vehicle Movement
by: Shi Luo, et al.
Published: (2023-01-01)