The paper addresses a crucial aspect of modern transportation technology by focusing on enhancing the robustness of traffic sign recognition systems. In the context of intelligent transportation systems, accurate traffic sign recognition plays a vital role in ensuring road safety and optimizing traffic management. This study introduces an innovative approach that combines color information with edge magnitude patterns, demonstrating its effectiveness in achieving robust traffic sign recognition. The proposed methodology includes data collection from diverse sources, grouping traffic signs into categories, preprocessing steps for standardization, and the extraction of 22 features using Gray Level Co-occurrence Matrix (GLCM) analysis. These features are then organized into a database and utilized for training a feedforward neural network with two layers for precise traffic sign detection. The project culminates in an overall accuracy rate of 90.2%, underscoring its potential to significantly enhance road safety and traffic regulation.
Identification of Indian Traffic Signs Using Artifical Neural Network
24.11.2023
936838 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Artifical intelligence applications to traffic engineering
TIBKAT | 1994
|Plant Growth Model Using Artifical Neural Networks
SAE Technical Papers | 1997
|Modeling of Shock Absorber Behavior using Artifical Neural Networks
SAE Technical Papers | 1994
|