This paper aims to study and construct a convolutional neural network utilizing traffic signal classification algorithm for Germany. The algorithm is constructed and trained using image data preprocessing and convolutional neural network. Accuracy, recall, precision, and f1-score were used to verify the effectiveness of the algorithm. A comparison between the proposed algorithm and VGG19 is conducted to demonstrate the superiority of the proposed approach.The experiment in this paper utilize GTSRB dataset, and the algorithm in this paper achieves outstanding correctnes and recall rates in the traffic sign classification tasks. Therefore, the proposed algorithm exhibits potential for practical applications and presents an effective and accurate solution in the domain of traffic safety.
Construction and research of German traffic sign recognition algorithm based on convolutional neural network
2023-10-11
3323254 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Traffic sign recognition using weighted multi-convolutional neural network
IET | 2018
|Traffic sign recognition using weighted multi‐convolutional neural network
Wiley | 2018
|Convolutional Neural Networks for Traffic Sign Recognition
TIBKAT | 2021
|