Abstract
One of the most critical challenges for self-driving vehicles is accurately identifying traffic signs, which are essential for self-navigation and decision-making. Systems for the detection and recognition of road signs play a crucial role in this process by providing vital information for the vehicle's decision-making. This study proposes an approach for road sign identification and recognition utilising the TensorFlow Object Detection API and the SSD MobileNet V2 FPN Lite model.
In this proposal, we combine the efficiency and accuracy of SSD with the lightweight architecture of MobileNet to achieve excellent performance in object detection benchmarks while maintaining a small model size and low processing power requirements. The model was trained using the German Traffic Sign Recognition Benchmark (GTSRB) dataset. The proposed methodology achieved a mean detection accuracy of 100% while requiring 0.317 seconds to detect and recognise each sign.
Recommended Citation
Dhaif, Zahraa Salah and El Abbadi, Nidhal K.
(2024)
"Road Signs Detection Using SSD MobileNetV2,"
Karbala International Journal of Modern Science: Vol. 10
:
Iss.
4
, Article 1.
Available at:
https://doi.org/10.33640/2405-609X.3373
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Included in
Biology Commons, Chemistry Commons, Computer Sciences Commons, Physics Commons
