التفاصيل البيبلوغرافية
| العنوان: |
Traffic sign recognition based on soft non-maximum suppression algorithm using SVM classification. |
| المؤلفون: |
Devi, C. Manjula, Deborah, R. Nancy, Gobinath, A., Priya, S. Padma, Jothi, M., Kanchana, J. S. |
| المصدر: |
AIP Conference Proceedings; 2024, Vol. 3180 Issue 1, p1-6, 6p |
| مستخلص: |
The recognition of traffic signs is a crucial area of emphasis in the advancement of autonomous driving systems and driver-assisted technology for automobiles. These signs convey vital information to drivers, allowing them to promptly and effectively react to current road conditions, hence minimizing the likelihood of accidents and improving overall safety. An enhanced algorithm for lightweight traffic sign identification has been developed to address the issues of low detection accuracy and inconsistent location in lightweight networks. This algorithm utilizes a gentle Non-Maximum Suppression (NMS) technique to enhance the selection of prediction boxes, guaranteeing that predictions for various targets are not mistakenly disregarded. This enhancement results in enhanced precision and higher rates of identifying and retrieving targets. In addition, the method utilizes SVM Classification to determine appropriate anchor sizes for the traffic sign dataset, hence improving detection recall rates and accuracy in target placing. The upgraded method's usefulness is supported by experimental results, which show superior performance on the TT100K dataset compared to the original YOLOv4-Tiny algorithm. [ABSTRACT FROM AUTHOR] |
|
Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Complementary Index |
Find this article in full text from Scitation.