Scholarlink

<p>Traffic Sign Recognition (TSR) is one of the crucial steps for enabling self-driving vehicles to analyze the sign boards and take necessary decisions to enhance road safety and navigation. This paper implements multiple deep learning (DL) architectures and optimizes their hyperparameters using swarm intelligence, namely Firefly optimization. To improve recognition performance, images undergo initial pre-processing, including resizing and grayscale conversion.&#xa0;These refined images are then represented as matrix structures to serve as inputs for various deep learning architectures. The proposed framework is tested on two datasets: <i>i.) </i>Chinese Traffic Sign Dataset (CHSTD) and <i>ii.) </i>German Traffic Sign Recognition Benchmark (GTSRB). The performance analysis on benchmark datasets indicates that the CNN outperforms other DL architectures by achieving an average accuracy of 96.67%, 92.85% and an F1-Score of 96.32%, 92.82% on CHSTD and GTSRB, respectively. These results highlight the supremacy of Convolutional Neural Networks (CNNs) as the leading approach for TSR. This research work underscores that a synergistic combination of deep learning, advanced preprocessing, and Firefly-driven feature optimization can enhance the navigation capabilities of autonomous vehicles.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimizing Deep Learning with Swarm Intelligence for Enhanced Visual Perception of Traffic Sign Recognition

  • 期刊论文

  • 发表日期：

    2026年6月26日

查看全文
  • Arunima Jaiswal,
  • Bam Bahadur Sinha,
  • Alongbar Wary,
  • Deepali,
  • Nitin Sachdeva

摘要

Traffic Sign Recognition (TSR) is one of the crucial steps for enabling self-driving vehicles to analyze the sign boards and take necessary decisions to enhance road safety and navigation. This paper implements multiple deep learning (DL) architectures and optimizes their hyperparameters using swarm intelligence, namely Firefly optimization. To improve recognition performance, images undergo initial pre-processing, including resizing and grayscale conversion. These refined images are then represented as matrix structures to serve as inputs for various deep learning architectures. The proposed framework is tested on two datasets: i.) Chinese Traffic Sign Dataset (CHSTD) and ii.) German Traffic Sign Recognition Benchmark (GTSRB). The performance analysis on benchmark datasets indicates that the CNN outperforms other DL architectures by achieving an average accuracy of 96.67%, 92.85% and an F1-Score of 96.32%, 92.82% on CHSTD and GTSRB, respectively. These results highlight the supremacy of Convolutional Neural Networks (CNNs) as the leading approach for TSR. This research work underscores that a synergistic combination of deep learning, advanced preprocessing, and Firefly-driven feature optimization can enhance the navigation capabilities of autonomous vehicles.