Indian Cautionary Traffic Sign (ICTS) data-set

Cautionary traffic signs are of immense significance to traffic safety. In this study, a robust and optimal real-time approach to recognize the Indian Cautionary Traffic Signs(ICTS) is proposed. ICTS are all triangles with a white backdrop, a red border, and a black pattern. A dataset of 34,000 real-time images has been acquired under various environmental conditions and categorized into 40 distinct classes. Pre-processing techniques are used to transform RGB images to Gray-scale images and enhance contrast in images for superior performance. To find the ICTS, an Optimised Adaptive Boosting Cascade Classifier is used. To classify the specific category of signs found by the Optimised Adaptive Boosting Cascade Classifier, an 11-layer CNN model is built. Finally, using computer vision methods, this model is tested in real-time. Evaluation metrics such as precision, recall, F1 score, error rate, and, mAP are expressed on the ICTS, GTSDB, LISA, STSD, and DITS-based datasets to evaluate the proposed method and compare the results of predictions with other investigations. When compared to other state-of-the-art objects detection models such as SSD, YOLOv3, and Faster RCNN, the proposed model outperformed them all, with a precision of 97.15%, a recall rate of 96.74%, an error rate of 3.26% f1-score of 96.94%, and mAP@0.5IoU of 95.6%.

警示交通标志对于交通安全具有极其重要的意义。本研究提出了一种鲁棒且最优化的实时方法，以识别印度警示交通标志（ICTS）。ICTS均由白色背景、红色边框和黑色图案构成三角形。在多种环境条件下，已收集了34,000张实时图像，并将其分类为40个独特的类别。通过预处理技术，将RGB图像转换为灰度图像，并增强图像对比度，以提高性能。为识别ICTS，采用了优化自适应提升级联分类器。为了对优化自适应提升级联分类器发现的特定标志类别进行分类，构建了一个11层的卷积神经网络（CNN）模型。最终，利用计算机视觉方法，在实时环境中对该模型进行了测试。在ICTS、GTSDB、LISA、STSD和DITS等基于数据集上，通过精确度、召回率、F1分数、错误率和平均精度（mAP）等评估指标，对所提出的方法进行了评估，并将预测结果与其他研究进行了比较。与SSD、YOLOv3和Faster RCNN等最先进的对象检测模型相比，所提出的模型在所有方面均表现优异，其精确度为97.15%，召回率为96.74%，错误率为3.26%，F1分数为96.94%，mAP@0.5IoU为95.6%。