Effective implementation of machine learning algorithms using 3D colour texture feature for traffic sign detection for smart cities

Abstract

In recent past, emerging technology, such as AI has revolutionized progress and advancement of traffic management solutions in context of smart cities. This paper describes a novel approach of using 3D colour-texture based feature for image detection on public datasets of Chinese traffic sign research database (TSRD) and Mapillary image database. The implementation of 3D colour texture feature for traffic sign detection is evaluated using artificial neural network and multiple other machine learning algorithms as classifier for image detection purposes. Both datasets used in our experiments are considered among most diverse traffic signage datasets globally with annotations of almost all classes. Image datasets have been publicly made available to researchers for academic purposes. For classification of traffic sign images on Chinese TSRD and Mapillary datasets, the result outcome from backpropagation neural network (NN) classifier outperforms all other and produced best results and under multiple ML algorithms, support vector machines (SVM) cubic has best results. For classification of traffic sign images on Mapillary dataset, the result outcome from rational quadratic Gaussian process regression has best results. Also, the comparisons of results with other similar novel works have also been discussed.The proposed approach outperformed the previous experiments as observed through comparative analysis performed on both datasets. The conclusion of the research work highlights that the image detection performance is noticeably improved by using the combined 3D colour-texture feature based proposed approach.

Exploring Explainable Artificial Intelligence Techniques for Interpretable Neural Networks in Traffic Sign Recognition Systems

“…Precision (P) is calculated as the ratio of true positives T P (i.e., correct positive predictions) to all the positive predictions made by the model, calculated in Equation (6). Precision gives us an understanding of the model's ability to avoid false positives F P , thus ensuring that the detected traffic signs are indeed correct.…”

“…T P T P + F P (6) Recall (R), also known as sensitivity, gauges the model's completeness. It measures the percentage of true positives out of all the actual positive cases present in the dataset, as outlined in Equation (7).…”

“…In the field of TSR, deep learning techniques, especially convolutional neural networks (CNNs), have become a popular choice due to their reliability and accuracy in recognizing and categorizing traffic signs. However, these models often lack transparency, making it challenging to understand the rationale behind their outcomes [5,6]. The intricacies of their internal mechanisms and decision-making processes often lack transparency, resulting in a "black-box" scenario where the logic behind specific outcomes is not clear.…”

R‐ICTS: Recognize the Indian cautionary traffic signs in real‐time using an optimized adaptive boosting cascade classifier and a convolutional neural network

“…The training and testing of the model are done on the GTSDB dataset and attained 92.11% accuracy. Vashisht et al 17 proposed a new 3D color texture‐based traffic sign identification algorithm. To begin, the region of interest (ROI) is extracted using image segmentation.…”

A Fusion Model With Yolov3 and Shufflenetv2 Networks for Traffic Sign Recognition

“…There are two methods for traffic sign feature extraction, one is based on color and shape features [7][8][9], and the object detection method based on color features is mainly to detect the region of interest (ROI). Due to the influence of uneven illumination and discoloration of traffic signs, it will cause seriously missed detection when using color features-based object detection methods.…”