Recognizing and classifying traffic signs is a challenging task that can significantly improve road safety. Deep neural networks have achieved impressive results in various applications, including ...object identification and automatic recognition of traffic signs. These deep neural network-based traffic sign recognition systems may have limitations in practical applications due to their computational requirements and resource consumption. To address this issue, this paper presents a lightweight neural network for traffic sign recognition that achieves high accuracy and precision with fewer trainable parameters. The proposed model is trained on the German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign (BelgiumTS) datasets. Experimental results demonstrate that the proposed model has achieved 98.41% and 92.06% accuracy on GTSRB and BelgiumTS datasets, respectively, outperforming several state-of-the-art models such as GoogleNet, AlexNet, VGG16, VGG19, MobileNetv2, and ResNetv2. Furthermore, the proposed model outperformed these methods by margins ranging from 0.1 to 4.20 percentage point on the GTSRB dataset and by margins ranging from 9.33 to 33.18 percentage point on the BelgiumTS dataset.
Traffic sign detection assists in driving by acquiring the temporal and spatial information of the potential signs for road awareness and safety. The purpose of conducting research on this topic is ...introduced to a novel and less complex algorithm that works for traffic signs identification, accurately. Initially, the authors estimate the global threshold value using the correlational property of the given image. In order to get red and blue traffic signs, a segmentation algorithm is developed using estimated threshold and morphological operations followed by an enhancement procedure, the net outcome of which is provided the greater number of potential signs. Moreover, remaining regions are filtered in terms of statistical measures using the non-potential regions. Furthermore, detection is performed on the basis of histogram of oriented gradient features by employing the support vector machine (SVM)–K-nearest neighbour (KNN) classifier. The denoising approach with the weighted fusion of KNN and SVM is used in order to improve the performance of the proposed algorithm by reducing the false positive. A recognition phase is performed on the GTSRB data set in order to formulate the feature vector. The proposed method performed the significant recognition with an accuracy rate of 99.32%. It is quite comparable to the existing state-of-the-art techniques.
Traffic signs recognition (TSR) is an important part of some advanced driver-assistance systems (ADASs) and auto driving systems (ADSs). As the first key step of TSR, traffic sign detection (TSD) is ...a challenging problem because of different types, small sizes, complex driving scenes, and occlusions. In recent years, there have been a large number of TSD algorithms based on machine vision and pattern recognition. In this paper, a comprehensive review of the literature on TSD is presented. We divide the reviewed detection methods into five main categories: color-based methods, shape-based methods, color- and shape-based methods, machine-learning-based methods, and LIDAR-based methods. The methods in each category are also classified into different subcategories for understanding and summarizing the mechanisms of different methods. For some reviewed methods that lack comparisons on public datasets, we reimplemented part of these methods for comparison. The experimental comparisons and analyses are presented on the reported performance and the performance of our reimplemented methods. Furthermore, future directions and recommendations of the TSD research are given to promote the development of the TSD.
For a safe and automated vehicle driving application, it is a prerequisite to have a robust and highly accurate traffic sign detection system. In this paper, we proposed a novel energy-efficient Thin ...yet Deep convolutional neural network architecture for traffic sign recognition. Within the proposed architecture, each convolutional layer contains less than 50 features enabling our convolutional neural network to be trained quickly even without the aid of a graphics processing unit. The performance of the proposed architecture is measured using two publicly available traffic sign datasets, namely the German Traffic Sign Recognition Benchmark and the Belgian Traffic Sign Classification dataset. First, we train and test the performance of the proposed architecture using the large German Traffic Sign Recognition Benchmark dataset. Then, we retrain the network models using transfer learning on the more challenging Belgian Traffic Sign Classification dataset to evaluate test performance. The proposed architecture outperforms the performance of the state-of-the-art traffic sign methods with at least five times less parameter in the individual end-to-end network for training.
•A novel CNN architecture is proposed designed for traffic sign recognition.•The proposed CNN architecture is capable of first training without using GPU.•Overlapping max pooling and sparsely strided convolution used for generalization.•Proposed architecture is capable of beating human level performance.
With the gradual popularization of self-driving, it is becoming increasingly important for vehicles to smartly make the right driving decisions and autonomously obey traffic rules by correctly ...recognizing traffic signs. However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server for model training, which brings serious privacy leakage risk because of traffic sign data containing lots of location privacy information. To address this issue, we first exploit privacy-preserving federated learning to perform collaborative training for accurate recognition models without sharing raw traffic sign data. Nevertheless, due to the limited computing and energy resources of most devices, it is hard for vehicles to continuously undertake complex artificial intelligence tasks. Therefore, we introduce powerful Spike Neural Networks (SNNs) into traffic sign recognition for energy-efficient and fast model training, which is the next generation of neural networks and is practical and well-fitted to IoV scenarios. Furthermore, we design a novel encoding scheme for SNNs based on neuron receptive fields to extract information from the pixel and spatial dimensions of traffic signs to achieve high-accuracy training. Numerical results indicate that the proposed federated SNN outperforms traditional federated convolutional neural networks in terms of accuracy, noise immunity, and energy efficiency as well.
This paper proposes a computationally efficient method for traffic sign recognition (TSR). This proposed method consists of two modules: (1) extraction of histogram of oriented gradient variant ...(HOGv) feature and (2) a single classifier trained by extreme learning machine (ELM) algorithm. The presented HOGv feature keeps a good balance between redundancy and local details such that it can represent distinctive shapes better. The classifier is a single-hidden-layer feedforward network. Based on ELM algorithm, the connection between input and hidden layers realizes the random feature mapping while only the weights between hidden and output layers are trained. As a result, layer-by-layer tuning is not required. Meanwhile, the norm of output weights is included in the cost function. Therefore, the ELM-based classifier can achieve an optimal and generalized solution for multiclass TSR. Furthermore, it can balance the recognition accuracy and computational cost. Three datasets, including the German TSR benchmark dataset, the Belgium traffic sign classification dataset and the revised mapping and assessing the state of traffic infrastructure (revised MASTIF) dataset, are used to evaluate this proposed method. Experimental results have shown that this proposed method obtains not only high recognition accuracy but also extremely high computational efficiency in both training and recognition processes in these three datasets.
Traffic sign recognition (TSR) is an important and challenging task for intelligent transportation systems. We describe the details of our model's architecture for TSR and suggest a hinge loss ...stochastic gradient descent (HLSGD) method to train convolutional neural networks (CNNs). Our CNN consists of three stages (70-110-180) with 1162 284 trainable parameters. The HLSGD is evaluated on the German Traffic Sign Recognition Benchmark, which offers a faster and more stable convergence and a state-of-the-art recognition rate of 99.65%. We write a graphics processing unit package to train several CNNs and establish the final classifier in an ensemble way.
Traffic sign recognition (TSR) has been a rising and lucrative field for researchers during the last decades. The high improvement of ADAS (autonomic driving autonomous system) has led researchers ...worldwide to concentrate on the development of TSR systems. As such, a novel automated multiclass TSR system is proposed. The architecture uses wavelet descriptors to extract the high information density and the traffic signs' edges and curves. The LL band image is directly fed into the classifier to avoid normalization. Three classifiers, CNN, CNN ensemble, and LSTM, are deployed for recognition. The architecture is implemented on IRSDBv1.0, the first available Indian traffic sign database. The architecture is also implemented on the standard traffic sign database GTSRB to investigate its effectiveness. An efficiency of 71.57% and 96.76% are recorded on IRSDBv1.0, and GTSRB, respectively. A list of comparative results is also provided to prove the competence of the architecture. The reasons behind the difference in the achieved accuracy are also discussed.
Adversarial patch is an important form of real-world adversarial attack that brings serious risks to the robustness of deep neural networks. Previous methods generate adversarial patches by either ...optimizing their perturbation values while fixing the pasting position or manipulating the position while fixing the patch's content. This reveals that the positions and perturbations are both important to the adversarial attack. For that, in this article, we propose a novel method to simultaneously optimize the position and perturbation for an adversarial patch, and thus obtain a high attack success rate in the black-box setting. Technically, we regard the patch's position, the pre-designed hyper-parameters to determine the patch's perturbations as the variables, and utilize the reinforcement learning framework to simultaneously solve for the optimal solution based on the rewards obtained from the target model with a small number of queries. Extensive experiments are conducted on the Face Recognition (FR) task, and results on four representative FR models show that our method can significantly improve the attack success rate and query efficiency. Besides, experiments on the commercial FR service and physical environments confirm its practical application value. We also extend our method to the traffic sign recognition task to verify its generalization ability.
Convolutional Neural Networks (CNN) achieves perfection in traffic sign identification with enough annotated training data. The dataset determines the quality of the complete visual system based on ...CNN. Unfortunately, databases for traffic signs from the majority of the world's nations are few. In this scenario, Generative Adversarial Networks (GAN) may be employed to produce more realistic and varied training pictures to supplement the actual arrangement of images. The purpose of this research is to describe how the quality of synthetic pictures created by DCGAN, LSGAN, and WGAN is determined. Our work combines synthetic images with original images to enhance datasets and verify the effectiveness of synthetic datasets. We use different numbers and sizes of images for training. Likewise, the Structural Similarity Index (SSIM) and Mean Square Error (MSE) were employed to assess picture quality. Our study quantifies the SSIM difference between the synthetic and actual images. When additional images are used for training, the synthetic image exhibits a high degree of resemblance to the genuine image. The highest SSIM value was achieved when using 200 total images as input and <inline-formula> <tex-math notation="LaTeX">32\times 32 </tex-math></inline-formula> image size. Further, we augment the original picture dataset with synthetic pictures and compare the original image model to the synthesis image model. For this experiment, we are using the latest iterations of Yolo, Yolo V3, and Yolo V4. After mixing the real image with the synthesized image produced by LSGAN, the recognition performance has been improved, achieving an accuracy of 84.9% on Yolo V3 and an accuracy of 89.33% on Yolo V4.