Traffic Sign Recognition Using Improved YOLOv7 Model

Traffic sign recognition system is a great important part of intelligent transportation system and advanced auxiliary driving system, and it is a key problem to improve the accuracy and real-time performance of traffic sign detection in reality.Considering to the perspective of accuracy and real-time of traffic sign detection and recognition, this article built the traffic sign detection and recognition method based on MATLAB. Finally, the paper proved the conclusion, and future traffic sign detection and recognition need to be further research topics and practical application prospect.

With the continuous development of driving assistance system and automatic driving technology in recent years, the requirements for traffic sign recognition technology are becoming higher and higher. Although the current mainstream target detection technology has been guaranteed in real-time and accuracy, due to the complexity of traffic signs and the fact that most traffic signs in the actual scene are small and dense, the identification accuracy of small target traffic signs is low. Based on the above situation, an improved YOLOv5 traffic sign recognition algorithm is proposed. We add CBAM attention mechanism to the model to improve the feature extraction ability of the target object. The structure based on the feature pyramid is improved to strengthen the features of small targets. The upsampling algorithm is replaced to save computing power. The overall detection and recognition ability of the model is improved. The loss function is improved to DIoU loss function, which enhances the robustness of the model.

info:eu-repo/semantics/published

To avoid road accidents and for safe driving, a proper traffic sign recognition and classification is necessary. It is also an important part of intelligent transport systems and driverless vehicles. This article outlines the different ways to recognize and classify traffic signs. Various types of algorithms are used to recognize text-based, shape-based and color-based traffic signs. With the development of Artificial Intelligence, deep learning models are becoming more popular. CNN models are used for both detection and classification. Self-driving cars must learn to obey road signs in order to drive safely and smoothly. A transfer learning-based approach to traffic sign recognition and classification is used to reduce data costs. This survey analyses different machine learning and deep learning based methods for traffic sign recognition. The traffic sign recognition and classifications are applicable in intelligent transport system, driving autonomous vehicle, conducting road surveys, improving road safety and infrastructure.

An accident is the cry of a lifetime. The role of traffic signs is most important in preventing or mitigating accidents. In many cases, while driving, traffic signs are not visible in the conventional approach; if traffic sign detection and recognition can alert the driver of important sign guidance ahead, it will help in accident mitigation. Traffic sign recognition plays a monumental role in expert systems, such as traffic assistance driving systems and automatic driving systems. The prime purpose of this paper is to design and identify a computer-based system that can spontaneously detect the direction of a road sign. For this research work, we have created our own dataset, which is called the Bangladeshi Traffic Sign Recognition Benchmark (BTSRB) dataset. The dataset, BTSRB, was created by capturing images from different angles and under different parameters and conditions. A total of 7320 images were collected to create this comprehensive database. This dataset called BTSRB all the images collected from Bangladesh. In this paper, we used five different types of models (CNN, Inception V3, MobileNetV2, ResNet50, and VGG16), which are pre-trained on the ImageNet dataset. Later, we finetuned the pre-trained model and used transfer learning. The main challenge of this research is collecting datasets from a country like Bangladesh, where no recognized dataset is available. When compared to another model, the accuracy of this model is greater than 91%. This paper emphasizes the significance of traffic sign recognition in expert systems and the necessity for a well-established dataset in nations where such resources are not readily available.

In this paper, we propose a traffic sign recognition algorithm based on support vector machine (SVM) and convolutional neural network (CNN) for the traffic sign recognition of intelligent transportation and unmanned vehicle. In the detection of traffic signs, by using color features, firstly we convert the RGB color space to HSV color space, which can get the regions of interest (ROI). Then extract the Histogram of Oriented Gradient (HOG) features, and determine whether it is traffic sign by support vector machine (SVM). This algorithm can successfully detect traffic signs with a high detecting rate. The following is the classification of the detected traffic signs, by using a kind of convolutional neural network, which fuse the RGB information of a picture. In the end, the `German traffic signs' dataset is used to verify the accuracy. Experimental results show that the proposed algorithm can effectively recognize traffic signs, achieving high accuracy and the algorithm complexity is lower.

Worldwide, traffic safety is a strong concern as traffic accidents are one of the leading causes of death. In this context, advanced driver assistance systems (ADAS) and autonomous vehicles are traffic management measures aimed at improving road safety and flow. Automatic detection and recognition of traffic signs are important for intelligent vehicles and ADAS systems. This work proposes a pipeline of digital image processing (DIP) techniques, machine learning (ML), and temporal coherence to perform the detection and recognition of Brazilian traffic signs in videos aiming an application for real-time systems to help in traffic safety and to reduce the number of fatal accidents. We are mainly interested in recognizing signs of speed limit group, no overtaking and obligatory passage, thus our detection considers the traffic sign with a circular shape and red border. For detection, the red color segmentation and the Hough transform are used to find circular regions that will be classified through the SVM algorithm in sign and not sign. For recognition of these signs, the support vector machines (SVM) are used. For speed limit signs the thresholding and contours are used to segment the digits for later classification. Our proposed method achieved an accuracy of 0.82 in detection, an increase of 18% in the number of recognized frames and 0.96 in the recognition stage using temporal coherence.

Locating roadworks sites via detecting change in lateral positions of traffic signs measured relative to the ego-car

Traffic sign recognition is an important step for integrating smart vehicles into existing road transportation systems. In this paper, an NVIDIA Jetson TX1-based traffic sign recognition system is introduced for driver assistance applications. The system incorporates two major operations, traffic sign detection and recognition. Image color and shape based detection is used to locate potential signs in each frame. A pre-trained convolutional neural network performs classification on these potential sign candidates. The proposed system is implemented on NVIDIA Jetson TX1 board with web-camera. Based on a well-known benchmark suite, 96% detection accuracy is achieved while executing at 1.6 frames per seconds.

Shape Classification for Traffic Sign Recognition

In this paper we describe traffic sign recognition with neural networks in the frequency domain. Traffic signs exist in all countries to regulate the traffic of vehicles and pedestrians. Each country has its own set of traffic signs that are more or less similar. They consist of a set of abstract forms, symbols, numbers and letters, which are combined into different signs. Automatic traffic sign recognition is important for driver assistance systems and for autonomous driving. Traffic sign recognition is a subtype of image recognition. The traffic signs are usually recorded by a camera and must be recognized in real time, i.e. assigned to a class. We use neural networks for traffic sign recognition. The special feature of our method is that the traffic sign recognition does not take place in the spatial domain but in the frequency domain. This has advantages because it is possible to significantly reduce the number of neurons and thus the computing effort of the neural network compared to a conventional neural network.

With the notion of smart cities transforming cities into digital societies and making people's lives easier in every way, Intelligent Transportation Systems have become an integral element among all. The Intelligent Transportation System (ITS) attempts to improve traffic efficiency by reducing congestion and ensuring the safety and comfort of commuters in real time. Traffic sign detection and recognition is one of the multifaceted conjunctive fields of research in ITS. In this paper, we address the issue of the TSR (traffic sign recognition) problem, i.e., classification of traffic signs along the roadside which plays a crucial role in developing advanced driver assistance and autonomous driving systems. CNN's network design has a huge impact on its performance and convergence. As a result, we use the Genetic Algorithm (GA) to automate the task of selecting a high-performance CNN (Convolutional Neural Network) Architecture for the GTSRB (German Traffic Sign Recognition Benchmark) dataset. The model is optimized through GA using multiple network configurations in the search space. Our model takes into account the limitations of the dataset, and we use certain data augmentation approaches to address the issues. We were able to attain an average accuracy of 98.2% which demonstrates the state-of-the-art performance on the publicly available dataset.KeywordsConvolutional neural networkGenetic algorithmMulticlass classificationDeep learningModel optimization

Traffic Sign Recognition (TSR) system is a significant component of Intelligent Transport System (ITS) as traffic signs assist the drivers to drive more safely and efficiently. This paper represents a new approach for TSR system where detection of traffic sign is carried out using fuzzy rules based color segmentation method and recognition is accomplished using Speeded Up Robust Features(SURF) descriptor, trained by artificial neural network (ANN) classifier. In the detection step, the region of interest (sign area) is segmented using a set of fuzzy rules depending on the hue and saturation values of each pixel in the HSV color space, post processed to filter unwanted region. Finally the recognition of the traffic sign is implemented using ANN classifier upon the training of SURF features descriptor. The proposed system simulated on offline road scene images captured under different illumination conditions. The detection algorithm shows a high robustness and the recognition rate is quite satisfactory. The performance of the ANN model is illustrated in terms of cross entropy, confusion matrix and receiver operating characteristic (ROC) curves. Also, performances of some classifier such as Support Vector Machine (SVM), Decision Trees, Ensembles Learners (Adaboost) and K-Nearest Neighbor (KNN) classifier are assessed with ANN approach. The simulation results illustrate that recognition using ANN model is higher than classifiers stated above.

To solve the issue of standard traffic sign identification algorithms' poor detection accuracy, an improved YOLOv5 algorithm for traffic sign recognition is proposed. To begin, the YOLOv5 algorithm's backbone network is enhanced, and the original YOLOv5 network's backbone feature extraction network is replaced with the ultra-lightweight convolutional neural network MobileOne. To increase the model's focus on additional locations, the Coordinate Attention module's introduction, it incorporates location information into channel attention and performs multi-scale processing and feature fusion. Experiments demonstrate that the new lightweight network model is only 76% the size of the original YOLOv5 model, and the mAP on the dataset reaches 96.2%. This strategy significantly decreases the amount of model parameters and procedures required to ensure detection accuracy, while also improving detection speed and accuracy.

Made available in DSpace on 2020-12-12T02:40:27Z (GMT). No. of bitstreams: 0\n Previous issue date: 2020-03-01