Indian traffic sign detection and recognition using deep learning

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.

Automatic detection and recognition of traffic sign has been a topic of great interest in advanced driver assistance system. It enhances vehicle and driver safety by providing the condition and state of the road to the drivers. However, visual occlusion and ambiguities in the real-world scenario make the traffic sign recognition a challenging task. This paper presents an Automatic Traffic Sign Detection and Recognition (ATSDR) system, involving three modules: segmentation, detection, and recognition. Region of Interest (ROI) is extracted using multiple thresholding schemes with a novel environmental selection strategy. Then, the traffic sign detection is carried out using correlation computation between log-polar mapped inner regions and the reference template. Finally, recognition is performed using Support Vector Machine (SVM) classifier. Our proposed system achieved a recognition accuracy of 98.3 % and the experimental results demonstrates the robustness of traffic sign detection and recognition in real-world scenario.

A vision-based driver assistance system using image processing technology consists of three main modules: road detection, traffic sign detection/identification, obstacle detection. Traffic Sign Recognition is an upcoming research field under applied Computer Vision and Machine Learning which deals with the automatic detection and classification of traffic signs in traffic scene images. In the current paper, we discuss the methodology used to detect the road sign from a traffic sign scene image and present a technique that can be used to construct a system that recognizes road signs in images. Such a system will ensure that each driver is aware of the rules & hazards on the road & will thus help in improving road safety. Also, the location of the road sign in the traffic sign image is unknown. Once these obstacles are overcome, such a system could be integrated in a Driver Assistance System. The primary objective is to develop an algorithm, which will identify various types of road signs from streaming video of real time road scenes in a reasonable time frame. The algorithm has two main parts: the first one, detection which uses the color and shape information to detect a road sign in a traffic scene picture. The second one, prediction & classification based on Neural Network concept. Our algorithm proposes a variety of MATLAB Image Processing Toolbox commands to determine if a road sign is present in current image. If present, the sign is resized and certain features from the Region of Interest (RoI) are fed as a feature vector to a neural net. This trained Neural Classifier then predicts the class of the road sign. Genetic Algorithms (GA) with built-in intelligence could be incorporated into the current system which will try to look for traffic signs only in environments where there is probability of finding/detecting one.

Automatic traffic sign detection and recognition has achieved good results using convolutional neural networks. Novel architectures are still being proposed in order to improve accuracy of detection and segmentation of traffic sings. In this paper, we are examining the possibility for traffic sign detection and recognition in real-time. For that purpose, we employed a novel YOLOv3 architecture, which has been proven to be fast and accurate method for object detection. It was shown that real-time detection can be achieved, even on HD images, with mAP above 88%.

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

info:eu-repo/semantics/published

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.

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.

Hemorrhages in the retinal fundus are a common symptom of both diabetic retinopathy and diabetic macular edema, making their detection crucial for early diagnosis and treatment. For this task, the aim is to evaluate the performance of two pre-trained and additionally fine-tuned models from the Detectron2 model zoo, Faster R-CNN (R50-FPN) and Mask R-CNN (R50-FPN). Experiments show that the Mask R-CNN (R50-FPN) model provides highly accurate segmentation masks for each detected hemorrhage, with an accuracy of 99.34%. The Faster R-CNN (R50-FPN) model detects hemorrhages with an accuracy of 99.22%. The results of both models are compared using a publicly available image database with ground truth marked by experts. Overall, this study demonstrates that current models are valuable tools for early diagnosis and treatment of diabetic retinopathy and diabetic macular edema.

Traffic Road sign detection and classification is a fundamental technology for building automated driver guidance system with the aid of computer vision technologies. Due to improper and irregular road signage’s the accident are increasing day to day. Many practices are presented for identifying, recognition and classification of traffic signs from daces. To address this acute problem the study is conceded out for the detection and classification of signage’s grounded on arrangement of matching and discriminative feature sets. The feature like LBP, HOG, and LPQ are used to extract the features. The Classification is carried using K-d Tree and KNN machine learning algorithms. The presentation of the anticipated technique is conceded on database which is created in heterogeneous climatic condition for Indian road systems. The tentative outcomes reveal that each feature yields high performance and the feature fusion gives good accompaniment and yielded good classification rate in competent with the prevailing algorithm.

Traffic sign detection plays an important role in a traffic sign recognition system. It is also an unsolved problem in the intelligence transportation system. Two main technique routes are typically used in current research of the traffic sign detection: the technique using gray-level object image or that using color object image. The former has the advantage that the related theories and methods are more mature, but the weakness is short of information, which results in more chances of misdetection. The latter has the advantage that more abundant information can be provided same as human sense of vision, but the weakness is that the related theories and methods are still immaturity. This research proposes a concept of color-shape pair based on the prior characteristic of the color and the geometric shape by analyzing the traffic signs that might appear in Chinese highways. Also, a model of traffic signs, color-geometric model, is given according to the relative definition of the Color-Shape Pair. This model is constituted with 5 kinds of basic shapes and 3 kinds of basic colors of the traffic signs, focusing on the unique determinacy that is the most important characteristics of color and geometric shape. Therefore, using the detection of traffic signs based on color-geometric model, we can realize the rough classification of the traffic signs. Furthermore, we can divide 116 kinds of traffic signs on Chinese road into 7 subclasses, and reduce the complexity of recognition system of road traffic signs. The simulation experiment results have shown that this method can achieve 100% correct ratio for the traffic sign detection and the rough classification, and the robustness and real-time performance are also improved.

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.

Abstract. TSR (Traffic sign recognition) is an important problem in ITS (intelligent traffic system), which is being paid more and more attention for realizing drivers assisting system and unmanned vehicle etc. TSR consists of two steps: detection and recognition, and this paper describe a new traffic sign detection method. The design principle of the traffic sign is comply with the visual attention mechanism of human, so we propose a method using visual attention mechanism to detect traffic sign ,which is reasonable. In our method, the whole scene will firstly be analyzed by visual attention model to acquire the area where traffic signs might be placed. And then, these candidate areas will be analyzed according to the shape characteristics of the traffic sign to detect traffic signs. In traffic sign detection experiments, the result shows the proposed method is effectively and robust than other existing saliency detection method.

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.