German Traffic Sign Recognition Benchmark Research Articles

Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods

This paper presents a Deep Learning approach for traffic sign recognition systems. Several classification experiments are conducted over publicly available traffic sign datasets from Germany and Belgium using a Deep Neural Network which comprises Convolutional layers and Spatial Transformer Networks. Such trials are built to measure the impact of diverse factors with the end goal of designing a Convolutional Neural Network that can improve the state-of-the-art of traffic sign classification task. First, different adaptive and non-adaptive stochastic gradient descent optimisation algorithms such as SGD, SGD-Nesterov, RMSprop and Adam are evaluated. Subsequently, multiple combinations of Spatial Transformer Networks placed at distinct positions within the main neural network are analysed. The recognition rate of the proposed Convolutional Neural Network reports an accuracy of 99.71% in the German Traffic Sign Recognition Benchmark, outperforming previous state-of-the-art methods and also being more efficient in terms of memory requirements.

MicronNet: A Highly Compact Deep Convolutional Neural Network Architecture for Real-Time Embedded Traffic Sign Classification

Traffic sign recognition is a very important computer vision task for a number of real-world applications such as intelligent transportation surveillance and analysis. While deep neural networks have been demonstrated in recent years to provide the state-of-the-art performance traffic sign recognition, a key challenge for enabling the widespread deployment of deep neural networks for embedded traffic sign recognition is the high computational and memory requirements of such networks. As a consequence, there are significant benefits in investigating compact deep neural network architectures for traffic sign recognition that are better suited for embedded devices. In this paper, we introduce MicronNet, a highly compact deep convolutional neural network for real-time embedded traffic sign recognition designed based on macroarchitecture design principles (e.g., spectral macroarchitecture augmentation, parameter precision optimization, etc.) as well as numerical microarchitecture optimization strategies. The resulting overall architecture of MicronNet is thus designed with as few parameters and computations as possible while maintaining recognition performance, leading to optimized information density of the proposed network. The resulting MicronNet possesses a model size of just ~1 MB and ~5 10 000 parameters ( $\sim 27\times $ fewer parameters than state-of-the-art) while still achieving a human performance level top-1 accuracy of 98.9% on the German traffic sign recognition benchmark. Furthermore, the MicronNet requires just ~10 million multiply-accumulate operations to perform inference, and has a time-to-compute of just 32.19 ms on a Cortex-A53 high efficiency processor. These experimental results show that the highly compact, optimized deep neural network architectures can be designed for real-time traffic sign recognition that are well-suited for embedded scenarios.

Traffic Sign Recognition Based On Multi-feature Fusion and ELM Classifier

This paper proposes a novel and efficient method for traffic sign recognition based on combination of complementary and discriminative feature sets. The extracted features are the histogram of oriented gradients (HOG) feature, Gabor feature and Compound local binary pattern (CLBP) feature. The classification is performed using the extreme learning machine (ELM) algorithm. Performances of the proposed approach are evaluated on both German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign Classification (BTSC) Datasets respectively. The results of the experimental work demonstrate that each feature yields fairly high accuracy and the combination of three features has shown good complementariness and yielded fast recognition rate and is more adequate for real-time application as well.

Traffic sign recognition based on deep convolutional neural network

Traffic sign recognition (TSR) is an important component of automated driving system. It is a rather challenging task to design a high-performance classifier for the TSR system. In this paper, we proposed a new method for TSR system based on deep convolutional neural network. In order to enhance the expression of the network, a novel structure (dubbed block-layer below) which combines Network-in-Network and residual connection was designed. Our network has 10 layers with parameters (block-layer be seen as a single layer); the first seven are alternate convolutional layers and block-layers, and the remaining three are fully-connected layers. We trained our TSR network on the German Traffic Sign Recognition Benchmark (GTSRB) dataset. To reduce overfitting, we did data augmentation on the training images and employed a regularization method named dropout. We also employed a mechanism called Batch Normalization which has been proved to be efficient for accelerating the training of deep neural networks. To speed up the training, we used an efficient GPU to accelerate the convolutional operation. On the test dataset of GTSRB, we achieve the accuracy rate of 98.96%, exceeding the human average raters.

An efficient traffic sign recognition based on graph embedding features

Traffic sign recognition (TSR) is one of the significant modules of an intelligent transportation system. It instantly assists the drivers to efficiently recognize the traffic sign. Recognition of traffic sign is a large-scale feature learning problem with different real-world appearances. The main goal of this paper is to develop an efficient TSR method, which can run on an ordinary personal computer (PC). In the proposed method, GIST descriptors of the traffic sign images are extracted and subjected to graph-based linear discriminant analysis to reduce the dimension. Moreover, it effectively learns the discriminative subspace through the graph structure with increased computational efficiency. An efficient TSR module is built by conducting series of experiments using support vector machine, extreme learning machine, and k-nearest neighbor (k-NN) classifiers on available public datasets. Our approach achieved the highest recognition accuracy of 96.33 and 97.79% using k-NN classifier for German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign Classification Benchmark (BelgiumTSC), respectively. Also it achieved 99.1% accuracy for a subcategory of GTSRB traffic signs and able to predict the class of unknown traffic sign within 0.0019 s on an ordinary PC. Hence, it can be used in real-world driver assistance system.

A Shallow Network with Combined Pooling for Fast Traffic Sign Recognition

Traffic sign recognition plays an important role in intelligent transportation systems. Motivated by the recent success of deep learning in the application of traffic sign recognition, we present a shallow network architecture based on convolutional neural networks (CNNs). The network consists of only three convolutional layers for feature extraction, and it learns in a backward optimization way. We propose the method of combining different pooling operations to improve sign recognition performance. In view of real-time performance, we use the activation function ReLU to improve computational efficiency. In addition, a linear layer with softmax-loss is taken as the classifier. We use the German traffic sign recognition benchmark (GTSRB) to evaluate the network on CPU, without expensive GPU acceleration hardware, under real-world recognition conditions. The experiment results indicate that the proposed method is effective and fast, and it achieves the highest recognition rate compared with other state-of-the-art algorithms.

Artificial Bee Colony Optimization for Feature Selection of Traffic Sign Recognition

This paper proposes the application of a swarm intelligence algorithm called Artificial Bee Colony (ABC) for the feature selection to feed a Random Forest (RF) classifier aiming to recognise Traffic Signs. In this paper, the authors define and assess several fitness functions for the feature selection stage. The idea is to minimise the correlation and maximise the entropy of a set of masks to be used for feature extraction results in a higher information gain and allows to reach recognition accuracies comparable with other state-of-art algorithms. The RF comprises as a committee based on decision trees, which allows handling large datasets and features with high performance, enabling a Traffic Sign Recognition (TSR) system oriented for real-time implementations. The German Traffic Sign Recognition Benchmark (GTSRB) was used for experiments, serving as a real basis for comparison of performance for the authors' proposal.

Local texture patterns for traffic sign recognition using higher order spectra

Traffic sign recognition (TSR) is considered as one of the most important modules of driver assistance system (DAS). It can be used as a decision supporting tool for driver and autonomous vehicles. Eventually, TSR is a large-scale feature learning problem and hence attracted the attention of researchers recently. The essential parameters such as huge training dataset size, recognition accuracy and computational complexity need to be considered while designing a practical TSR system. In this paper, we have used higher order spectra (HOS) coupled with texture based features to develop an efficient TSR model. These features represent the shape and content of the traffic signs clearly. Then a subspace learning method with graph embedding under linear discriminant analysis framework is used to increase the discrimination power between various traffic symbols. As a result the proposed method attained a maximum recognition accuracy of 98.89%. The proposed method is evaluated using two publicly available datasets such as, Belgium traffic sign classification (BTSC) and German traffic sign recognition benchmark (GTSRB). Our experimental results demonstrate that the proposed approach is computationally efficient and shows promising recognition accuracy.

Traffic sign recognition based on color, shape, and pictogram classification using support vector machines

Traffic sign recognition is the second part of traffic sign detection and recognition systems. It plays a crucial role in driver assistance systems and provides drivers with crucial safety and precaution information. In this study, the recognition of the TS is performed based on its border color, shape, and pictogram information. This technique breaks down the recognition system into small parts, which makes it efficient and accurate. Moreover, this makes it easy to understand TS components. The proposed technique is composed of three independent stages. The first stage involves extracting the border colors using an adaptive image segmentation technique that is based on learning vector quantization. Then, the shape of the TS is detected using a fast and simple matching technique based on the logical exclusive OR operator. Finally, the pictogram is extracted and classified using a support vector machines classifier model. The proposed technique is applied on the German traffic sign recognition benchmark and achieves an overall recognition rate of 98.23%, with an average computational speed of 30 ms.

A new sparse model for traffic sign classification using soft histogram of oriented gradients

Traffic sign recognition (TSR) is an integrated part of driver assistance systems and it remains an active research topic in computer vision today. This paper proposes a solution for TSR problem which composed of robust traffic sign image descriptor and sparse classifiers. Specifically, we outline a variant of histogram of oriented gradients (HOG), namely Soft HOG (SHOG) which exploits the symmetry shape of traffic sign images to find the optimal locations of the cell of histogram for SHOG computation. We show that our compact SHOG feature is more discriminative than HOG. Furthermore, two sparse analytical polynomial based classifiers, namely Sparse Bayesian Multivariate polynomial model and Sparse Bayesian Reduced polynomial model are introduced. The proposed sparse classifiers enable implicit feature selection and alleviate the overfitting problem. This leads to higher accuracy performance with prudent set of features. Our solution is evaluated on publicly available German Traffic Sign Recognition Benchmark (GTSRB) dataset and 16 datasets from (UCI) repository. Experiment results demonstrated that the proposed method has satisfactory result when compared to state-of-the-art methods.

Traffic sign recognition based on weighted ELM and AdaBoost

A novel multiclass AdaBoost-based extreme learning machine (ELM) ensemble algorithm is proposed, in which the weighted ELM is selected as the basic weak classifier because of its much faster learning speed and much better generalisation performance than traditional support vector machines. AdaBoost acts as an ensemble learning method of a number of weighted ELMs. Then, an ensemble strong classifier is constructed by the weighted majority vote of all the weighted ELMs. Compared with the existing ELM methods, the proposed algorithm solves the problem of how to train the weighted samples by ELM in multiclass classification directly. Experiments on the German Traffic Sign Recognition Benchmark database demonstrate that the proposed algorithm can achieve a high recognition accuracy of 99.12% with a relatively lower computational complexity than many state-of-the-art algorithms.

Traffic sign detection and recognition based on random forests

In this paper we present a new traffic sign detection and recognition (TSDR) method, which is achieved in three main steps. The first step segments the image based on thresholding of HSI color space components. The second step detects traffic signs by processing the blobs extracted by the first step. The last one performs the recognition of the detected traffic signs. The main contributions of the paper are as follows. First, we propose, in the second step, to use invariant geometric moments to classify shapes instead of machine learning algorithms. Second, inspired by the existing features, new ones have been proposed for the recognition. The histogram of oriented gradients (HOG) features has been extended to the HSI color space and combined with the local self-similarity (LSS) features to get the descriptor we use in our algorithm. As a classifier, random forest and support vector machine (SVM) classifiers have been tested together with the new descriptor. The proposed method has been tested on both the German Traffic Sign Detection and Recognition Benchmark and the Swedish Traffic Signs Data sets. The results obtained are satisfactory when compared to the state-of-the-art methods.

Traffic Sign Recognition Using Kernel Extreme Learning Machines With Deep Perceptual Features

Traffic sign recognition plays an important role in autonomous vehicles as well as advanced driver assistance systems. Although various methods have been developed, it is still difficult for the state-of-the-art algorithms to obtain high recognition precision with low computational costs. In this paper, based on the investigation on the influence that color spaces have on the representation learning of convolutional neural network, a novel traffic sign recognition approach called DP-KELM is proposed by using a kernel-based extreme learning machine (KELM) classifier with deep perceptual features. Unlike the previous approaches, the representation learning process in DP-KELM is implemented in the perceptual Lab color space. Based on the learned deep perceptual feature, a kernel-based ELM classifier is trained with high computational efficiency and generalization performance. Through the experiments on the German traffic sign recognition benchmark, the proposed method is demonstrated to have higher precision than most of the state-of-the-art approaches. In particular, when compared with the hinge loss stochastic gradient descent method which has the highest precision, the proposed method can achieve a comparable recognition rate with significantly fewer computational costs.

On circular traffic sign detection and recognition

Automatic traffic sign detection and recognition play crucial roles in several expert systems such as driver assistance and autonomous driving systems. In this work, novel approaches for circular traffic sign detection and recognition on color images are proposed. In traffic sign detection, a new approach, which utilizes a recently developed circle detection algorithm and an RGB-based color thresholding technique, is proposed. In traffic sign recognition, an ensemble of features including histogram of oriented gradients, local binary patterns and Gabor features are employed within a support vector machine classification framework. Performances of the proposed detection and recognition approaches are evaluated on German Traffic Sign Detection and Recognition Benchmark datasets, respectively. The results of the experimental work reveal that both approaches offer comparable or even better performances with respect to the best ones reported in the literature and are compatible to real-time operation as well.

랜덤 포레스트 분류기 기반의 컨벌루션 뉴럴 네트워크를 이용한 속도제한 표지판 인식

= >?@ABCD>!.AEFG,HI!J >KLMGNOPQR>S:.TG /0 .1 234UVWX+ Y.Z. /0 .1 234[\]?^_`a34 b>?cd.ef[gh6:i@jCNN (Convolutional neural network)[k-.Z. l m n!CNN5opqr[\]Zs!5tu,k-v:qrwxy>N]MLP(Multi-layer perceptron) Ry!z{|x(fully-connected) 4 [k-}~€ y U‚,ƒ,„ @†‡,iZ. = >?@,ˆ.†‡[‰, \]2Xu!CNN[Šel:`a +\] (Random forest)+x‹lhz{|x,Œ|x4 [Ž-lZ. GTSRB(German Traffic Sign Recognition Benchmark),‘!’“Y{1 2”>?8•/0 .1 2,‘+k-lh Yl@4 ,SVM (Support Vector Machine),HMLP +Ž-–—gZef,˜s}[™šlZ. AbstractIn this paper, we propose a robust speed-limit sign recognition system which is durable to any sign changes caused by exterior damage or color contrast due to light direction. For recognition of speed-limit sign, we apply CNN which is showing an outstanding performance in pattern recognition field. However, original CNN uses multiple hidden layers to extract features and uses fully-connected method with MLP(Multi-layer perceptron) on the result. Therefore, the major demerit of conventional CNN is to require a long time for training and testing. In this paper, we apply randomly-connected classifier instead of fully-connected classifier by combining random forest with output of 2 layers of CNN. We prove that the recognition results of CNN with random forest show best performance than recognition results of CNN with SVM (Support Vector Machine) or MLP classifier when we use eight speed-limit signs of GTSRB (German Traffic Sign Recognition Benchmark).Keyword : Convolutional Neural Network, Random forest, speed-limit sign recognition , feature extraction, ADAS

Evolutionary feature and instance selection for traffic sign recognition

The problem of traffic sign recognition is generally approached by first constructing a classifier, which is trained by some relevant image features extracted from traffic signs, to recognize new unknown traffic signs. Feature selection and instance selection are two important data preprocessing steps in data mining, with the former aimed at removing some irrelevant and/or redundant features from a given dataset and the latter at discarding the faulty data. However, there has thus far been no study examining the impact of performing feature and instance selection on traffic sign recognition performance. Given that genetic algorithms (GA) have been widely used for these types of data preprocessing tasks in related studies, we introduce a novel genetic-based biological algorithm (GBA). GBA fits “biological evolution” into the evolutionary process, where the most streamlined process also complies with reasonable rules. In other words, after long-term evolution, organisms find the most efficient way to allocate resources and evolve. Similarly, we closely simulate the natural evolution of an algorithm, to find an option it will be both efficient and effective. Experiments are carried out comparing the performance of the GBA and a GA based on the German Traffic Sign Recognition Benchmark. The results show that the GBA outperforms the GA in terms of the reduction rate, classification accuracy, and computational cost.

Traffic Sign Recognition With Hinge Loss Trained Convolutional Neural Networks

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 using group sparse coding

Recognizing traffic signs is a challenging problem; and it has captured the attention of the computer vision community for several decades. Essentially, traffic sign recognition is a multi-class classification problem that has become a real challenge for computer vision and machine learning techniques. Although many machine learning approaches are used for traffic sign recognition, they are primarily used for classification, not feature design. Identifying rich features using modern machine learning methods has recently attracted attention and has achieved success in many benchmarks. However these approaches have not been fully implemented in the traffic sign recognition problem. In this paper, we propose a new approach to tackle the traffic sign recognition problem. First, we introduce a new feature learning approach using group sparse coding. The primary goal is to exploit the intrinsic structure of the pre-learned visual codebook. This new coding strategy preserves locality and encourages similar descriptors to share similar sparse representation patterns. Second, we use a non-uniform quantization approach based on log-polar mapping. Using the log-polar mapping of the traffic sign image, rotated and scaled patterns are converted into shifted patterns in the new space. We extract the local descriptors from these patterns to learn the features. Finally, by evaluating the proposed approach using the German Traffic Sign Recognition Benchmark dataset, we show that the proposed coding strategy outperforms existing coding methods and the obtained results are comparable to the state-of-the-art.

Application of BW-ELM model on traffic sign recognition

Traffic sign recognition is an important and active research topic of intelligent transport system. With a constant increasing of the training database size, not only the recognition accuracy, but also the computation complexity should be considered in designing a feasible recognition approach. In this paper, an effective and efficient algorithm based on a relatively new artificial neural network, extreme learning machine (ELM), is proposed for traffic sign recognition. In the proposed algorithm, the locally normalized histograms of the oriented gradient (HOG) descriptors, which are extracted from the traffic sign images, are used as the features and the inputs of the ELM classification model. Moreover, the ratio of feature's between-category to within-category sums of squares (BW) is designed as a feature selection criterion to improve the recognition accuracy and to decrease the computation burden. Application on a well known database, German traffic sign recognition benchmark (GTSRB) dataset, demonstrates the feasibility and efficiency of the proposed BW-ELM model.

C-HMAX: Artificial cognitive model inspired by the color vision mechanism of the human brain

Artificial cognitive models and computational neuroscience methods have garnered great interest from both neurologist and leading analysts in recent years. Among the cognitive models, HMAX has been widely used in computer vision systems for its robustness shape and texture features inspired by the ventral stream of the human brain. This work presents a Color-HMAX (C-HMAX) model based on the HMAX model which imitates the color vision mechanism of the human brain that the HMAX model does not include. C-HMAX is then applied to the German Traffic Sign Recognition Benchmark (GTSRB) which has 43 categories and 51 840 sample traffic signs with an accuracy of 98.41%, higher than most other models including linear discriminant analysis and multi-scale convolutional neural network.