Search

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the rapid development of intelligent driving and self-driving, how to quickly identify traffic signs in traffic scenes image is an urgent problem that needs to be solved. The existing object detection method can be divided into two categories: the one-staged method, which has a fast detection speed, and the two-stage method, which has higher detection accuracy. How to quickly and accurately detect targets in traffic scenes images is a current research focus. In this paper, an effective detection operator for the region of interest of traffic signs that utilizes the color, shape, and layout characteristics of traffic signs was proposed. It can accurately extract the region of interest in the traffic scene image for detection stage. The existing two-stage network was also fine-tuned to improve the accuracy of traffic sign detection. On the basis of the existing public data set, 13,000 images were collected and annotated to expand the training and test data. These data were used to verify the method proposed in this article. Experiments demonstrated that the proposed method has been improved in detection speed and detection accuracy. [ABSTRACT FROM AUTHOR]

Traffic light and traffic sign detection are important in the field of self-driving. They can guide vehicles to drive safely on the road. It is difficult for existing algorithms of object detection to detect targets simultaneously and achieve high accuracy. In this paper, a dual-model framework is proposed to detect traffic light and signs for a self-driving vehicle based on prior information. This framework can switch the detection model according to the prior information. The color information of the traffic sign is used to extract the ROI and improve the detection efficiency. The work of this paper also includes collecting and annotating a large amount of image data to apply the model trained on the proposed framework to self-driving. The proposed framework is verified on a real road test of a self-driving vehicle. [ABSTRACT FROM AUTHOR]

With the development of driverless technology, we are in dire need of a method to understand traffic scenes. However, it is still a difficult task to detect traffic signs because of the tiny scale of signs in real-world images. In complex scenarios, some traffic signs could be very elusive due to the awful weather and lighting conditions. To implement a more comprehensive detection and recognition system, we develop a two-stage network. At the region proposal stage, we adopt a deep feature pyramid architecture with lateral connections, which makes the semantic feature of small object more sensitive. At the classification stage, densely connected convolutional network is used to strengthen the feature transmission and multiplexed, which leads to more accurate classification with less number of parameters. We test on GTSDB detection benchmark, as well as the challenging Tsinghua-Tencent 100K benchmark which is pretty difficult for most traditional networks. Experiments show that our proposed method achieves a very great performance and surpasses the other state-of-the-art methods. Implementation source code is available at https://github.com/derderking/Traffic-Sign. [ABSTRACT FROM AUTHOR]

The technology for simultaneous localization and mapping (SLAM) has been well investigated with the rising interest in autonomous driving. Visual odometry (VO) is a variation of SLAM without global consistency for estimating the position and orientation of the moving object through analyzing the image sequences captured by associated cameras. However, in the real-world applications, we are inevitably to experience drift error problem in the VO process due to the frame-by-frame pose estimation. The drift can be more severe for monocular VO compared with stereo matching. By jointly refining the camera poses via several local keyframes and the coordinate of 3D map points triangulated from extracted features, bundle adjustment (BA) can mitigate the drift error problem only to some extent. To further improve the performance, we introduce a traffic sign feature-based joint BA module to eliminate and relieve the incrementally accumulated pose errors. The continuously extracted traffic sign feature with standard size and planar information will provide powerful additional constraints for improving the VO estimation accuracy through BA. Our framework can collaborate well with existing VO systems, e.g., ORB-SLAM2, and the traffic sign feature can also be replaced with feature extracted from other size-known planar objects. Experimental results by applying our traffic sign feature-based BA module show an improved vehicular localization accuracy compared with the state-of-the-art baseline VO method. [ABSTRACT FROM AUTHOR]

Copyright of Revista Facultad de Ingeniería - UPTC is the property of Universidad Pedagogica y Tecnologica de Colombia, Facultad de Ingenieria and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Traffic sign detection is one of the key components in autonomous driving. Advanced autonomous vehicles armed with high quality sensors capture high definition images for further analysis. Detecting traffic signs, moving vehicles, and lanes is important for localization and decision making. Traffic signs, especially those that are far from the camera, are small, and so are challenging to traditional object detection methods. In this work, in order to reduce computational cost and improve detection performance, we split the large input images into small blocks and then recognize traffic signs in the blocks using another detection module. Therefore, this paper proposes a three-stage traffic sign detector, which connects a BlockNet with an RPN–RCNN detection network. BlockNet, which is composed of a set of CNN layers, is capable of performing block-level foreground detection, making inferences in less than 1 ms. Then, the RPN–RCNN two-stage detector is used to identify traffic sign objects in each block; it is trained on a derived dataset named TT100KPatch. Experiments show that our framework can achieve both state-of-the-art accuracy and recall; its fastest detection speed is 102 fps. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin University of Science & Technology is the property of Journal of Harbin University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper presents a framework to build a joint 2-D–3-D traffic sign landmark data set for geo-localization using mobile laser scanning (MLS) data. The MLS data include 3-D point clouds and corresponding multi-view images. First, an integrated method, based on a deep learning network and the retro-reflective properties of traffic signs, is developed to accurately extract traffic signs from MLS point clouds. Next, the semantic and spatial properties of the traffic signs (type, location, position, and geometric characteristics) are obtained. Then, a joint 2-D–3-D traffic sign landmark data set is built, and a semantic-spatial organization graph is used to organize the traffic sign data set. Last, based on the traffic sign landmark data set, a geo-localization method for a driving car is proposed to estimate the driving trajectory. It can be used for auxiliary positioning of autonomous vehicles. Experimental results demonstrate the reliability of our proposed method for traffic sign detection and the potential of building 2-D–3-D traffic sign landmark data set for driving trajectory estimation from MLS data. [ABSTRACT FROM AUTHOR]

Due to the growth in human population and number of vehicles, the traffic accidents on highways are drastically increased in both developed and developing countries, in recent years. In traffic accidents, the rate of accidents caused by bad weather has an important place. Among adverse weather conditions, driving under foggy conditions is one of the potentially dangerous activity. However, few studies have been reported the effect of foggy weathers in highway traffic accidents. In recent years, the driver support systems, in which several cameras and sensors are used to warn or help the drivers. In this study, it is suggested to use a real time defogging algorithm to preprocess the camera data before reflected to the driver support system screen. By this way, the traffic accidents occurred under foggy conditions is expected to be reduced. [ABSTRACT FROM AUTHOR]

Effective traffic sign recognition algorithms can assist drivers or automatic driving systems in detecting and recognizing traffic signs in real-time. This paper proposes a multiscale recognition method for traffic signs based on the Gaussian Mixture Model (GMM) and Category Quality Focal Loss (CQFL) to enhance recognition speed and recognition accuracy. Specifically, GMM is utilized to cluster the prior anchors, which are in favor of reducing the clustering error. Meanwhile, considering the most common issue in supervised learning (i.e., the imbalance of data set categories), the category proportion factor is introduced into Quality Focal Loss, which is referred to as CQFL. Furthermore, a five-scale recognition network with a prior anchor allocation strategy is designed for small target objects i.e., traffic sign recognition. Combining five existing tricks, the best speed and accuracy tradeoff on our data set (40.1% mAP and 15 FPS on a single 1080Ti GPU), can be achieved. The experimental results demonstrate that the proposed method is superior to the existing mainstream algorithms, in terms of recognition accuracy and recognition speed.

Traffic sign detection and recognition has been a topic of research for at least the last two decades. Efforts are being made to reliably detect candidate traffic signs in natural uncontrolled environment and to recognize their contents. For detection, a large proportion of relevant literature discusses color based segmentation by either sticking to a predefined color space (e.g., RGB, HSI, YCbCr etc.) or make use of empirically selected subset of eigen space to achieve partially data dependent segmentation. Since, the input RGB data for various color classes and the background is not linearly separable, none of the existing methods guarantee to achieve complete separation among pixels corresponding to traffic signs and the background objects. To tackle this problem, we propose a completely data driven segmentation technique that adaptively selects an optimized color space based on available training data. To recognize the contents of potential traffic signs, we present a hybrid spatio-frequency radial feature extraction technique with an emphasis on the regions containing useful information. We explore the energy compaction property of steerable discrete cosine transform for feature extraction and augment it with well known circular histogram of oriented gradients in a pyramid. Using our proposed method, experiments on (1) German Traffic Sign Detection Benchmark, (2) our self collected dataset and on a (3) hand crafted version of the combination of the two provide competitive performance compared to various latest and state of the art methods by achieving up to 0.978 precision and 0.98 recall values at an expense of only an insignificant additional computational cost. The method also obtained 0.81 precision on traffic signs partially occluded by other objects. [ABSTRACT FROM AUTHOR]

Road traffic sign recognition is an important task in intelligent transportation system. Convolutional neural networks (CNNs) have achieved a breakthrough in computer vision tasks and made great success in traffic sign classification. In this paper, it presents a road traffic sign recognition algorithm based on a convolutional neural network. In natural scenes, traffic signs are disturbed by factors such as illumination, occlusion, missing and deformation, and the accuracy of recognition decreases, this paper proposes a model called Improved VGG (IVGG) inspired by VGG model. The IVGG model includes 9 layers, compared with the original VGG model, it is added max-pooling operation and dropout operation after multiple convolutional layers, to catch the main features and save the training time. The paper proposes the method which adds dropout and Batch Normalization (BN) operations after each fully-connected layer, to further accelerate the model convergence, and then it can get better classification effect. It uses the German Traffic Sign Recognition Benchmark (GTSRB) dataset in the experiment. The IVGG model enhances the recognition rate of traffic signs and robustness by using the data augmentation and transfer learning, and the spent time is also reduced greatly. [ABSTRACT FROM AUTHOR]

Highlights • The interactions between accident severity levels and traffic signs are identified in state roads. • A seemingly unrelated regression (SUR) model in unbalanced panel data approach is proposed. • The seemingly. unrelated regression model addresses the correlation of residuals between different accident severity levels, and the panel data model accommodates the heterogeneity attributed to unobserved factors. • By comparing the pooled, fixed-effects and random-effects SUR models, the random-effects SUR model shows priority to the other two. • The results reveal that different traffic signs cause different accident severity levels, which benefits the policy makers and roadway management departments. Abstract This study intended to investigate the interactions between accident severity levels and traffic signs in state roads located in Croatia, and explore the correlation within accident severity levels and heterogeneity attributed to unobserved factors. The data from 410 state roads between 2012 and 2016 were collected from Traffic Accident Database System maintained by the Republic of Croatia Ministry of the Interior. To address the correlation and heterogeneity, a seemingly unrelated regression (SUR) model in unbalanced panel data approach was proposed, in which the seemingly unrelated model addressed the correlation of residuals, while the panel data model accommodated the heterogeneity due to unobserved factors. By comparing the pooled, fixed-effects and random-effects SUR models, the random-effects SUR model showed priority to the other two. Results revealed that (1) low visibility and the number of invalid traffic signs per km increased the accident rate of material damage, death or injured; (2) average speed limit exhibited a high accident rate of death or injured; (3) the number of mandatory signs was more likely to reduce the accident rate of material damage, while the number of warning signs was significant for accident rate of death or injured. [ABSTRACT FROM AUTHOR]

Introduction Drivers' ability to comprehend the meaning of traffic signs is essential to safe driving. Drivers' personal characteristics are believed to play a crucial role in determining drivers' comprehension of traffic signs. Method This study investigates the role of age, gender, marital status, license category, educational level, driving experience, monthly income, and number of traffic violation during the last five years in drivers' comprehension of 39 posted traffic signs in the city of Irbid, Jordan. These signs include 15 regulatory signs, 17 warning signs, and 7 guidance signs. A total of 400 paper-based surveys were completed by drivers with different socio-economic characteristics. Subsequently, a decision tree was created for each category of traffic signs to identify the most influential factors affecting drivers' comprehension. Each tree was created twice; once using the whole data set for building and validating the tree, and a second time only using 80% of the data for building and 20% for validating. Results The accuracy of the generated trees in predicting drivers' comprehension of regulatory, guidance, and warning traffic signs was 70%, 71%, and 66.5%, respectively, when using the whole data for building and validating the tree, and was 65%, 62.5%, and 61.3%, respectively, when using only 80% of the data for building and the remaining for validating. Conclusions The generated decision trees showed that driving experience, marital status, age, and education background are the most influential factors in determining drivers' comprehension of traffic signs as they were primary splitters in such trees. Practical application The rules obtained from the decision tree can be utilized by transportation agencies to determine the drivers who need help with understanding the road traffic signs. [ABSTRACT FROM AUTHOR]

Road signs do not necessarily lead to the right response. Especially when signs are changed, drivers may not always detect new signs and may therefore fail to respond correctly to the situation indicated. The present driving simulator study investigated whether road familiarity (increased exposure to the same road) influenced failure to respond to a change in road signs. In order to study the failure to respond, participants were presented with a change in the road lay-out (as indicated by a road sign) in the last of a series of simulated drives. The change introduced was the conversion of a normal road into a No-Entry road. Results show that several participants failed to respond to this change. However, the failure to respond was not simply the result of familiarity with the road or prior exposure to precisely the same road, but seemed to be influenced by expectations induced by the road design. Additional safety measures such as the placement of additional road signs reduced the failure to respond. An auditory in-vehicle message gave the best results. Interestingly, both in the case of additional signs and of the in-vehicle message, a general warning was sufficient, without the need to specify the precise traffic situation. [ABSTRACT FROM AUTHOR]

Highway traffic control signs are commonly used to regulate, warn, and guide road users. It is widely believed that traffic signs comprehension has a tremendous effect on traffic safety. The primary objective of this research is to investigate the relationship between drivers’ personal characteristics and their familiarity/comprehensibility with a thirty nine posted traffic signs. To this end, 400 surveys were distributed among Jordanian drivers. The results showed that the familiarity level of traffic signs is higher than comprehensibility level. On average 79%, 77%, and 83% of the drivers were familiar with regulatory, warning, and guidance traffic signs, respectively. On the other hand, only 61%, 66%, and 75% of the drivers comprehended regulatory, warning, and guidance traffic signs, respectively. “Narrow Bridge”, “Divided Roadway a Head”, “Dead End” and “Highway” received the lowest comprehensibility scores among drivers. Participants with commercial driving license had higher familiarity and comprehensibility levels than those with regular license. Drivers with a driving experience more than 11years show more familiarity and comprehensibility for traffic signs than those with less than 2 years driving experience. The number of traffic violations did not have a significant effect on traffic signs familiarity and comprehensibility. [ABSTRACT FROM AUTHOR]

Copyright of Ingenius, Revista Ciencia y Tecnología is the property of Universidad Politecnica Salesiana and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

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. [ABSTRACT FROM AUTHOR]

Traffic sign detection and recognition systems provide an additional level of driver assistance, leading to improved safety for passengers, road users and vehicles. The automatic road-signs recognition is an important part of driver assisting systems which helps driver to increase safety and driving comfort. In this paper we proposed an efficient system for the detection and recognition of the road sign in the road and acquiring the traffic scene images from a fixed source.The road sign recognition system is divided into two parts, the first part is detection stage which is used to detect the signs from a whole image by using the shape filtering method, and the second part is the recognition stage where the traffic sign obtained is analyzed then the names and directions of cities are extracted using the artificial neural network (ANN).The system accuracy more than 90%. [ABSTRACT FROM AUTHOR]