Showing papers in "IEEE Transactions on Intelligent Transportation Systems in 2018"
TL;DR: A deep architecture that is able to run in real time while providing accurate semantic segmentation, and a novel layer that uses residual connections and factorized convolutions in order to remain efficient while retaining remarkable accuracy is proposed.
Abstract: Semantic segmentation is a challenging task that addresses most of the perception needs of intelligent vehicles (IVs) in an unified way. Deep neural networks excel at this task, as they can be trained end-to-end to accurately classify multiple object categories in an image at pixel level. However, a good tradeoff between high quality and computational resources is yet not present in the state-of-the-art semantic segmentation approaches, limiting their application in real vehicles. In this paper, we propose a deep architecture that is able to run in real time while providing accurate semantic segmentation. The core of our architecture is a novel layer that uses residual connections and factorized convolutions in order to remain efficient while retaining remarkable accuracy. Our approach is able to run at over 83 FPS in a single Titan X, and 7 FPS in a Jetson TX1 (embedded device). A comprehensive set of experiments on the publicly available Cityscapes data set demonstrates that our system achieves an accuracy that is similar to the state of the art, while being orders of magnitude faster to compute than other architectures that achieve top precision. The resulting tradeoff makes our model an ideal approach for scene understanding in IV applications. The code is publicly available at: https://github.com/Eromera/erfnet
1,134 citations
TL;DR: A survey on driving style characterization and recognition revising a variety of algorithms, with particular emphasis on machine learning approaches based on current and future trends is provided.
Abstract: Driver driving style plays an important role in vehicle energy management as well as driving safety. Furthermore, it is key for advance driver assistance systems development, toward increasing levels of vehicle automation. This fact has motivated numerous research and development efforts on driving style identification and classification. This paper provides a survey on driving style characterization and recognition revising a variety of algorithms, with particular emphasis on machine learning approaches based on current and future trends. Applications of driving style recognition to intelligent vehicle controls are also briefly discussed, including experts’ predictions of the future development.
442 citations
TL;DR: This paper proposes an effective announcement network called CreditCoin, a novel privacy-preserving incentive announcement network based on Blockchain via an efficient anonymous vehicular announcement aggregation protocol, and shows that CreditCoin is efficient and practical in simulations of smart transportation.
Abstract: The vehicular announcement network is one of the most promising utilities in the communications of smart vehicles and in the smart transportation systems. In general, there are two major issues in building an effective vehicular announcement network. First, it is difficult to forward reliable announcements without revealing users’ identities. Second, users usually lack the motivation to forward announcements. In this paper, we endeavor to resolve these two issues through proposing an effective announcement network called CreditCoin , a novel privacy-preserving incentive announcement network based on Blockchain via an efficient anonymous vehicular announcement aggregation protocol. On the one hand, CreditCoin allows nondeterministic different signers (i.e., users) to generate the signatures and to send announcements anonymously in the nonfully trusted environment. On the other hand, with Blockchain, CreditCoin motivates users with incentives to share traffic information. In addition, transactions and account information in CreditCoin are tamper-resistant. CreditCoin also achieves conditional privacy since Trace manager in CreditCoin traces malicious users’ identities in anonymous announcements with related transactions. CreditCoin thus is able to motivate users to forward announcements anonymously and reliably. Extensive experimental results show that CreditCoin is efficient and practical in simulations of smart transportation.
441 citations
TL;DR: This paper summarizes the state of the art in connected vehicles—from the need for vehicle data and applications thereof, to enabling technologies, challenges, and identified opportunities—from extensibility and scalability to privacy and security.
Abstract: This paper summarizes the state of the art in connected vehicles—from the need for vehicle data and applications thereof, to enabling technologies, challenges, and identified opportunities. Connectivity is increasing around the world and its expansion to vehicles is no exception. With improvements in connectivity, sensing, and computation, the future will see vehicles used as development platforms capable of generating rich data, acting based on inference, and effecting great change in transportation, the human-vehicle dynamic, the environment, and the economy. Connected vehicle technologies have already been used to improve fleet safety and efficiency, with emerging technologies additionally allowing data to be used to inform aspects of vehicle design, ownership, and use. While the demand for connected vehicles and its enabling technology has progressed significantly in recent years, there remain challenges to connected and collaborative vehicle application deployment before the full potential of connected cars may be realized. From extensibility and scalability to privacy and security, this paper informs the reader about key enabling technologies, opportunities, and challenges in the connected vehicle landscape.
305 citations
TL;DR: An overview of the past and current literature discussing the GNSS integrity for urban transport applications is provided so as to point out possible challenges faced by GNSS receivers in such scenario.
Abstract: Integrity is one criteria to evaluate GNSS performance, which was first introduced in the aviation field. It is a measure of trust which can be placed in the correctness of the information supplied by the total system. In recent years, many GNSS-based applications emerge in the urban environment including liability critical ones, so the concept of integrity attracts more and more attention from urban GNSS users. However, the algorithms developed for the aerospace domain cannot be introduced directly to the GNSS land applications. This is because a high data redundancy exists in the aviation domain and the hypothesis that only one failure occurs at a time is made, which is not the case for the urban users. The main objective of this paper is to provide an overview of the past and current literature discussing the GNSS integrity for urban transport applications so as to point out possible challenges faced by GNSS receivers in such scenario. Key differences between integrity monitoring scheme in aviation domain and urban transport field are addressed. And this paper also points out several open research issues in this field.
265 citations
TL;DR: AIS data sources and relevant aspects of navigation in which such data are or could be exploited for safety of seafaring are surveyed, namely traffic anomaly detection, route estimation, collision prediction, and path planning.
Abstract: The automatic identification system (AIS) tracks vessel movement by means of electronic exchange of navigation data between vessels, with onboard transceiver, terrestrial, and/or satellite base stations. The gathered data contain a wealth of information useful for maritime safety, security, and efficiency. Because of the close relationship between data and methodology in marine data mining and the importance of both of them in marine intelligence research, this paper surveys AIS data sources and relevant aspects of navigation in which such data are or could be exploited for safety of seafaring, namely traffic anomaly detection, route estimation, collision prediction, and path planning.
264 citations
TL;DR: A one-stage supervised deep hashing framework (SDHP) is proposed to learn high-quality binary codes, and a deep convolutional neural network is implemented to enforce the learned codes to meet the following criterions.
Abstract: Image content analysis is an important surround perception modality of intelligent vehicles. In order to efficiently recognize the on-road environment based on image content analysis from the large-scale scene database, relevant images retrieval becomes one of the fundamental problems. To improve the efficiency of calculating similarities between images, hashing techniques have received increasing attentions. For most existing hash methods, the suboptimal binary codes are generated, as the hand-crafted feature representation is not optimally compatible with the binary codes. In this paper, a one-stage supervised deep hashing framework (SDHP) is proposed to learn high-quality binary codes. A deep convolutional neural network is implemented, and we enforce the learned codes to meet the following criterions: 1) similar images should be encoded into similar binary codes, and vice versa; 2) the quantization loss from Euclidean space to Hamming space should be minimized; and 3) the learned codes should be evenly distributed. The method is further extended into SDHP+ to improve the discriminative power of binary codes. Extensive experimental comparisons with state-of-the-art hashing algorithms are conducted on CIFAR-10 and NUS-WIDE, the MAP of SDHP reaches to 87.67% and 77.48% with 48 b, respectively, and the MAP of SDHP+ reaches to 91.16%, 81.08% with 12 b, 48 b on CIFAR-10 and NUS-WIDE, respectively. It illustrates that the proposed method can obviously improve the search accuracy.
239 citations
TL;DR: This paper proposes a sequence learning model that can predict future taxi requests in each area of a city based on the recent demand and other relevant information, and shows that this approach outperforms other prediction methods, such as feed-forward neural networks.
Abstract: Predicting taxi demand throughout a city can help to organize the taxi fleet and minimize the wait-time for passengers and drivers. In this paper, we propose a sequence learning model that can predict future taxi requests in each area of a city based on the recent demand and other relevant information. Remembering information from the past is critical here, since taxi requests in the future are correlated with information about actions that happened in the past. For example, someone who requests a taxi to a shopping center, may also request a taxi to return home after few hours. We use one of the best sequence learning methods, long short term memory that has a gating mechanism to store the relevant information for future use. We evaluate our method on a data set of taxi requests in New York City by dividing the city into small areas and predicting the demand in each area. We show that this approach outperforms other prediction methods, such as feed-forward neural networks. In addition, we show how adding other relevant information, such as weather, time, and drop-offs affects the results.
234 citations
TL;DR: A wide range of visual perception tasks including the object detection, drivable region detection, localization, image enhancement, depth estimation, and colorization are designed using a single/multi-spectral approach.
Abstract: We introduce the KAIST multi-spectral data set, which covers a great range of drivable regions, from urban to residential, for autonomous systems. Our data set provides the different perspectives of the world captured in coarse time slots (day and night), in addition to fine time slots (sunrise, morning, afternoon, sunset, night, and dawn). For all-day perception of autonomous systems, we propose the use of a different spectral sensor, i.e., a thermal imaging camera. Toward this goal, we develop a multi-sensor platform, which supports the use of a co-aligned RGB/Thermal camera, RGB stereo, 3-D LiDAR, and inertial sensors (GPS/IMU) and a related calibration technique. We design a wide range of visual perception tasks including the object detection, drivable region detection, localization, image enhancement, depth estimation, and colorization using a single/multi-spectral approach. In this paper, we provide a description of our benchmark with the recording platform, data format, development toolkits, and lessons about the progress of capturing data sets.
231 citations
TL;DR: A CNN-based MD-YOLO framework for multi-directional car license plate detection that can elegantly manage rotational problems in real-time scenarios and outperforms over other existing state-of-the-art methods in terms of better accuracy and lower computational cost.
Abstract: This paper presents a novel convolutional neural network (CNN) -based method for high-accuracy real-time car license plate detection. Many contemporary methods for car license plate detection are reasonably effective under the specific conditions or strong assumptions only. However, they exhibit poor performance when the assessed car license plate images have a degree of rotation, as a result of manual capture by traffic police or deviation of the camera. Therefore, we propose the a CNN-based MD-YOLO framework for multi-directional car license plate detection. Using accurate rotation angle prediction and a fast intersection-over-union evaluation strategy, our proposed method can elegantly manage rotational problems in real-time scenarios. A series of experiments have been carried out to establish that the proposed method outperforms over other existing state-of-the-art methods in terms of better accuracy and lower computational cost.
223 citations
TL;DR: A deep neural network-based car-following model that takes the velocities, velocity differences, and position differences that were observed in the last few time intervals as inputs and tries to embed prediction capability or memory effect of human drivers in a natural and efficient way.
Abstract: In this paper, we propose a deep neural network-based car-following model that has two distinctive properties. First, unlike most existing car-following models that take only the instantaneous velocity, velocity difference, and position difference as inputs, this new model takes the velocities, velocity differences, and position differences that were observed in the last few time intervals as inputs. That is, we assume that drivers’ actions are temporally dependent in this model and try to embed prediction capability or memory effect of human drivers in a natural and efficient way. Second, this car-following model is built in a data-driven way, in which we reduce human interference to the minimum degree. Specially, we use recently developing deep neural networks rather than conventional neural networks to establish the model, since deep learning technique provides us more flexibility and accuracy to describe complicated human actions. Tests on empirical trajectory records show that this deep neural network-based car-following model yield significantly higher simulation accuracy than existing car-following models. All these findings provide a novel way to study traffic flow theory and traffic simulations.
TL;DR: In this article, a siamesed FCN-based road detection model is proposed, which considers RGB-channel images, semantic contours, and location priors simultaneously to segment the road region elaborately.
Abstract: Road detection from the perspective of moving vehicles is a challenging issue in autonomous driving. Recently, many deep learning methods spring up for this task, because they can extract high-level local features to find road regions from raw RGB data, such as convolutional neural networks and fully convolutional networks (FCNs). However, how to detect the boundary of road accurately is still an intractable problem. In this paper, we propose siamesed FCNs (named “s-FCN-loc”), which is able to consider RGB-channel images, semantic contours, and location priors simultaneously to segment the road region elaborately. To be specific, the s-FCN-loc has two streams to process the original RGB images and contour maps, respectively. At the same time, the location prior is directly appended to the siamesed FCN to promote the final detection performance. Our contributions are threefold: 1) An s-FCN-loc is proposed that learns more discriminative features of road boundaries than the original FCN to detect more accurate road regions. 2) Location prior is viewed as a type of feature map and directly appended to the final feature map in s-FCN-loc to promote the detection performance effectively, which is easier than other traditional methods, namely, different priors for different inputs (image patches). 3) The convergent speed of training s-FCN-loc model is 30% faster than the original FCN because of the guidance of highly structured contours. The proposed approach is evaluated on the KITTI road detection benchmark and one-class road detection data set, and achieves a competitive result with the state of the arts.
TL;DR: Numerical results indicate that the proposed privacy-preserved pseudonym management scheme effectively enhances location privacy and reduces communication overhead for the vehicles and a hierarchical architecture for the scheme is introduced in F-IoV.
Abstract: As a promising branch of Internet of Things, Internet of Vehicles (IoV) is envisioned to serve as an essential data sensing and processing platform for intelligent transportation systems. In this paper, we aim to address location privacy issues in IoV. In traditional pseudonym systems, the pseudonym management is carried out by a centralized way resulting in big latency and high cost. Therefore, we present a new paradigm named Fog computing supported IoV (F-IoV) to exploit resources at the network edge for effective pseudonym management. By utilizing abundant edge resources, a privacy-preserved pseudonym ( $P^{3}$ ) scheme is proposed in F-IoV. The pseudonym management in this scheme is shifted to specialized fogs at the network edge named pseudonym fogs, which are composed of roadside infrastructures and deployed in close proximity of vehicles. $P^{3}$ scheme has following advantages: 1) context-aware pseudonym changing; 2) timely pseudonym distribution; and 3) reduced pseudonym management overhead. Moreover, a hierarchical architecture for $P^{3}$ scheme is introduced in F-IoV. Enabled by the architecture, a context-aware pseudonym changing game and secure pseudonym management communication protocols are proposed. The security analysis shows that $P^{3}$ scheme provides secure communication and privacy preservation for vehicles. Numerical results indicate that $P^{3}$ scheme effectively enhances location privacy and reduces communication overhead for the vehicles.
TL;DR: This paper jointly considers multiple decision factors to facilitate vehicle-to-infrastructure networking, where the energy efficiency of the networks is adopted as an important factor in the network selection process.
Abstract: The emerging technologies for connected vehicles have become hot topics. In addition, connected vehicle applications are generally found in heterogeneous wireless networks. In such a context, user terminals face the challenge of access network selection. The method of selecting the appropriate access network is quite important for connected vehicle applications. This paper jointly considers multiple decision factors to facilitate vehicle-to-infrastructure networking, where the energy efficiency of the networks is adopted as an important factor in the network selection process. To effectively characterize users’ preference and network performance, we exploit energy efficiency, signal intensity, network cost, delay, and bandwidth to establish utility functions. Then, these utility functions and multi-criteria utility theory are used to construct an energy-efficient network selection approach. We propose design strategies to establish a joint multi-criteria utility function for network selection. Then, we model network selection in connected vehicle applications as a multi-constraint optimization problem. Finally, a multi-criteria access selection algorithm is presented to solve the built model. Simulation results show that the proposed access network selection approach is feasible and effective.
TL;DR: In this paper, the authors proposed accelerated evaluation, focusing on the car-following scenario, where stochastic human-controlled vehicle (HV) motions are modeled based on 1.3 million miles of naturalistic driving data collected by the University of Michigan Safety Pilot Model Deployment Program.
Abstract: The safety of automated vehicles (AVs) must be assured before their release and deployment. The current approach to evaluation relies primarily on 1) testing AVs on public roads or 2) track testing with scenarios defined in a test matrix. These two methods have completely opposing drawbacks: the former, while offering realistic scenarios, takes too much time to execute and the latter, though it can be completed in a short amount of time, has no clear correlation to safety benefits in the real world. To avoid the aforementioned problems, we propose accelerated evaluation, focusing on the car-following scenario. The stochastic human-controlled vehicle (HV) motions are modeled based on 1.3 million miles of naturalistic driving data collected by the University of Michigan Safety Pilot Model Deployment Program. The statistics of the HV behaviors are then modified to generate more intense interactions between HVs and AVs to accelerate the evaluation procedure. The importance sampling theory was used to ensure that the safety benefits of AVs are accurately assessed under accelerated tests. Crash, injury and conflict rates for a simulated AV are simulated to demonstrate the proposed approach. Results show that test duration is reduced by a factor of 300 to 100 000 compared with the non-accelerated (naturalistic) evaluation. In other words, the proposed techniques have great potential for accelerating the AV evaluation process.
TL;DR: An effective Uyghur language text detection system in complex background images by a new channel-enhanced maximally stable extremal regions (MSERs) algorithm put forward to detect component candidates and a two-layer filtering mechanism designed to remove most non-character regions.
Abstract: Text detection in complex background images is a challenging task for intelligent vehicles. Actually, almost all the widely-used systems focus on commonly used languages while for some minority languages, such as the Uyghur language, text detection is paid less attention. In this paper, we propose an effective Uyghur language text detection system in complex background images. First, a new channel-enhanced maximally stable extremal regions (MSERs) algorithm is put forward to detect component candidates. Second, a two-layer filtering mechanism is designed to remove most non-character regions. Third, the remaining component regions are connected into short chains, and the short chains are extended by a novel extension algorithm to connect the missed MSERs. Finally, a two-layer chain elimination filter is proposed to prune the non-text chains. To evaluate the system, we build a new data set by various Uyghur texts with complex backgrounds. Extensive experimental comparisons show that our system is obviously effective for Uyghur language text detection in complex background images. The F-measure is 85%, which is much better than the state-of-the-art performance of 75.5%.
TL;DR: This work forms the Charging Station Placement Problem (CSPP) as a bilevel optimization problem, and proposes an algorithm Optimizing eleCtric vEhicle chArging statioN (OCEAN) to compute the optimal allocation of charging stations.
Abstract: To reduce the air pollution and improve the energy efficiency, many countries and cities (e.g., Singapore) are on the way of introducing electric vehicles (EVs) to replace the vehicles serving in current traffic system. Effective placement of charging stations is essential for the rapid development of EVs, because it is necessary for providing convenience for EVs and ensuring the efficiency of the traffic network. However, existing works mostly concentrate on the mileage anxiety from EV users but ignore their strategic and competitive charging behaviors. To capture the competitive and strategic charging behaviors of the EV users, we consider that an EV user’s charging cost, which is dependent on other EV users’ choices, consists of the travel cost to access the charging station and the queuing cost in charging stations. First, we formulate the Charging Station Placement Problem (CSPP) as a bilevel optimization problem. Then, by exploiting the equilibrium of the EV charging game, we convert the bilevel optimization problem to a single-level one, following which we analyze the properties of CSPP and propose an algorithm Optimizing eleCtric vEhicle chArging statioN (OCEAN) to compute the optimal allocation of charging stations. Due to OCEAN’s scalability issue, we furthermore present a heuristic algorithm OCEAN with Continuous variables to deal with large-scale real-world problems. Finally, we demonstrate and discuss the results of the extensive experiments we did. It is shown that our approach outperform baseline methods significantly.
TL;DR: A real-time scheme that can potentially detect the occurrence of a particular cyber attack, namely denial of service; and estimate the effect of the attack on the connected vehicle system is proposed.
Abstract: Advanced connectivity features in today’s smart vehicles are giving rise to several promising intelligent transportation technologies. Connected vehicle system is one among such technologies, where a set of vehicles can communicate with each other and the infrastructure via communication networks. Connected vehicles have the potential to improve the traffic throughput, minimize the risk of accidents and reduce vehicle energy consumption. Despite these promising features, connected vehicles suffer from the safety and security issues. Especially, vehicle-to-vehicle and vehicle-to-infrastructure communication make the connected vehicles vulnerable to cyber attacks. In order to improve safety and security, advanced vehicular control systems must be designed to be resilient to such cyber attacks. The first step of designing such attack-resilient control system is detection of the occurrence of the cyber attack. In this paper, we address this need and propose a real-time scheme that can potentially 1) detect the occurrence of a particular cyber attack, namely denial of service; and 2) estimate the effect of the attack on the connected vehicle system. The scheme consists of a set of observers, which are designed using sliding mode and adaptive estimation theory. The mathematical convergence properties of the observers are analyzed via Lyapunov’s stability theory. Finally, simulation demonstrates the performance of the approach and the robustness of the scheme under several forms of uncertainties.
TL;DR: A new data-driven system to recognize all categories of traffic signs, which include both symbol-based and text-based signs, in video sequences captured by a camera mounted on a car is proposed.
Abstract: Although traffic sign recognition has been studied for many years, most existing works are focused on the symbol-based traffic signs. This paper proposes a new data-driven system to recognize all categories of traffic signs, which include both symbol-based and text-based signs, in video sequences captured by a camera mounted on a car. The system consists of three stages, traffic sign regions of interest (ROIs) extraction, ROIs refinement and classification, and post-processing. Traffic sign ROIs from each frame are first extracted using maximally stable extremal regions on gray and normalized RGB channels. Then, they are refined and assigned to their detailed classes via the proposed multi-task convolutional neural network, which is trained with a large amount of data, including synthetic traffic signs and images labeled from street views. The post-processing finally combines the results in all frames to make a recognition decision. Experimental results have demonstrated the effectiveness of the proposed system.
TL;DR: In this article, the authors considered the robustness analysis and distributed H-infinity controller synthesis for a platoon of connected vehicles with undirected topologies and provided an explicit scaling trend of robustness measure.
Abstract: This paper considers the robustness analysis and distributed $\mathcal {H}_{\infty }$ (H-infinity) controller synthesis for a platoon of connected vehicles with undirected topologies. We first formulate a unified model to describe the collective behavior of homogeneous platoons with external disturbances using graph theory. By exploiting the spectral decomposition of a symmetric matrix, the collective dynamics of a platoon is equivalently decomposed into a set of subsystems sharing the same size with one single vehicle. Then, we provide an explicit scaling trend of robustness measure $\gamma $ -gain, and introduce a scalable multi-step procedure to synthesize a distributed $\mathcal {H}_{\infty }$ controller for large-scale platoons. It is shown that communication topology, especially the leader’s information, exerts great influence on both robustness performance and controller synthesis. Furthermore, an intuitive optimization problem is formulated to optimize an undirected topology for a platoon system, and the upper and lower bounds of the objective are explicitly analyzed, which hints us that coordination of multiple mini-platoons is one reasonable architecture to control large-scale platoons. Numerical simulations are conducted to illustrate our findings.
TL;DR: The neural network approach improves the performance on wheels with flat spots and non-roundness by explicitly modeling the multi sensor structure of the measurement system through multiple instance learning and shift invariant networks.
Abstract: Wheel defects on railway wagons have been identified as an important source of damage to the railway infrastructure and rolling stock. They also cause noise and vibration emissions that are costly to mitigate. We propose two machine learning methods to automatically detect these wheel defects, based on the wheel vertical force measured by a permanently installed sensor system on the railway network. Our methods automatically learn different types of wheel defects and predict during normal operation if a wheel has a defect or not. The first method is based on novel features for classifying time series data and it is used for classification with a support vector machine. To evaluate the performance of our method we construct multiple data sets for the following defect types: flat spot, shelling, and non-roundness. We outperform classical defect detection methods for flat spots and demonstrate prediction for the other two defect types for the first time. Motivated by the recent success of artificial neural networks for image classification, we train custom artificial neural networks with convolutional layers on 2-D representations of the measurement time series. The neural network approach improves the performance on wheels with flat spots and non-roundness by explicitly modeling the multi sensor structure of the measurement system through multiple instance learning and shift invariant networks.
TL;DR: A hierarchical trajectory planning based on the integration of a sampling and an optimization method for urban autonomous driving is presented and the proposed algorithms of the sampling-based behavioral and optimization-based motion trajectory were evaluated.
Abstract: This paper presents a hierarchical trajectory planning based on the integration of a sampling and an optimization method for urban autonomous driving. To manage a complex driving environment, the upper behavioral trajectory planner searches the macro-scale trajectory to determine the behavior of an autonomous car by using environment models, such as traffic control device and objects. This planner infers reasonable behavior and provides it to the motion trajectory planner. For planning the behavioral trajectory, the sampling-based approach is used due to its advantage of a free-form cost function for discrete models of the driving environments and simplification of the searching area. The lower motion trajectory planner determines the micro-scale trajectory based on the results of the upper trajectory planning with the environment model. The lower planner strongly considers vehicle dynamics within the planned behavior of the behavioral trajectory. Therefore, the planning space of the lower planner can be limited, allowing for improvement of the efficiency of the numerical optimization of the lower planner to find the best trajectory. For the motion trajectory planning, the numerical optimization is applied due to its advantages of a mathematical model for the continuous elements of the driving environments and low computation to converge minima in the convex function. The proposed algorithms of the sampling-based behavioral and optimization-based motion trajectory were evaluated through experiments in various scenarios of an urban area.
TL;DR: A joint method of priori convolutional neural networks at superpixel level (called as “priori s-CNNs”) and soft restricted context transfer and a soft restricted MRF energy function is defined to improve the priori s- CNNs model’s labeling performance and reduce the over smoothness at the same time.
Abstract: Street scene understanding is an essential task for autonomous driving. One important step toward this direction is scene labeling, which annotates each pixel in the images with a correct class label. Although many approaches have been developed, there are still some weak points. First, many methods are based on the hand-crafted features whose image representation ability is limited. Second, they cannot label foreground objects accurately due to the data set bias. Third, in the refinement stage, the traditional Markov random filed inference is prone to over smoothness. For improving the above problems, this paper proposes a joint method of priori convolutional neural networks at superpixel level (called as “priori s-CNNs”) and soft restricted context transfer. Our contributions are threefold: 1) a priori s-CNNs model that learns priori location information at superpixel level is proposed to describe various objects discriminatingly; 2) a hierarchical data augmentation method is presented to alleviate data set bias in the priori s-CNNs training stage, which improves foreground objects labeling significantly; and 3) a soft restricted MRF energy function is defined to improve the priori s-CNNs model’s labeling performance and reduce the over smoothness at the same time. The proposed approach is verified on CamVid data set (11 classes) and SIFT Flow Street data set (16 classes) and achieves a competitive performance.
TL;DR: Numerical results demonstrate that the proposed algorithm can achieve superior performance in terms of average network delay and content distribution efficiency compared with the other heuristic schemes.
Abstract: Driven by the evolutionary development of automobile industry and cellular technologies, dependable vehicular connectivity has become essential to realize future intelligent transportation systems (ITS). In this paper, we investigate how to achieve dependable content distribution in device-to-device (D2D)-based cooperative vehicular networks by combining big data-based vehicle trajectory prediction with coalition formation game-based resource allocation. First, vehicle trajectory is predicted based on global positioning system and geographic information system data, which is critical for finding reliable and long-lasting vehicle connections. Then, the determination of content distribution groups with different lifetimes is formulated as a coalition formation game. We model the utility function based on the minimization of average network delay, which is transferable to the individual payoff of each coalition member according to its contribution. The merge and split process is implemented iteratively based on preference relations, and the final partition is proved to converge to a Nash-stable equilibrium. Finally, we evaluate the proposed algorithm based on real-world map and realistic vehicular traffic. Numerical results demonstrate that the proposed algorithm can achieve superior performance in terms of average network delay and content distribution efficiency compared with the other heuristic schemes.
TL;DR: The work detailed in this paper reports on the development and implementation of a novel smart wireless sensor for traffic monitoring that is portable, reliable, and cost-effective.
Abstract: Real-time traffic surveillance is essential in today’s intelligent transportation systems and will surely play a vital role in tomorrow’s smart cities. The work detailed in this paper reports on the development and implementation of a novel smart wireless sensor for traffic monitoring. Computationally efficient and reliable algorithms for vehicle detection, speed and length estimation, classification, and time-synchronization were fully developed, integrated, and evaluated. Comprehensive system evaluation and extensive data analysis were performed to tune and validate the system for a reliable and robust operation. Several field studies conducted on highway and urban roads for different scenarios and under various traffic conditions resulted in 99.98% detection accuracy, 97.11% speed estimation accuracy, and 97% length-based vehicle classification accuracy. The developed system is portable, reliable, and cost-effective. The system can also be used for short-term or long-term installment on surface of highway, roadway, and roadside. Implementation cost of a single node including enclosure is US $50.
TL;DR: A probabilistic two-phase framework, named TripImputor, for making the real-time taxi trip purpose imputation and recommending services to passengers at their dropoff points, which is able to infer the trip purpose accurately and can provide recommendation results to passengers within 1.6 s in Manhattan on average.
Abstract: Travel behavior understanding is a long-standing and critically important topic in the area of smart cities. Big volumes of various GPS-based travel data can be easily collected, among which the taxi GPS trajectory data is a typical example. However, in GPS trajectory data, there is usually little information on travelers’ activities, thereby they can only support limited applications. Quite a few studies have been focused on enriching the semantic meaning for raw data, such as travel mode/purpose inferring. Unfortunately, trip purpose imputation receives relatively less attention and requires no real-time response. To narrow the gap, we propose a probabilistic two-phase framework named TripImputor , for making the real-time taxi trip purpose imputation and recommending services to passengers at their dropoff points. Specifically, in the first phase, we propose a two-stage clustering algorithm to identify candidate activity areas (CAAs) in the urban space. Then, we extract fine-granularity spatial and temporal patterns of human behaviors inside the CAAs from foursquare check-in data to approximate the priori probability for each activity, and compute the posterior probabilities (i.e., infer the trip purposes) using Bayes’ theorem. In the second phase, we take a sophisticated procedure that clusters historical dropoff points and matches the dropoff clusters and CAAs to immerse the real-time response. Finally, we evaluate the effectiveness and efficiency of the proposed two-phase framework using real-world data sets, which consist of road network, check-in data generated by over 38 000 users in one year, and the large-scale taxi trip data generated by over 19 000 taxis in a month in Manhattan, New York City, USA. Experimental results demonstrate that the system is able to infer the trip purpose accurately, and can provide recommendation results to passengers within 1.6 s in Manhattan on average, just using a single normal PC.
TL;DR: A Security Credential Management System (SCMS) for vehicle-to-everything (V2X) communications is presented in this paper, which has been developed by the Crash Avoidance Metrics Partners LLC under a cooperative agreement with the USDOT.
Abstract: The U.S. Department of Transportation (USDOT) issued a proposed rule on January 12, 2017 to mandate vehicle-to-vehicle safety communications in light vehicles in the U.S. Cybersecurity and privacy are major challenges for such a deployment. We present a Security Credential Management System (SCMS) for vehicle-to-everything (V2X) communications in this paper, which has been developed by the Crash Avoidance Metrics Partners LLC under a cooperative agreement with the USDOT. This system design is currently transitioning from research to proof-of-concept and is a leading candidate to support the establishment of a nationwide Public Key Infrastructure for V2X security. It issues digital certificates to participating vehicles and infrastructure devices for trustworthy communications among them, which is necessary for safety and mobility applications that are based on V2X communications. The SCMS supports four main use cases, namely, bootstrapping, certificate provisioning, misbehavior reporting, and revocation. The main design goal is to provide both security and privacy to the largest extent reasonable and possible. To achieve a reasonable level of privacy in this context, vehicles are issued pseudonym certificates, and the generation and provisioning of those certificates are divided among multiple organizations. Given the large number of pseudonym certificates per vehicle, one of the main challenges is to facilitate efficient revocation of misbehaving or malfunctioning vehicles, while preserving privacy against attacks from insiders. The proposed SCMS supports all identified V2X use-cases and certificate types necessary for V2X communication security. This paper is based upon work supported by the USDOT. Any opinions, findings, and conclusions or recommendations expressed in this publication are those of the authors (“we”) and do not necessarily reflect the view of the USDOT.
TL;DR: A robust and real-time vision-based lane detection algorithm with an efficient region of interest is proposed to reduce the high noise level and the calculation time and fulfills the real- time operation requirement on embedded systems with low computing power.
Abstract: An effective lane-detection algorithm is a fundamental component of an advanced driver assistant system, as it provides important information that supports driving safety. The challenges faced by the lane detection and tracking algorithm include the lack of clarity of lane markings, poor visibility due to bad weather, illumination and light reflection, shadows, and dense road-based instructions. In this paper, a robust and real-time vision-based lane detection algorithm with an efficient region of interest is proposed to reduce the high noise level and the calculation time. The proposed algorithm also processes a gradient cue and a color cue together and a line clustering with scan-line tests to verify the characteristics of the lane markings. It removes any false lane markings and tracks the real lane markings using the accumulated statistical data. The experiment results show that the proposed algorithm gives accurate results and fulfills the real-time operation requirement on embedded systems with low computing power.
TL;DR: In this paper, the authors use RL for the control of systems modeled by discretized non-linear partial differential equations (PDEs) and devise a novel algorithm to use non-parametric control techniques for large multi-agent systems.
Abstract: This paper shows how the recent breakthroughs in reinforcement learning (RL) that have enabled robots to learn to play arcade video games, walk, or assemble colored bricks, can be used to perform other tasks that are currently at the core of engineering cyberphysical systems. We present the first use of RL for the control of systems modeled by discretized non-linear partial differential equations (PDEs) and devise a novel algorithm to use non-parametric control techniques for large multi-agent systems. Cyberphysical systems (e.g., hydraulic channels, transportation systems, the energy grid, and electromagnetic systems) are commonly modeled by PDEs, which historically have been a reliable way to enable engineering applications in these domains. However, it is known that the control of these PDE models is notoriously difficult. We show how neural network-based RL enables the control of discretized PDEs whose parameters are unknown, random, and time-varying. We introduce an algorithm of mutual weight regularization (MWR), which alleviates the curse of dimensionality of multi-agent control schemes by sharing experience between agents while giving each agent the opportunity to specialize its action policy so as to tailor it to the local parameters of the part of the system it is located in. A discretized PDE, such as the scalar Lighthill–Whitham–Richards PDE can indeed be considered as a macroscopic freeway traffic simulator and which presents the most salient challenges for learning to control large cyberphysical system with multiple agents. We consider two different discretization procedures and show the opportunities offered by applying deep reinforcement for continuous control on both. Using a neural RL PDE controller on a traffic flow simulation based on a Godunov discretization of the San Francisco Bay Bridge, we are able to achieve precise adaptive metering without model calibration thereby beating the state of the art in traffic metering. Furthermore, with the more accurate BeATS simulator, we manage to achieve a control performance on par with ALINEA, a state-of-the-art parametric control scheme, and show how using MWR improves the learning procedure.
TL;DR: This paper extends upon earlier works on perimeter control-based MPC schemes with MFD modeling by integrating route guidance type actuation, which distributes flows exiting a region over its neighboring regions, which shows the possibility of substantial improvements in urban network performance.
Abstract: Local traffic control schemes fall short of achieving coordination with other parts of the urban road network, whereas a centralized controller based on the detailed traffic models would suffer from excessive computational burden. State estimation for detailed traffic models with limited observations and unpredictability of individual driver behavior create additional complications in the applicability of these models for large-scale traffic control. This point toward the need for designing network-level controllers building on aggregated traffic models, which have recently attracted attention through the macroscopic fundamental diagram (MFD) of urban traffic. Under some conditions, the MFD provides a unimodal, low-scatter, and demand-insensitive relationship between vehicle accumulation and travel production inside an urban region. In this paper, we propose MFD-based economic model predictive control (MPC) schemes to improve mobility in heterogeneously congested large-scale urban road networks. For more realistic simulations of urban networks with route guidance actuation-based control, a new model with cyclic behavior prohibition is developed. This paper extends upon earlier works on perimeter control-based MPC schemes with MFD modeling by integrating route guidance type actuation, which distributes flows exiting a region over its neighboring regions. Performance of the proposed schemes is evaluated via simulations of congested scenarios with noise in demand estimation and measurement errors. Results show the possibility of substantial improvements in urban network performance, in terms of network delays and traveled distance, even for low levels of driver compliance to route guidance.