Search

Surround-view system (SVS) is widely used in the advanced driver assistance system (ADAS). SVS uses four fish-eye lenses to monitor real-time scenes around the vehicle. However, accurate intrinsic and extrinsic parameter estimation is required for the proper functioning of the system. At present, the intrinsic calibration can be pipeline by utilizing checkerboard algorithm, while extrinsic calibration is still immature. Therefore, we proposed a specific calibration pipeline to estimate extrinsic parameters robustly. This scheme takes a driving sequence of four cameras as input. It firstly utilizes lane line to roughly estimate each camera pose. Considering the environmental condition differences in each camera, we separately select strategies from two methods to accurately estimate the extrinsic parameters. To achieve accurate estimates for both front and rear camera, we proposed a method that mutually iterating line detection and pose estimation. As for bilateral camera, we iteratively adjust the camera pose and position by minimizing texture and edge error between ground projections of adjacent cameras. After estimating the extrinsic parameters, the surround-view image can be synthesized by homography-based transformation. The proposed pipeline can robustly estimate the four SVS camera extrinsic parameters in real driving environments. In addition, to evaluate the proposed scheme, we build a surround-view fish-eye dataset, which contains 40 videos with 32,000 frames, acquired from different real traffic scenarios. All the frames in each video are manually labeled with lane annotation, with its GT extrinsic parameters. Moreover, this surround-view dataset could be used by other researchers to evaluate their performance. The dataset will be available soon. [ABSTRACT FROM AUTHOR]

• Belgian drivers have rather positive opinions about lower-level ADAS (SAE-0). • The SEM empirically validates UMDA, explaining 68.9% of variance in ADAS acceptance. • User-specific characteristics impact the ADAS acceptance. • Attitude mediates relationship between system-specific beliefs and ADAS acceptance. Advanced Driver Assistance Systems (ADAS) are linked with enhanced transportation system efficiency and safety. However, prior research highlights the indispensable role of drivers' acceptance in realizing these benefits. Several models have been introduced to investigate drivers' acceptance of ADAS. This study examined the predictive validity of the Unified Model of Driver Acceptance (UMDA) using Structural Equation Modelling (SEM), expanding beyond multiple regression utilized in the past and taking the full conceptual Model of Driver Acceptance proposed by Rahman et al. (2018) as the theoretical starting point. Specifically, we focused on Belgian car drivers' acceptance towards a retrofitted ADAS bundle, encompassing forward collision warning, headway monitoring and warning, and lane-keep assist. Because of the new European law, the provision of certain ADAS technologies in vehicles will be mandatory, and this will accelerate the retrofitting of ADAS into older vehicles. Therefore, knowing the determinants of drivers' acceptance of retrofitted systems is important. Data was collected through an online structured questionnaire based on the UMDA framework. The final dataset consisting of responses from 322 participants underwent Principal Component Analysis (PCA) to identify the factor structure, Confirmatory Factor Analysis (CFA) to verify it, and path analysis to reveal determinants of ADAS acceptance. Additionally, the study employed independent sample t -test and ANOVA to assess how driver-related variables moderated the model's constructs. Descriptive findings indicated moderate overall acceptance, with participants generally favouring system-specific characteristics. PCA and CFA identified and confirmed four distinct factors: endorsement, attitude, usability, and affordability. SEM path analysis unveiled that attitude played a dual role— mediating the impact of affordability and endorsement on behavioural intention to use ADAS as well as exerting a direct effect on behavioural intention. Other variables directly impacting behavioural intention included endorsement and usability. Demographic and driving-related variables moderated the influence of system-related factors on intention to use ADAS. To conclude, the study identified a factor structure distinct from the original UMDA hypothesis. Moreover, the application of SEM provides novel insights into ADAS acceptance that could be helpful, specifically in the EU context where ADAS retrofitting into vehicles is under consideration. The findings suggest that policymakers should prioritize strategies encouraging ADAS adoption and use. This prioritization should extend beyond shaping decision-making processes alone. [ABSTRACT FROM AUTHOR]

Advanced Driver Assistance System (ADAS) is the latest buzzword in the automotive industry aimed at reducing human errors and enhancing safety. In ADAS systems, the choice of control strategy is not straightforward due to the highly complex nonlinear dynamics, control objectives, and safety critical constraints. Nonlinear Model Predictive Control (NMPC) has evolved as a favorite option for optimal control due to its ability to handle such constrained, Multi-Input Multi-Output (MIMO) systems efficiently. However, NMPC suffers from a bottleneck of high computational complexity, making it unsuitable for fast real-time applications. This paper presents a generic framework using Successive Online Linearization-based NMPC (SOL-NMPC) for for the control in ADAS. The nonlinear system is linearized and solved using Linear Model Predictive Control every iteration. Furthermore, offset-free MPC is developed with the Extended Kalman Filter for reducing model mismatch. The developed SOL-NMPC is validated using the 14-Degrees-of-Freedom (DoF) model of a D-class light motor vehicle. The performance is simulated in matlab/Simulink and validated using the CarSim® software (Version 2016). The real-time implementation of the proposed strategy is tested in the Hardware-In-the-Loop (HIL) co-simulation using the STM32-Nucleo-144 development board. The detailed performance analysis is presented along with time profiling. It can be seen that the loss of accuracy can be counteracted by the fast response of the proposed framework. [ABSTRACT FROM AUTHOR]

Rigorous testing of automotive sensors for accuracy and precision is essential before finalizing designs and proceeding with mass production. This testing process plays a crucial role in identifying these sensors’ potential shortcomings, which are essential components in the Advanced Driver Assistance Systems (ADAS). A virtual environment for sensor model simulation and testing provides a significant advantage in experimenting with the sensor in a vast array of realistic scenarios, which may be cost-prohibitive in physical testing. Thus, radar sensors, a commonly used sensor in ADAS, have been modeled using various methodologies in virtual environments. However, there is a need for a radar model that is both computationally efficient and accurate under different combinations of radar reflectivity, directivity, and signal-to-noise ratio (SNR). In this study, we propose a model of a Delphi-ESR 2.5 medium-range automotive radar in the Unreal Engine environment that leverages grid-based DBSCAN for point-cloud clustering and radar equations to calculate the SNR of grid points, facilitating object detection and tracking. The proposed model incorporates the reflectivity and directivity concept of Radar Cross-Section (RCS) to emulate the behavior of an actual radar. The sensor model exhibits superior accuracy and low computational requirement, with a mean error rate of 10.8% and an output rate of 8.7 Hz. This approach provides a reliable means of simulating and testing automotive radar sensors in a virtual environment, contributing to the further advancements of the ADAS systems.

While computer vision and computing technology advances have facilitated advanced driver assistance applications, systems with multi-task design remain highly demanding to operate at high speed on resource-constrained devices. Our study addresses this challenge by proposing a real-time driver assistance solution specifically developed for a single Jetson AGX Xavier embedded device. It simultaneously performs lane detection, traffic object detection and recognition, and rule-based scene analysis. To achieve high throughput (up to 43 frames per second) without reliance on additional hardware or cloud server, the system exploits Jetson device’s specialized AI accelerator and employs various optimization techniques: multithreaded programming, the TensorRT framework, and post-training quantization. The modular design integrates state-of-the-art task-specific methods and ensures adaptation to diverse traffic scenarios across countries as well as future hardware and solutions. Experimental results using a Korean dashcam traffic dataset validated the system’s effectiveness and practicality.

Advanced Driver Assistance System (ADAS) is the latest buzzword in the automotive industry aimed at reducing human errors and enhancing safety. In ADAS systems, the choice of control strategy is not straightforward due to the highly complex nonlinear dynamics, control objectives, and safety critical constraints. Nonlinear Model Predictive Control (NMPC) has evolved as a favorite option for optimal control due to its ability to handle such constrained, Multi-Input Multi-Output (MIMO) systems efficiently. However, NMPC suffers from a bottleneck of high computational complexity, making it unsuitable for fast real-time applications. This paper presents a generic framework using Successive Online Linearization-based NMPC (SOL-NMPC) for for the control in ADAS. The nonlinear system is linearized and solved using Linear Model Predictive Control every iteration. Furthermore, offset-free MPC is developed with the Extended Kalman Filter for reducing model mismatch. The developed SOL-NMPC is validated using the 14-Degrees-of-Freedom (DoF) model of a D-class light motor vehicle. The performance is simulated in matlab/Simulink and validated using the CarSim® software (Version 2016). The real-time implementation of the proposed strategy is tested in the Hardware-In-the-Loop (HIL) co-simulation using the STM32-Nucleo-144 development board. The detailed performance analysis is presented along with time profiling. It can be seen that the loss of accuracy can be counteracted by the fast response of the proposed framework.

As an important part of the advanced driver assistance system (ADAS), the active emergency collision avoidance system can effectively reduce the incidence of accidents. Previously, static obstacle avoidance has been realized by employing piecewise polynomial path planning to improve vehicle stability. However, regarding moving obstacles, the collision avoidance problem becomes more intractable. To address the problem, a novel method based on the technical framework of piecewise polynomial path planning is proposed in this paper to conduct collision avoidance with moving obstacles. First, the Multivariate Gaussian Distribution model is adopted to estimate the velocity of the obstacle ahead, and the longitudinal motion trajectory of the obstacle is calculated. Then, the longitudinal length of the first target path is selected by the rule-based method. Moreover, yielding from the method for static obstacles, the collision avoidance algorithm for moving obstacles is proposed. Finally, the co-simulations are carried out in Simulink/CarSim, of which the results prove that the proposed method can avoid the moving obstacle effectively. [ABSTRACT FROM AUTHOR]

The objective of this study was to characterize driving safety and the factors affecting it among physicians in combat units in the Israel Defense Forces (IDF), who have high workloads and substantial sleep deprivation, which could influence driving safety. This cross-sectional study included physicians in combat units who had a personal vehicle equipped with an advanced driver assistance system (ADAS). The study outcomes included events such as drowsy driving or falling asleep while driving, as well as motor vehicle accidents (MVAs), obtained from self-reports from digital questionnaires, and objective ADAS driving safety scores. Sleep hours, burnout scores (Maslach Burnout Inventory), combat activity levels, and demographic characteristics were obtained through digital questionnaires, and their effects on the outcomes were analyzed. Sixty-four military combat unit physicians were included in the study. No differences in drowsy driving, MVAs, or ADAS scores were found between the 2 combat activity level groups. The results showed that 82% of participants reported dozing off while driving, and this was positively correlated with accelerations (β = 0.19; P =.004) and negatively correlated (adjusted R2 = 21%) with hours of sleep (β = −0.28; P =.001). Eleven percent reported experiencing MVAs, none of whom required hospitalization. The mean ADAS safety score was 87.17 ± 7.54, and this was positively correlated with the cynicism score (β = 1.45; P =.04; adjusted R2 = 4.7%). No association between dozing off/falling asleep while driving and the reported MVAs was found (P =.10 and P =.27, respectively). Physicians in combat units have a low incidence of MVAs and high ADAS scores. This may be attributed to the high safety climate enforced in military units. However, the high rate of dozing off while driving highlights the importance of addressing driving safety in this population. [ABSTRACT FROM AUTHOR]

The visual information complexity of automotive head-up displays (HUDs) may affect cognitive load and reduce driver performance in critical situations. This study investigated whether physiological indicators of cognitive load can predict the type of HUD while driving. Physiological signals of heart rate variability (HRV), electrodermal activity (EDA), skin temperature, and pupil dilation were recorded from 28 participants using a motion-based driving simulator. Two types of HUD with different information complexities were compared: baseline HUD and augmented reality HUD. Heart rate and EDA were processed to create standardized biomedical features. Time-series analysis and basic statistics generated two sets of features for pupil dilation and skin temperature. The effect of signal combinations on classification performance was tested using signal fusion. Three gradient boosting classifiers (LGBM, HGBC, and XGB) were trained on physiological signals to predict HUD type. The fusion of HRV, EDA, and time-series features for skin temperature and pupil dilation yielded moderate performance, with average AUC ROC scores of XGB = 0.67, LGBM = 0.69, and HGBC = 0.70. Combining HRV, EDA, and basic statistical features for skin temperature and pupil dilation, the classifiers achieved an improved average AUC ROC score of 0.76. The best scores were 0.96 (LGBM and XGB) and 0.98 (HGBC). These results demonstrate the potential of physiological signals for modeling HUD-induced cognitive load and dynamically regulating its effects in real-time.

Explanations — reasons or justifications for action — are being used to promote the acceptance of automated vehicles (AVs). Yet, it is unclear whether and how the modality of explanation affects its effectiveness. Despite its importance in the technology acceptance literature, the impact of technology suspicion on the adoption of AVs is yet to be fully examined. To expand our understanding of AV explanation, we conducted a within-subjects experiment with 32 participants using a high-fidelity driving simulator. Four conditions were presented to participants: (1) auditory explanation with a non-driving-related task (NDRT), (2) auditory explanation without NDRT, (3) visual explanation with NDRT, and (4) visual explanation without NDRT. The results indicate that auditory explanations are more effective in reducing anxiety and unsafety perception for high-suspicion individuals, especially in the absence of NDRT. Conversely, individuals who are less technology suspicious prefer visual explanations, which can result in lower levels of anxiety and perceived unsafety. The study highlights the importance of considering individuals’ technology suspicion and engagement with NDRT when selecting the appropriate explanation modality, and the findings can guide the design of future AV systems to promote effective human-machine interaction.

Advanced driver assistance systems (ADASs) are becoming increasingly common in modern-day vehicles, as they not only improve safety and reduce accidents but also aid in smoother and easier driving. ADASs rely on a variety of sensors such as cameras, radars, lidars, and a combination of sensors, to perceive their surroundings and identify and track objects on the road. The key components of ADASs are object detection, recognition, and tracking algorithms that allow vehicles to identify and track other objects on the road, such as other vehicles, pedestrians, cyclists, obstacles, traffic signs, traffic lights, etc. This information is then used to warn the driver of potential hazards or used by the ADAS itself to take corrective actions to avoid an accident. This paper provides a review of prominent state-of-the-art object detection, recognition, and tracking algorithms used in different functionalities of ADASs. The paper begins by introducing the history and fundamentals of ADASs followed by reviewing recent trends in various ADAS algorithms and their functionalities, along with the datasets employed. The paper concludes by discussing the future of object detection, recognition, and tracking algorithms for ADASs. The paper also discusses the need for more research on object detection, recognition, and tracking in challenging environments, such as those with low visibility or high traffic density.

Mode awareness is important for the safe use of automated vehicles, yet drivers' understanding of mode transitions has not been sufficiently investigated. In this study, we administered an online survey to 838 respondents to examine their understanding of control responsibilities in partial and conditional driving automation with four types of interventions (brake pedal, steering wheel, gas pedal, and take-over request). Results show that most drivers understand that they are responsible for speed and distance control after brake pedal interventions and steering control after steering wheel interventions. However, drivers have mixed responses regarding the responsibility for speed and distance control after steering wheel interventions and the responsibility for steering control after gas pedal interventions. With a higher automation level (conditional driving automation), drivers expect automation to remain responsible more often compared to a lower automation level (partial driving automation). Regarding Hands-on requirements, more than 99% of respondents answered that drivers would keep their hands on the steering wheel after all intervention types in partial automation, while 60–95% would place their hands on the wheel after various intervention types in conditional automation. A misalignment between actual logic and drivers' expectations regarding control responsibilities is observed by comparing survey responses to the mode transition logic of commercial partially automated vehicles. To resolve confusion about control responsibilities and ensure consistent expectations, we propose implementing a consistent mode design and providing enhanced information to drivers. [ABSTRACT FROM AUTHOR]

This paper presents a driving circuitry system for high-resolution, pixelated-LED automotive headlamps. The system consists of an array of pixel drivers, and a row/column driver suitable for an active-matrix array configuration with the individual dimming control capabilities on each pixelated-LED. An asynchronous serial communication protocol is introduced to minimize the number of data transmission interface signals between the row/column driver and pixel drivers. The proposed pixel driver is designed to drive each pixelated-LED with constant current and pulse width modulation (PWM). It contains a memory cell for dimming data, and a sample-and-hold driver stage to minimize the static power consumption of the pixel driver. The proposed system has been fabricated by using a 0.18- $\mu \text{m}$ CMOS process. The test chip includes a $2\times16$ pixel array with an embedded row/column driver. The functional operation has been verified with an $8\times16$ LED array system prototype.

This paper proposes an improvement to the multi-object tracking system framework based on the image inputs. By analyzing the role and performance of each block in the original multi-objects tracking system, the blocks of the original system are reconstructed to enhance the efficiency and yield a faster processing speed suiting the real-time applications. In the proposed method, the first two parts of the multi-object tracking system are merged into a single neural network designed for object detection and feature extraction. A new object association judgment method and JDE inspired prediction head are included in order to achieve a better and an outstanding association effect resulting in the overall improvement of the original system by 45.2%. The enhanced method is aimed at the application of smart roadside units and uses fixed-viewpoint image input to achieve multi-object tracking on embedded platforms. The proposed method is implemented on the NVIDIA Jetson AGX Xavier embedded platform. The NVIDIA TensorRT software development kit is used to accelerate the neural network. The overall performance of the proposed system yields better efficiency compared to that of the original SDE design and the overall computing performance achieve up to 14–26 images per second, making it ideal for the real-time smart roadside unit applications.

Accurate identification of lane-changing intention can effectively assist intelligent driving vehicles in terms of decision-making and trajectory planning, which plays a significant role in enhancing driving safety by reducing traffic accidents caused by lane-changing. Based on the trajectory characteristics and vehicle interaction information, an attention-enhanced bidirectional multi-layer residual long-short term memory neural network (Attention Enhanced Residual-MBi-LSTM) model is proposed for lane change intention recognition in this paper. Firstly, an EWMA filter is employed to smooth the noisy data collected from the vehicle. Then a four-layer bidirectional residual LSTM memory (Residual-MBi-LSTM) structure is used to extract lane-changing features from the historical driving trajectories of ego-vehicle and vehicle interaction information. Besides, the attention mechanism is added to adjust the weight of data in different time frames. After that, the current lane-changing probability is calculated and output by the Softmax function. Finally, the vehicle lane-changing intention recognition model is firstly trained and then verified in the HighD dataset. According to the HIL experiment, the proposed model has the ability to identify driver intention on average of 2.07 seconds in advance.

In recent years, automatic driving and advanced driving support systems have become more widespread; however, control systems do not consider the driving characteristics of each driver. This study constructed a personalized driver model for following forward vehicles on highways using LSTM (Long Short-Term Memory). In particular, the setting parameters for training with LSTM was focused upon and consequently, the relationship between the setting parameters and model accuracy was evaluated. The LSTM parameters considered were the number of hidden units, learning rate, number of epochs, and number of LSTM layers. Further, the driving data were measured using a driving simulator. Moreover, the model was evaluated in terms of accuracy using the coefficient of determination, and 125 combinations of parameters were compared using the mean value of the coefficient of determination and its significant difference. The order of parameter comparisons was performed considering the accuracy and learning time of the model. Consequently, the parameter set that is likely to allow efficient building of a highly accurate driver model was determined. Applying the parameter evaluation in this study contributes to the development of personalized driver models with high accuracy.

Lane detection is one of the key steps for developing driver assistance and vehicle automation features. A number of techniques are available for lane detection as part of computer vision tools to perform lane detection with different levels of accuracies. In this paper a unique method has been proposed for lane detection based on dynamic origin (DOT). This method provides better flexibility to adjust the outcome as per the specific needs of the intended application compared to other techniques. As the method offers better degree of control during the lane detection process, it can be adapted to detect lanes in varied situations like poor lighting or low quality road markings. Moreover, the Piecewise Linear Stretching Function (PLSF) has also been incorporated into the proposed method to improve the contrast of the input image source. Adding the PLSF method to the proposed lane detection technique, has significantly improved the accuracy of lane detection when compared to hough transform method from 87.88% to 98.25% in day light situations and from 94.15% to 97% in low light situations.

Traffic sign detection and recognition (TSDR) plays an important role in the fields for assistant driving, autonomous vehicle and so on. However, due to the complexity of real driving scene and variety of traffic signs, many challenging problems occurred, such as inaccurate color segmentation and time consumption of recognition algorithm based on deep learning. This paper describes an approach for efficiently detection and recognizing in real world scenarios. First of all, a traffic sign region of interest extraction algorithm based on multi-color space is proposed, the fusion future of HSV and RGB color space can obtain better color segmentation for the SVM classifier. Next a novel multi-scale two-stage lightweight network (MSTSN) is investigated, which adopts a coarse-to-fine strategy to improve recognition accuracy. Specially, the candidate Region of Interests (ROIs) are fed into a binary classification layer and only positive ones are further classified with multi-class classification network. The deeply separable convolution, residual structure and feature enhancement module is the bottleneck of MSTSN, which obtains more discriminative features and meets requirement for real-time performance. The experimental results successfully demonstrate effectiveness of our method. [ABSTRACT FROM AUTHOR]

This paper aims to develop an integrated adaptive control strategy to control vehicle lateral dynamics. A hierarchical control scheme consisted of two control levels is designed to keep the vehicle handling and improve yaw stability control using the coordination of active front steering (AFS) and direct yaw moment control (DYC). At the upper control level, the desired yaw moment and additive steering angle are obtained through proper adaptive laws in the first level adaptation (FLA) control structure. A constraint optimisation algorithm is utilised in the lower control level to adjust the impact of the steering and braking actuators. The desired yaw moment is converted into the brake torques and effectively distributed to the wheels. Improvement in the yaw stability control is demonstrated through simulation studies for a nonlinear 8 degree-of-freedom (DOF) vehicle model. Furthermore, the performance of the proposed control strategy is compared with that of the adaptive controller without integration. Simulation results of two different maneuvers point to the superiority of the proposed approach, highlighting some of its appealing features, like better tracking performance with lower control efforts in terms of brake torque and steering angle, as compared to the conventional adaptive method. [ABSTRACT FROM AUTHOR]

When we are studying the copiloting system, how to consider the driver's intention more comprehensively is a difficult issue. To this end, this paper presents a novel shared control framework based on handling inverse dynamics and driving intention for lane changing. In particular, the influence of the driver's lane-changing start point and end point is considered in the design of the shared controller. The human driver's driving intention, desired maneuver, and the start and end point are recognized. Moreover, the infinite-dimensional generalized ridge regression in reproducing kernel Hilbert spaces (RKHS) is used to deal with the lane change's start and end point prediction. Besides, a handling inverse dynamics model, including time-varying vehicle speed, is established for the automated controller, and the Multi-stage Gaussian pseudo-spectral method (GPM) is designed to solve the optimal control problem. With a shared fuzzy controller based on the state assessment, the controller generates outputs that can relieve the driver's burden. Finally, the shared control framework is validated in both overtaking and emergency obstacle avoidance scenarios. The results prove that the shared driving control framework can effectively relieve the burden on drivers and improve lane changing safety. [ABSTRACT FROM AUTHOR]

This paper presents a lightweight Multi-task Semantic Attention Network (MTSAN) to collectively deal with object detection as well as semantic segmentation aiding real-time applications of the Advanced Driver Assistance Systems (ADAS). This paper proposes a Semantic Attention Module (SAM) that introduces the semantic contextual clues from a segmentation subnet to guide a detection subnet. The SAM significantly boosts up the detection performance and computational cost by considerably decreasing the false alarm rate and it is completely independent of any other parameters. The experimental results show the effectiveness of each component of the network and demonstrate that the proposed MTSAN yields a better balance between accuracy and speed. Following the post-processing methods, the proposed module is tested and proved for its accuracy in the Lane Departure Warning System (LDWS) and Forward Collision Warning System (FCWS). In addition, the proposed lightweight network is deployable on low-power embedded devices to meet the requirements of the real-time applications yielding 10FPS @ 512 X 256 on NVIDIA Jetson Xavier and 15FPS @ 512 X 256 on Texas Instrument’s TDA2x.

Effectively detecting road objects in various environments would significantly improve driving safety for autonomous vehicles. However, small objects, low illumination, and blurred outline in images strongly limit the performance of current road object detection methods. To solve these problems, this paper proposed a novel deep learning anchor-free approach based on CenterNet. The atrous spatial pyramid pooling (ASPP) was used to extract features from multiple scales to improve the detection performance while not increasing the computational cost and the number of parameters. The space to depth algorithm was then adopted in our proposed approach to optimize the traditional downsampling process. A large-scale naturalistic driving dataset (BDD100K) was used to examined the effectiveness of our proposed approach. The experimental results show that our proposed approach can effectively improve the detection performance on small objects in various traffic situations.

Lane detection is one of the key steps for developing driver assistance and vehicle automation features. A number of techniques are available for lane detection as part of computer vision tools to perform lane detection with different levels of accuracies. In this paper a unique method has been proposed for lane detection based on dynamic origin (DOT). This method provides better flexibility to adjust the outcome as per the specific needs of the intended application compared to other techniques. As the method offers better degree of control during the lane detection process, it can be adapted to detect lanes in varied situations like poor lighting or low quality road markings. Moreover, the Piecewise Linear Stretching Function (PLSF) has also been incorporated into the proposed method to improve the contrast of the input image source. Adding the PLSF method to the proposed lane detection technique, has significantly improved the accuracy of lane detection when compared to hough transform method from 87.88% to 98.25% in day light situations and from 94.15% to 97% in low light situations. [ABSTRACT FROM AUTHOR]

In the advanced driver assistance system (ADAS) and autonomous driving systems, accurate information on preceding vehicle motion states is vital for the path planning and control. To develop those intelligent driving systems, a modular integrated estimation algorithm for the preceding vehicle longitudinal and lateral states is proposed in this paper, the coupled nonlinear characteristics of vehicle dynamics are applied to improve state estimation accuracy. First, considering driver aggressiveness, a linear moving horizon estimator for the vehicle longitudinal speed is designed based on the car following model. Then, the estimated vehicle longitudinal speed is delivered to the lateral estimator module in real-time. For the arbitrary driving routes, the Serret-Frenet equations and nonlinear lateral dynamics are combined to describe the lateral motion of preceding vehicle. Furthermore, a nonlinear moving horizon estimator is constructed to estimate vehicle lateral states accurately. To reduce the computational burden, the multiple shooting (MS) method is introduced, then the objective function is divided into several segments to improve the strong nonlinearity produced by multiple iterations. The proposed estimation algorithm can effectively handle the initial biases, the additive biases and model error, which are common in the acquired signals, and provide an accurate estimate of preceding vehicle states. [ABSTRACT FROM AUTHOR]

Many autonomous vehicles and advanced driver-assistance systems are equipped with front-facing cameras that detect and track objects using deep-learning-based algorithms. However, the localization capability of monocular cameras is often overlooked. In this paper, a novel method for estimating the pixel-wise error in a detected object's location versus its ground truth is proposed. As the object moves away from the camera, the pixel errors are shown to be normally distributed with unique spreads along the image's vertical axis (y-pixel). The pixel error appears to be smaller as objects get farther away, while at the same distance range, objects have similar error distribution across the camera's horizontal view. The horizontal axis (x-pixel) error appears to be smaller while the distance moves further away. However, the x-pixel location along a constant y-pixel row has no impact on the error distribution. The estimated x and y-pixel error distributions can in turn be used to form a spatial error distribution for finding the location of a detected object within a certain confidence interval. The spatial errors are then projected onto the world coordinate system using a camera transformation matrix to give a more realistic sense of what this error means. The results show that location estimation using monocular cameras generates an elliptical error distribution around the object with a larger error in the y-pixel direction compared to the x-pixel direction. This error distribution can be important to fuse information from multiple range-detecting sensors as well as multi-vehicle and multi-object tracking. The uncertainty characterization for position measurement, as demonstrated in this paper is an essential element of tracking and, is sensor and algorithm dependent. [ABSTRACT FROM AUTHOR]

Light detection and rangings (LiDARs) are considered essential for the environmental sensing required by most advanced driver assistance system (ADAS), including autonomous driving. This has led to significant investments resulted in the availability of countless measuring systems that are increasingly performing and less expensive. Nevertheless, the extremely high speed of light still leads to a nonnegligible quantization error in the direct time-of-flight (ToF) measure at the base of pulsed LiDARs—the leading technology for automotive applications. Hence, pulsed 3-D LiDARs analyze the surrounding by approximating and deforming it on concentric spheres whose radii are quantized with a quantization step that, for most commercial systems, is on the order of some centimeters. The deformation and error introduced by such quantization can thus be significant. In this study, we point out the approximations and assumptions intrinsic to 3-D LiDARs and propose a measurement procedure that, through the analysis of the fine variations of the target position, allows an accurate investigation of the axial resolution and error—probably among the few limitations still affecting this technology. To the best of our knowledge, this is the first study focused on the detailed analysis of the quantization error in 3-D LiDARs. The proposed method has been tested on one of the most popular 3-D LiDARs, namely the MRS 6000 by Sick. The obtained results revealed for the MRS 6000 a quantization step of about 6 cm (ToF quantization of about 0.4 ns) and an axial error normally distributed with experimental standard deviation of about 30 mm. [ABSTRACT FROM AUTHOR]

Most individuals involved in traffic accidents receive assistance from drivers, passengers, or other people. However, when a traffic accident occurs in a sparsely populated area or the driver is the only person in the vehicle and the crash results in loss of consciousness, no one will be available to send a distress message to the proper authorities within the golden window for medical treatment. Considering these issues, a method for detecting high-speed head-on and single-vehicle collisions, analyzing the situation, and raising an alarm is needed. To address such issues, this paper proposes a deep learning-based Internet of Vehicles (IoV) system called DeepCrash, which includes an in-vehicle infotainment (IVI) telematics platform with a vehicle self-collision detection sensor and a front camera, a cloud-based deep learning server, and a cloud-based management platform. When a head-on or single-vehicle collision is detected, accident detection information is uploaded to the cloud-based database server for self-collision vehicle accident recognition, and a related emergency notification is provided. The experimental results show that the accuracy of traffic collision detection can reach 96% and that the average response time for emergency-related announcements is approximately 7 s.

A new strategy for millimeter-wave (mm-Wave) circuit and system synthesis, where the accuracy of electromagnetic simulations can be achieved in optimization-based design methodologies without sacrificing efficiency, is presented and tested within a real industrial project. This is done by properly partitioning the system, generating libraries of passive devices which are electromagnetically simulated prior to any circuit optimization, generating performance tradeoffs at different hierarchical levels with multiobjective optimization algorithms and hierarchically composing lower level sub-blocks. With this proposed solution, an entire mm-Wave system, from the passive component level up to the system level, has been designed and compared with the results obtained from a conventional design approach, demonstrating the outstanding capabilities of the methodology. [ABSTRACT FROM AUTHOR]

In recent years, many Advanced Driver Assistance Systems (ADAS) have been proposed and introduced under the development of sensing technology and the issue of driving safety. But many kinds of ADASs have a specific threshold to control the alarm or some support. This is decided based on the experimental or mathematical calculations in terms of the optimization of the human-machine interface of each system. But almost all of the systems (especially warning systems) have just a single threshold value to issue the warning, and the driving performance of drivers fluctuating in real time is not considered. In this study, we proposed a quantification method of riding performance and performed the logistic regression analysis for the collision prediction model based on riding performance to optimize the warning threshold of ADAS. For this study, 64 test subjects (Mean age = 22.14, S.D. = 3.71) participated in the experiments using simulator. Experiments were conducted for three risk events (left-angle collision when a rider was driving on priority road or driving on non-priority road, and right turning collision) and dummy events with the same road environment without risky situations. We proposed a quantification method of riding performance through the total sum of a product of the generalized value of riding behaviours. We also proposed the logit model, which can be constructed in terms of the collision probabilities and riding performance, which is quantified using our proposed method. In the logit model, collision occurrence was used as the dependent variable and riding performance was used as the independent variable for logistic regression analysis to clarify the condition where the probability of collision increases. Finally, we proposed a concept of the setting method of threshold value for the warning timing of ADAS according to the rider’s performance level based on collision probabilities during each riding performance.

Performance improvement of advanced driver assistance systems yields two major benefits: increasingly rapid progress towards autonomous driving and a simultaneous advance in vehicle safety. Integration of multiple advanced driver assistance systems leads to the so-called automated driving system, which can intervene jointly on braking and steering to avert impending crashes. Nevertheless, obstacles such as stationary vehicles and buildings can interpose between the opponent vehicles and the working field of advanced driver assistance systems' sensors, potentially resulting in an inevitable collision state. Currently available devices cannot properly handle an inevitable collision state, because its occurrence is not subject to evaluations by the system. In the present work, criteria for intervention on braking and steering are introduced, based on the vehicle occupants' injury risk. The system must monitor the surrounding and act on the degrees of freedom adapting to the evolution of the scenario, following an adaptive logic. The model-in-the-loop, software-in-the-loop and hardware-in-the-loop for such adaptive intervention are first introduced. To highlight the potential benefits offered by the adaptive advanced driver assistance systems, simulation software has been developed. The adaptive logic has been tested in correspondence of three inevitable collision state conditions between two motor vehicles: at each instant, the adaptive logic attitude of creating impact configurations associated with minimum injury risk is ultimately demonstrated. [ABSTRACT FROM AUTHOR]

Forward Vehicle Collision Warning (FCW) is one of the most important functions for the Advanced Driver Assistance System (ADAS). In this procedure, vehicle detection and distance measurement are core components, requiring accurate localization and estimation. In this paper, we propose a simple but efficient forward vehicle collision warning framework by aggregating monocular distance measurement and precise vehicle detection. In order to obtain forward vehicle distance, a quick camera calibration method which only needs three physical points to calibrate related camera parameters is utilized. As for the forward vehicle detection, a multi-scale detection algorithm that regards the result of calibration as distance prior is proposed to improve the precision. What's more, traditional deterministic FCW approaches cannot be personalized for different drivers, which will lead to false warnings when drivers are in diverse driving status. Therefore, abnormal driver behaviors are introduced to make FCW adaptive. Specifically, the proposed adaptive FCW generates warnings by considering the different behaviors of the driver. Intensive experiments are conducted in our established real scene dataset and the results have demonstrated the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]

In this paper, a method to generate the downward image of current vehicle location using a commercial around view monitor (AVM) is proposed. The proposed system consists of three stages, namely feature tracking, obstacle filtering, and downward view generation. In the feature tracking stage, the Shi–Tomasi corner detection is used and feature tracking is performed with a Kanade–Lucas–Tomasi (KLT) tracker to determine the transformation between AVM images. In the obstacle filtering stage, features on obstacles are filtered by using the difference in a tracking distance between features detected on the ground and features detected on the obstacle. This is performed by using a histogram based on the tracking distance of features. Finally, in the downward view generation stage, transformation between the current AVM image and the previous AVM image is obtained by using the tracked feature pair refined via the aforementioned steps. Specifically, the random sample consensus (RANSAC) method is used to obtain transformations from which the influence of outliers is removed. The downward image of the current vehicle is generated by the obtained transformation and is synthesized to the existing AVM image. The results indicate that the proposed system synthesizes the existing AVM image and the generated downward image of a vehicle in a seamless way by determining the exact pair of matching points between current and the previous AVM images. We believe the proposed system can be utilized in efficient wireless charging system and safe driving system. [ABSTRACT FROM AUTHOR]

• Many business drivers were unaware of with which ADAS their car is equipped. • Others stated owning specific ADAS in contradiction to their vehicle's specifications. • Self-reported ADAS ownership is in fact awareness of ADAS ownership. • Vehicle specifications are required to assess drivers' ADAS usage by questionnaire. Now Advanced Driver Assistant Systems (ADAS) have entered the consumer market policymakers need instruments to monitor not only the amount of ADAS-equipped cars but also whether car owners actually use these systems; a prerequisite for many ADAS to achieve road safety and/or CO 2 reduction benefits. Although questionnaires provide the most common method for large scale fleet assessment, current questionnaires fall short in their ability to assess ADAS usage. Their main pitfall is that ADAS ownership – necessary to compute the gap between ADAS ownership and usage – is based on self-reported rather than actual ADAS ownership. In other words, it is implicitly presumed that car owners are aware of the ADAS with which their car is, or is not, equipped. To our knowledge, the presumption of awareness of ADAS ownership has not been acknowledged as a limitation in current questionnaire-based studies on ADAS usage. Therefore, this paper presents a methodology to address the awareness gap by combining survey and vehicle registration analysis to assess car owners' usage of ADAS in fleets. In this method, ADAS awareness constitutes of the difference between ADAS presence based on self-report and ADAS presence based on the vehicle specifications of participants' own car (obtained through participants' licence plate registration number). To test both the assumption that an awareness gap exists for ADAS as well as the feasibility of the method itself, a survey was performed under 1355 Dutch business drivers. It involved ADAS such as Adaptive Cruise Control, Lane Departure Warning and Emergency Brake. The study showed that many business drivers were unaware of with which ADAS their car is equipped and as a result, they were unable to report they own the ADAS concerned. However, drivers aware of owning a specific system generally reported that they use it. Additionally, the study revealed another group of participants: those who stated owning a specific ADAS while their vehicle specifications contradict this. In conclusion, awareness of ADAS ownership constitutes an important link that is currently missing when concatenating market penetration studies and regular questionnaires on ADAS usage. The proposed method may overcome this shortcoming, increase the validity of surveys on ADAS usage and provide large scale insights in the use of ADAS throughout an entire fleet of vehicles. [ABSTRACT FROM AUTHOR]

Conventional autonomous emergency braking (AEB) systems derive the relative distance of a curve using a curvature calculated through an in-vehicle sensor. However, as the AEB system cannot reflect geometric factors of a curve with variable curvature, it does not accurately estimate relative distances, based on which the AEB performance is evaluated. Accordingly, an AEB system reflecting the geometric information of curves needs to be considered and developed to improve the AEB performance for curves. This study proposes a method to improve the performance of AEB systems for curves through curvilinear coordinate conversion, which is used to reflect the geometric information of roads for the navigation of an autonomous vehicle. Both the host and target vehicles are located by means of curvilinear coordinate conversion. The positions thus identified are used to calculate the relative distance and lanes. Finally, the hazard risk criterion—that is, time-to-collision (TTC)—is derived using the proposed AEB system. To demonstrate the effectiveness of the proposed AEB system, this study compares it with the conventional AEB system by analyzing the collision avoidance performance on curves through relative distances and TTC. [ABSTRACT FROM AUTHOR]

Physiological signals are immediate and sensitive to neurological changes resulting from the mental workload induced by various driving environments and are considered a quantifying tool for understanding the association between neurological outcomes and driving cognitive workloads. Neurological assessment, outside of a highly-equipped clinical setting, requires an ambulatory electroencephalography (EEG) headset. This study aimed to quantify neurological biomarkers during a resting state and two different scenarios of driving states in a virtual driving environment. We investigated the neurological responses of seventeen healthy male drivers. EEG data were measured in an initial resting state, city-roadways driving state, and expressway driving state using a portable EEG headset in a driving simulator. During the experiment, the participants drove while experiencing cognitive workloads due to various driving environments, such as road traffic conditions, lane changes of surrounding vehicles, the speed limit, etc. The power of the beta and gamma bands decreased, and the power of the delta waves, theta, and frontal theta asymmetry increased in the driving state relative to the resting state. Delta-alpha ratio (DAR) and delta-theta ratio (DTR) showed a strong correlation with a resting state, city-roadways driving state, and expressway driving state. Binary machine-learning (ML) classification models showed a near-perfect accuracy between the resting state and driving state. Moderate classification performances were observed between the resting state, city-roadways state, and expressway state in multi-class classification. An EEG-based neurological state prediction approach may be utilized in an advanced driver-assistance system (ADAS).

Advanced driver assistance systems (ADASs) are becoming increasingly common in modern-day vehicles, as they not only improve safety and reduce accidents but also aid in smoother and easier driving. ADASs rely on a variety of sensors such as cameras, radars, lidars, and a combination of sensors, to perceive their surroundings and identify and track objects on the road. The key components of ADASs are object detection, recognition, and tracking algorithms that allow vehicles to identify and track other objects on the road, such as other vehicles, pedestrians, cyclists, obstacles, traffic signs, traffic lights, etc. This information is then used to warn the driver of potential hazards or used by the ADAS itself to take corrective actions to avoid an accident. This paper provides a review of prominent state-of-the-art object detection, recognition, and tracking algorithms used in different functionalities of ADASs. The paper begins by introducing the history and fundamentals of ADASs followed by reviewing recent trends in various ADAS algorithms and their functionalities, along with the datasets employed. The paper concludes by discussing the future of object detection, recognition, and tracking algorithms for ADASs. The paper also discusses the need for more research on object detection, recognition, and tracking in challenging environments, such as those with low visibility or high traffic density.

Traffic flow data, such as flow, density and speed, are crucial for transportation planning and traffic system operation. Recently, a novel traffic state estimating method was proposed using the distance to a leading vehicle measured by an advanced driver assistance system (ADAS) camera. This study examined the effect of an ADAS camera with enhanced capabilities on traffic state estimation using image-based vehicle identification technology. Considering the realistic distance error of the ADAS camera from the field experiment, a microscopic simulation model, VISSIM, was employed with multiple underlying parameters such as the number of lanes, traffic demand, the penetration rate of ADAS vehicles and the spatiotemporal range of the estimation area. Although the enhanced functions of the ADAS camera did not affect the accuracy of the traffic state estimates significantly, the ADAS camera can be used for traffic state estimation. Furthermore, the vehicle identification distance of the ADAS camera and traffic conditions with more lanes did not always ensure better accuracy of the estimates. Instead, it is recommended that transportation planners and traffic engineering practitioners carefully select the relevant parameters and their range to ensure a certain level of accuracy for traffic state estimates that suit their purposes.

Driving intention has been widely used in intelligent driver assistance systems, automated driving systems, and electric vehicle control strategies. The accuracy, practicality, and timeliness of the driving intention identification model are its key issues. In this paper, a novel driver's braking intention identification model based on the Gaussian mixture-hidden Markov model (GHMM) and generalized growing and pruning radial basis function neural network (GGAP-RBFNN) is proposed to improve the identification accuracy of the model. The simplest brake pedal and vehicle speed data that are easily obtained from the vehicle are used as an observation sequence to improve practicality of the model. The data of the pressing brake pedal stage are used to identify the braking intention to improve the timeliness of the model. The experimental data collected from real vehicle tests are used for off-line training and online identification. The research results show that the accuracy of driver's braking intention identification model based on the GHMM/GGAP-RBFNN hybrid model is 94.69% for normal braking and 95.57% for slight braking, which are, respectively, 26.55% and 17.72% higher than achieved by the GHMM. In addition, the data of the pressing brake pedal stage are used for intention identification, which is 1.2 s faster than that of the existing identification model based on the GHMM. [ABSTRACT FROM AUTHOR]

Forward Collision Warning (FCW) is a promising Advanced Driver Assistance System (ADAS) to mitigate rear-end collisions. The deterministic FCW approaches may occasionally lead to the issuance of annoying false warnings, as they cannot be individualized for different drivers. This application oversight, which may cause the driver to deactivate the system, has been tackled with some adaptive methods. However, driver distraction, which is one of the most influential driver-specific factors on FCW warnings acceptability, has not been considered yet and is analyzed in this paper for the first time. Specifically, the adaptive FCW method proposed in this paper generates the warnings by continuously comparing Time Headway with a flexible threshold. The core of the proposed threshold updating mechanism is a real-time monitoring of the driver reactions against the previously generated warnings using the available indicators such as braking history. This method considers the driver distraction in parallel to fine-tune the calculated threshold in accordance with driver cognitive state. In order to incorporate the driver distraction in the system framework, a learning-based approach is designed which continuously estimates driver distraction by the virtue of different available Controller Area Network (CAN) bus time series, such as throttle pedal position, velocity, acceleration, and yaw rate. Neural network, as a widely adopted classification method, is nominated to detect driver distraction. The framework performance is evaluated over two realistic driving datasets. An approximately 80% false warning reduction is observed in analyzed safe scenarios, while no critical warning is missed in the dangerous ones. [ABSTRACT FROM AUTHOR]

Disabilities of the upper limb, such as hemiplegia or upper limb amputation, can limit automobile drivers to steering with one healthy arm. For the benefit of these drivers, recent studies have developed prototype interfaces that realized surface electromyography (sEMG)-controlled steering assistance with path-following accuracy that has been validated with driving simulations. In contrast, the current study expands the application of sEMG-controlled steering assistance by validating the Myo armband, a mass-produced sEMG-based interface, with respect to the path-following accuracy of a commercially available automobile. It was hypothesized that one-handed remote steering with the Myo armband would be comparable or superior to the conventional operation of the automobile steering wheel. Although results of low-speed field testing indicate that the Myo armband had lower path-following accuracy than the steering wheel during a 90° turn and wide U-turn at twice the minimum turning radius, the Myo armband had superior path-following accuracy for a narrow U-turn at the minimum turning radius and a 45° turn. Given its overall comparability to the steering wheel, the Myo armband could be feasibly applied in future automobile studies.