Lane Boundaries Research Articles

Lane Detection on Roads using Computer Vision

Lane Detection Systems which functions with the purpose to fete the lane borders on road and farther prompts the motorist if he changes and moves to wrong lane markings. Lane detecting system is an essential element of numerous technologically intelligent transport systems. Although it’s a complicate thing to reach because of scrupling road conditions that a person encounters especially while driving at night or indeed in daylight. Lane boundaries are detected using a camera that captures the view of the road, mounted on the front of the vehicle. Given a picture captured from a camera hooked up to a vehicle moving on a road during which captured road could or might not be leveled, or have easily described edges, or some former conceded patterns thereon, also road discovery from an image will be applied to hunt out the road in a picture so it might used as a place in robotization of driving system within the vehicles for moving the vehicle in precise road. In this system of chancing the road within the image prisoner by the vehicle, we're suitable to use some algorithms for vanish point discovery, exploitation Hough Transformation Space, chancing the region of interest, edge discovery exploitation canny edge discovery for road discovery. We've a tendency to use thousands of filmland of colorful roads to trainer our model so the model might notice the road as a result within the new image reused through the vehicle.

Hybrid adaptive method for lane detection of degraded road surface condition

Lane detection on roads is essential for autonomous vehicles. Most previous studies detected the area of the road and all possible lanes built on it, whereas only the specific lane that the car is currently traveling on should be detected. In addition, they are complex, slow, fail under degraded road conditions, and cannot be generalized to different scenarios. Moreover, these methods require costly hardware and under-consider road conditions. In this study, the ego lane, which is the lane a car is currently traveling on, is detected. This study proposes an adaptive hybrid lane detection method that adopts the advantages of traditional vision-based and machine-learning-based approaches. The proposed method involves a set of preprocessing methods for obtaining the candidate lane borders from an image in any degraded state. Subsequently, numerical features about the boundaries of the candidate lanes are extracted and used by a model of the k-nearest neighbor algorithm and the Gaussian process for final lane discovery. A set of experiments were conducted using the KITTI dataset to evaluate the performance. The results show that the proposed method overcomes various challenges. It is relatively simple and fast; it requires low-cost devices and processes and can be generalized without major modifications.

Study on the Design of Variable Lane Demarcation in Urban Tunnels

In order to alleviate the influence of low-speed vehicles on tunnel safety, this paper discusses the setting method of variable lane boundaries in urban tunnels. VISSIM simulation software is used to analyze the influence of low-speed vehicles on tunnel traffic flow when lane changes are allowed and when lane changes are prohibited. The results show that the influence of low-speed vehicles on the average speed of traffic flow in urban tunnels is the greatest, and the influence of low-speed vehicles on the average speed of traffic flow can be significantly alleviated when lane changes are allowed in the lane dividing line. When the speed of low-speed vehicles is 40 km/h and the variable lane is set, the average delay time is reduced by 30–50%. The existence of low-speed vehicles significantly increased the average delay time of the local lane, and the lower the vehicle speed and the greater the road traffic volume, the longer the average delay time. When the speed of low-speed vehicles is 40 km/h and the traffic volume is 1200 pcu/h, the traffic density of the right-hand lane decreases by 43.5% after the variable lane is set. While lane changing is prohibited, the presence of low-speed vehicles causes a backlog of vehicles in the rear of the lane, which leads to a significant increase in traffic density. Setting lane-changing permits can alleviate the impact of low-speed vehicles on traffic flow. The research results can provide a scientific basis for the operation and management of urban tunnels.

End-to-end human inspired learning based system for dynamic obstacle avoidance

As a first, the paper proposes modelling and learning of specific behaviors for dynamic obstacle avoidance in end-to-end motion planning. In the literature many end-to-end methods have been used in simulators to drive a car and to apply the learnt strategies to avoid the obstacles using the lane changing, following the vehicle as per the traffic rules, driving in-between the lane boundaries, and many more behaviors. The proposed method is designed to avoid obstacles in the scenarios where a dynamic obstacle is headed directly towards the robot from different directions. To avoid the critical encounter of the dynamic obstacles, we trained a novel deep neural network (DNN) with two specific behavioral obstacle avoidance strategies, namely “head-on collision avoidance” and “stop and move”. These two strategies of obstacle avoidance come from the human behavior of obstacle avoidance. Looking at the current frame only, for a very similar visual display of the scenario, the two strategies have contrasting outputs and overall outcomes that makes learning very difficult. A random data recording over general simulations is unlikely to record the corner cases of both behaviors that rarely occur, and a behavior-specific training used in this paper intensifies the same cases for a better learning of the robot in such corner cases. We calculate the intention of the obstacle, whether it will move or not. This proposed method is compared with three state-of-the-art methods of motion planning, namely Timed-Elastic Band, Dynamic Window Approach and Nonlinear Probabilistic Velocity Obstacle. The proposed method beats all the state-of-the-art methods used for comparisons.

Car-Following Dynamics, Characteristics, and Model Based on Interaction Potential Function

To model the car-following behavior more accurately, we carried out the molecular similarity analysis between the vehicles on the road and the inert gas system, comparing vehicles with microscopic particles in long and narrow pipes. The complex car-following interaction behavior is simplified into a dynamic process of the follower car that is constantly seeking to maintain the required safety distance from the leading vehicle. Through mathematical derivation of the Lennard–Jones potential function suitable for thermodynamic analysis of inert gas systems, the influence of each variable on the potential energy is clarified, and the existing problems of the existing molecular car-following model are analyzed, referring to the general Lennard–Jones potential function to build the vehicle interaction potential function. Considering the impact of the road wall potential generated by the lane boundary, a car-following model based on Lennard–Jones interaction potential is presented. The simulation test results show that compared with the existing molecular car-following model and IDM model, the average absolute error and root mean square error of the vehicle acceleration results obtained by this model and the actual data are lower, which proves that the vehicle is based on the Lennard–Jones interaction potential. The vehicle-following model based on Lennard–Jones interaction potential has a better fitting effect on the real vehicle-following behavior.

A Robust Lane Detection Method for Urban roads

Many intelligent transportation systems, such as advanced driver assistance systems (ADAS), have been being developed to increase traffic safety. ADAS have the potential to save lives and reduce crashes by eliminating the human error in driving process. The Lane detection system is designed to identify and estimate the position of lane boundaries in front of the ego-vehicle. Thus, it serves as a crucial and fundamental component in various ADAS, for instance, lane keeping assistance and lane departure warning assistance systems. In this paper, a proposed method of vision-based lane detection in urban roads is presented. First, we define a region of interest to exclude the misleading parts of the road image, then a bird’s-eye view of the road in front of the ego-vehicle is obtained by employing the inverse perspective mapping. Second, we utilize the distinct colors of lane markings to achieve robust lane markings candidate detection. Finally, the estimated lane boundaries are represented by quadratic models whose parameters are estimated from the detected lane pixels using the RANSAC algorithm. Furthermore, we present a thorough evaluation of the performance of the proposed method using the ground-truth data of the Caltech dataset and a comparative analysis between the quadratic model used and other models presented in the literature. Detection results show the effectiveness of the proposed method in detecting lane boundaries in different conditions in urban roads, including curved lanes, shadows, illumination variations and presence of street writings. Moreover, the overall process takes an average time of 30.63 milliseconds per frame.

Path Planning on Large Curvature Roads Using Driver-Vehicle-Road System Based on the Kinematic Vehicle Model

Path planning is a critical part for improving the driving safety and driver comfort of autonomous vehicles (AVs), especially in complex maneuvering conditions. In addition, different drivers have different preferences for AVs, thus, how to provide personalized trajectories for different drivers is a vital issue for AVs. The collision-free path planning problem in conditions with large road curvatures is investigated in this paper, with the consideration of environmental safety constraints, drivers’ comfort, vehicle actuator constraints, etc. Firstly, a Driver-Vehicle-Road (DVR) system is established based on the combination of the kinematic vehicle model and the two-point visual preview driver model, such that the driver's individual handling characteristics can be considered in the controller. The kinematic vehicle model is modified to have the similar understeering characteristics with those of the nonlinear full car models, and then the proposed DVR system can satisfy different groups of drivers and cars. Secondly, for environmental constraints, a new artificial potential field (APF) method is proposed, which can form a banana-shaped 3-D dangerous imaginary mountain and a lane boundary cliff suitable for arbitrary curvature roads to generate a collision-free evasive path. Finally, the Linear-Time-Varying (LTV) model predictive control (MPC) method is adopted to design the path planner. The CarSim-Simulink joint simulation illustrates that with the proposed planner, the host vehicle is capable of avoiding obstacles with a safer and more comfortable maneuver on large curvature roads. And the proposed path planner can provide individually safe trajectories for different drivers with good maneuverability.

An Enhanced System for Wrong-Way Driving Vehicle Detection with Road Boundary Detection Algorithm

Driving in the wrong direction is one of the main reasons that cause road accidents in Thailand. To efficiently detect wrong direction driving vehicles, we proposed a system that can track those moving vehicles from CCTVs using deep learning and image processing techniques. Our proposed system is composed of two main algorithms: Road Lane Boundary detection from CCTV algorithm (RLB-CCTV) and Majority-Based Correct Direction Detection algorithm (MBCDD). In this paper, we introduced the RLB-CCTV algorithm and the enhanced version of MBCDD algorithms for detecting road boundaries and wrong-direction driving vehicles. Based on our experiments, our system can identify the road lane boundary and track vehicles driving in the wrong direction on each lane with an accuracy of 96.61%.

Effect of Interactions between Vehicles and Mid-Block Crosswalks on Traffic Flow and CO2 Emission

Unsignalized mid-block raised crosswalks have been adopted as inclusive transport strategies, providing humps to reduce vehicles’ speed to promote drivers to yield to pedestrians. The interaction between vehicles and pedestrians can induce local jams that can merge to become a gridlock. The purpose of this paper is to investigate the interaction between vehicles and the mid-block raised crosswalk, analyzing its effects on traffic flow, instantaneous CO2 emissions, and energy dissipation. A pedestrian–vehicle cellular automata model was developed, where a single-lane road with a mid-block raised crosswalk is considered. The lane boundaries were controlled with the injections rate (α) and extraction rate (β), while the pedestrians’ entrance was controlled with the rate (αp). The system’s phase diagram was constructed, identifying four phases: maximum current, jamming, congestion, and gridlock. All observed phase transitions are of the second order. The transition from maximum current (or jamming) phase to gridlock phase is not noticed. Moreover, since the crosswalk is a bottleneck, the gridlock phase takes place when the pedestrians’ influx exceeds a critical value (αp > 0.8). The study also revealed that the crosswalk is the main precursor of energy dissipation and CO2 emissions, whose major effects are observed during the jamming phase.

A risk field-based metric correlates with driver’s perceived risk in manual and automated driving: A test-track study

Quantifying drivers’ perceived risk is important in the design and evaluation of the behaviour of automated vehicles (AVs) and in predicting takeovers by the driver. A ‘Driver’s Risk Field’ (DRF) function has been previously shown to be able to predict manual driving behaviour in several simulated scenarios. In this paper, we tested if the DRF-based risk estimate (rˆ) could predict manual driving behaviour and the driver’s perceived risk during automated driving. To ensure that the participants perceived realistic levels of risk, the experiment was conducted in a test vehicle. Eight participants drove five laps manually and experienced 12 different laps of automated driving on a test track. The test track consisted of three sections (which were sub-divided into 12 sectors): curve driving (9 sectors), parked car (1 sector), and 90-degree intersections (2 sectors). If the driver verbally expressed risk or performed a takeover, that particular sector was labelled as risky. The results show that the DRF risk estimate (rˆ) predicted manual driving behaviour (ρsteering=0.69, ρspeed=0.64), as well as correlated with the driver’s perceived risk in curve driving (r2 = 0.98) and while negotiating a car parked outside the lane boundary (r2=0.59). In conclusion, the DRF-based risk estimate (rˆ) is predictive of manual driving behaviour and perceived risk in automated driving. Future research should include tactical and strategic components to the driving task.

Lane Detection and Lane Departure Warning System

Lane detection is important for autonomous vehicles. For this reason, many approaches use lane boundary information to locate the vehicle inside the street, or to integrate GPS-based localization. Advanced driverassistance systems are developed to assist drivers in the driving process reducing road accidents. In this work, we present an end-to-end system for lane identification, clustering and classification, based on two cascaded neural networks, that runs in real-time. The first step is camera calibration which is used to remove the effect of lens distortion. Then a canny edge detection algorithm finds the edges of the images. Then the region of interest (ROI) is selected. The ROI is actually based on the rectangular shape appearing at the bottom of the image. ROI removes the unwanted region in the image. The potential lane markers are then determined using the Hough transform to analyze lane boundaries. Once the lane pixels are found, these pixels are continuously scanned to obtain the best linear regression analysis.It is qualified to be applied on highways and urban roadways. It also has been successfully verified in sunny, and rainy conditions for both day and night.

Hidden Markov Model of Lane-Changing-Based Car-Following Behavior on Freeways using Naturalistic Driving Data

This paper develops a methodology for simultaneously modeling lane-changing and car-following behavior of automated vehicles on freeways. Naturalistic driving data from the Safety Pilot Model Deployment (SPMD) program are used. First, a framework to process the SPMD data is proposed using various data analytics techniques including data fusion, data mining, and machine learning. Second, pairs of automated host vehicle and their corresponding front vehicle are identified along with their lane-change and car-following relationship data. Using these data, a lane-changing-based car-following (LCCF) model, which explicitly considers lane-change and car-following behavior simultaneously, is developed. The LCCF model is based on Gaussian-mixture-based hidden Markov model theory and is disaggregated into two processes: LCCF association and LCCF dissociation. These categories are based on the result of the lane change. The overall goal is to predict a driver’s lane-change intention using the LCCF model. Results show that the model can predict the lane-change event in the order of 0.6 to 1.3 s before the moment of the vehicle body across the lane boundary. In addition, the execution times of lane-change maneuvers average between 0.55 and 0.86 s. The LCCF model allows the intention time and execution time of driver’s lane-change behavior to be forecast, which will help to develop better advanced driver assistance systems for vehicle controls with respect to lane-change and car-following warning functions.

Testing and Analysis of Lane Departure Warning and Lane Keeping Assist System Response

<div class="section abstract"><div class="htmlview paragraph">Many new vehicles come equipped with Advanced Driver Assistance Systems (ADAS) as standard or optional features. These technology packages frequently include Lane Departure Warning (LDW), an electronic system designed to alert the driver when the vehicle begins to depart from its lane. These systems identify lane boundaries using computer analysis of video captured by a forward-facing camera, typically mounted near the rear-view mirror. Some vehicles are also equipped with Lane Keeping Assist (LKA). Upon detecting an unintended lane departure, LKA will make electronic steering and/or braking control inputs to keep the vehicle in its original travel lane. Four vehicles equipped with LDW and LKA were tested: a 2019 Toyota Corolla, 2019 Honda Civic, 2020 Ford Explorer, and 2019 Chevrolet Tahoe. Tests were conducted on a straight, flat road with clear lane markings. Lane departures to the left and to the right were initiated by the test driver at 45 and 65 mph. Using a VBOX 3i RTK DGPS, data related to the vehicle’s speed, acceleration, and driver- and software-related control inputs were collected via the vehicle’s CAN bus. Additionally, the VBOX collected vehicle location data of ±2 cm (±0.79 in) accuracy relative to survey points. Analysis of test data yielded details of system-level behaviors. For LDW, the average warning issue point (lateral distance prior to reaching the lane boundary) observed was 1.33 ft, the average rate of departure (lateral velocity) was 1.45 ft/s, and the warning occurred 0.76 sec before lane departure. Lane keeping actions began, on average, 1.13 ft from the lane boundary (0.66 sec before lane departure) and involved 4.81 degrees of steering with an average maximum lateral acceleration of 2.86 ft/s<sup>2</sup> (0.09 g). The LKA systems tested permitted the vehicles’ outside tires to exceed the lane boundaries by an average of 0.14 ft.</div></div>

Multi-Lane Detection and Tracking Using Temporal-Spatial Model and Particle Filtering

Since vision-based methods are vulnerable to challenging environmental conditions such as bad whether, shadows, occlusions and illumination, robustness is important. In this paper, a robust algorithm for detecting and tracking multiple lanes with arbitrary shape is proposed. We extend previous lane detection and tracking processes from the spatial domain to the temporal-spatial domain using our more robust and general multiple lane model. Distinct from traditional image pre-processing procedures, we adopt slice images generated from image sequence decomposition and reconstruction that contains important structured historical information. In this domain, we propose assumptions to reduce the algorithm’s complexity and computation further. First, instead of common binarization, a more general lane marker detector is proposed with weak constraints to obtain cleaner binary image. Then, the lane marker candidates are used as the initialization of following particle filtering tracking process. We propose a confidence map computed from binary slice images by using an improved distance transform for particles sampling and weights calculation. The multi-lane model supports the use of multiple independent particle filters for tracking each lane boundary separately. Finally, a range of experimental results on testing dataset indicate that the proposed algorithm is effective with high performance and comparing with other methods, it has better tolerance to challenging environments.

Moment-based multi-lane detection and tracking

Lane-detection methods are still facing robustness issues when confronted with challenging road surfaces, road markings and illumination conditions. Such combined challenges occur infrequently but are crucial for driving safety. Although advanced learning-based methods (using deep learning) demonstrate an impressive performance, they rely on plenty of training images for varying scenes and their performance is limited for scenes not covered by the training data. Also, multi-lane detection is indispensable for determining the exact position of both ego-car and surrounding vehicles as well as lane changing behavior on the road. In this paper we propose a new multi-lane detection algorithm, detecting all visible lane boundaries in front of the ego-car. In contrast to the Hough transforms often used for lane boundaries detection, our approach uses moments to calculate the deflection angles and the centroids of lane segments, achieving more precise lane boundaries. We propose a novel algorithm based on moments and Kalman filtering to achieve lane tracking. State-of-the-art neural-network-based methods are compared with the proposed method concretely. Experimental results show that our method outperforms other (recently published) multi-lane detection algorithms regarding detection rate as well as accuracy.

Practical limitations of lane detection algorithm based on Hough transform in challenging scenarios

The vision-based road lane detection technique plays a key role in driver assistance system. While existing lane recognition algorithms demonstrated over 90% detection rate, the validation test was usually conducted on limited scenarios. Significant gaps still exist when applied in real-life autonomous driving. The goal of this article was to identify these gaps and to suggest research directions that can bridge them. The straight lane detection algorithm based on linear Hough transform (HT) was used in this study as an example to evaluate the possible perception issues under challenging scenarios, including various road types, different weather conditions and shades, changed lighting conditions, and so on. The study found that the HT-based algorithm presented an acceptable detection rate in simple backgrounds, such as driving on a highway or conditions showing distinguishable contrast between lane boundaries and their surroundings. However, it failed to recognize road dividing lines under varied lighting conditions. The failure was attributed to the binarization process failing to extract lane features before detections. In addition, the existing HT-based algorithm would be interfered by lane-like interferences, such as guardrails, railways, bikeways, utility poles, pedestrian sidewalks, buildings and so on. Overall, all these findings support the need for further improvements of current road lane detection algorithms to be robust against interference and illumination variations. Moreover, the widely used algorithm has the potential to raise the lane boundary detection rate if an appropriate search range restriction and illumination classification process is added.

Temporal evolution of small-scale internetwork magnetic fields in the solar photosphere

Context. While the longitudinal field that dominates in photospheric network regions has been studied extensively, small-scale transverse fields have recently been found to be ubiquitous in the quiet internetwork photosphere and this merits further study. Furthermore, few observations have been able to capture how this field evolves. Aims. We aim to statistically characterize the magnetic vector in a quiet Sun internetwork region and observe the temporal evolution of specific small-scale magnetic features. Methods. We present two high spatio-temporal resolution observations that reveal the dynamics of two disk-centre internetwork regions taken by the new GREGOR Infrared Spectrograph Integral Field Unit with the highly magnetically sensitive photospheric Fe I line pair at 15648.52 Å and 15652.87 Å. We record the full Stokes vector and apply inversions with the Stokes inversions based on response functions code to retrieve the parameters characterizing the atmosphere. We consider two inversion schemes: scheme 1 (S1), where a magnetic atmosphere is embedded in a field free medium, and scheme 2 (S2), with two magnetic models and a fixed 30% stray light component. Results. The magnetic properties produced from S1 inversions returned a median magnetic field strength of 200 and 240 G for the two datasets, respectively. We consider the median transverse (horizontal) component, among pixels with Stokes Q or U, and the median unsigned longitudinal (vertical) component, among pixels with Stokes V, above a noise threshold. We determined the former to be 263 G and 267 G, and the latter to be 131 G and 145 G, for the two datasets, respectively. Finally, we present three regions of interest, tracking the dynamics of small-scale magnetic features. We apply S1 and S2 inversions to specific profiles of interest and find that the latter produces better approximations when there is evidence of mixed polarities. We find patches of linear polarization with magnetic flux density of the order of 130−150 G and find that linear polarization appears preferentially at granule-intergranular lane boundaries. The weak magnetic field appears to be organized in terms of complex ‘loop-like’ structures, with transverse fields often flanked by opposite polarity longitudinal fields.

Comparative Safety Assessment of Automated Driving Strategies at Highway Merges in Mixed Traffic

We present a simulation-based approach to assess the safety impacts of vehicles equipped with Automated Driving Systems (ADS) in mixed traffic with Human-driven Vehicles (HV). Specifically, we compare two generic longitudinal strategies of ADS to handle a cut-in: Reactive ADS acting only when the cut-in vehicle crosses the target lane boundary, and Predictive ADS acting at the onset of the cut-in manoeuvre. We identify their distinctive effects on the traffic safety under cut-in maneuvers of adjacent human-driven vehicles at highway merges. We employ a microscopic traffic flow simulator that describes the lane changing process with high detail, accounting for the vehicle interaction and consequent trajectory updates. These high-resolution trajectories are post-processed to estimate a set of relevant surrogate measures of safety. By analyzing these measures, we find that the predictive ADS significantly outperforms the reactive ADS in aspects such as temporal proximity to crash, expected crash severity and the driving risk (combining the two aspects), and the number of aborted lane changes by HV. The negative safety impact of reactive ADS becomes prominent at penetration rate >10%. The major difference between the two ADS approaches appears in the dynamics of risk during the lane changing. When a vehicle cuts in ahead of Reactive ADS, the risk peaks approximately halfway through the maneuver; whereas with Predictive ADS the risk remains marginal throughout. This work demonstrates the potential of simulation-based safety assessment to differentiate the safety impacts of automation functionalities at an early stage of product development.

Novel dual‐layer‐oriented strategy for fully automated vehicles’ lane‐keeping system

A novel concept of a dual-layer-oriented control strategy for fully automated vehicles’ lane-keeping system is proposed which consists of an inner controller with a modified preview driver model and an outer cooperative copilot controller. With designed weighting function of displacement error based on a hyperbolic tangent and adjustable preview horizon according to road geometry, the inner controller is supposed to track the lane centreline precisely and efficiently through optimal control framework. The outer controller is specially designed for situations where the vehicle may run out of the lane and cause a collision. Only when the vehicle is at high risk of lane-crossing, the outer controller is activated to guide the vehicle back to lane centreline by exerting proper steering command, which is calculated by solving a model predictive control-based constrained optimisation problem with a designed quadratic cost function. Finally, simulation tests based on CarSim-Matlab joint platform are carried out to verify the proposed strategy. Results demonstrate that the modified preview driver model is able to improve path following performance and the dual-layer-oriented control strategy with less computational burden can effectively prevent the vehicle from crossing lane boundaries.

Autonomous Lane Keeping System: Lane Detection, Tracking and Control on Embedded System

Autonomous lane keeping system is the key technique to autonomous driving. It includes lane detection, lane tracking and control. It has been developed enormously, but it is still a challenge work due to different factors such as illumination, general hyper-parameters setting for different road condition and lane boundary correction. In addition, due to imbalance on accuracy and processing time, it is hard to conduct in embedding system. In this study, an autonomous lane keeping system is developed based on deep learning. First, a lane detection and tracking system is designed, which is robust to lane boundary correction. Especially for lane detection, a light-weight network named as LaneFCNet is proposed, which can balance accuracy and processing time. Then, lane tracking was followed by detector to improve the detection performance and create autonomous driving trajectory. Finally, to brief lane fitting problem, it was treated as ridge regression problem, which can enhance the effectiveness to the whole system. Experimental results show that our integrated lane detection and tracking system can trade off accuracy and processing time and the whole line keeping system is robust enough to autonomous driving.