Lane Departure Warning System Research Articles

Modeling commercial vehicle drivers’ acceptance of advanced driving assistance system (ADAS)

PurposeAdvanced driving assistance system (ADAS) has been applied in commercial vehicles. This paper aims to evaluate the influence factors of commercial vehicle drivers’ acceptance on ADAS and explore the characteristics of each key factors. Two most widely used functions, forward collision warning (FCW) and lane departure warning (LDW), were considered in this paper.Design/methodology/approachA random forests algorithm was applied to evaluate the influence factors of commercial drivers’ acceptance. ADAS data of 24 commercial vehicles were recorded from 1 November to 21 December 2018, in Jiangsu province. Respond or not was set as dependent variables, while six influence factors were considered.FindingsThe acceptance rate for FCW and LDW systems was 69.52% and 38.76%, respectively. The accuracy of random forests model for FCW and LDW systems is 0.816 and 0.820, respectively. For FCW system, vehicle speed, duration time and warning hour are three key factors. Drivers prefer to respond in a short duration during daytime and low vehicle speed. While for LDW system, duration time, vehicle speed and driver age are three key factors. Older drivers have higher respond probability under higher vehicle speed, and the respond time is longer than FCW system.Originality/valueFew research studies have focused on the attitudes of commercial vehicle drivers, though commercial vehicle accidents were proved to be more severe than passenger vehicles. The results of this study can help researchers to better understand the behavior of commercial vehicle drivers and make corresponding recommendations for ADAS of commercial vehicles.

Research of algorithms for road marking recognition in the lane departure warning system

The way to improve the safety of vehicles using ADAS systems has successfully proved itself in practice. The use of ADAS systems in vehicles is mandatory in many countries of the world and is accepted at the state level. One of the most widely used ADAS systems is the Lane Departure Warning System (LDWS). The paper describes the principles of operation of existing LDWS in the segment of light commercial vehicles (LCV). The algorithm and structure of the developed LDWS for the GAZelle Next vehicle are presented. The description and analysis of algorithms for recognition of road markings are given. The results and comparative analysis of virtual and road tests of the LDWS are presented. Conclusions are given on the operation of the system and the algorithm for recognizing road markings.

Advanced Driver Assistant System

Road accidents are the most terrifying thing that can happen to a driver. Worst of all, we refuse to learn from our mistakes along the way. The majority of road users are aware of the general rules and safety measures to take while on the road but injuries and crashes are caused by the negligence of road users. The most common cause of accidents and collision is human error. The aim of this project is to automate and improve the safety of vehicles. Lane Departure Warning System (LDWS) and Emergency Driver Assist System (EDAS) are described in this paper. The LDWS uses camera to track lane markers to see if the driver is drifting accidentally. In this project, whenever the vehicle is moving out of the lane, the device gives the driver a warning in the form of audio or visual signal. Whenever the driver's attention deviates from driving activity for a particular interval of time, EDAS alerts the driver.

Testing the Robustness of Commercial Lane Departure Warning Systems

Assessment methods are needed to rate the performances of advanced driver assistance systems in a range of real-world conditions, enabling the possibility of mandating minimum performance requirements beyond standardized, regulatory pass-or-fail tests, and ultimately ensuring a real and objectively measurable safety benefit. To bridge the gap between regulatory and real-world performance, this work presents a novel robustness assessment methodology and defines a robustness index determined from regulatory tests to analyze the real-world performance of lane departure warning (LDW) systems. In this context, a robust system means that it is insensitive to changes in driving conditions or environmental conditions. Distance to line (DTL) and time to line crossing (TTLC) were calculated for a light truck and a passenger car, and a black box model of the LDW systems was developed to predict their performance over different lane markings, drifting directions, and vehicle lateral and longitudinal speeds. During the test, neither of the vehicles triggered warning in around 10% of the trials despite the perfect condition of the markings painted on the proving ground. The type of lane marking significantly influenced DTL for both vehicles. For the light truck, the drifting direction, marking type, and their interaction were found to be statistically significant, which resulted in a lower robustness index than that of the passenger car. For both vehicles, TTLC was inversely proportional to the lateral speed, which greatly influences crash avoidance.

Field effectiveness of general motors advanced driver assistance and headlighting systems

This study examined the field effectiveness of General Motors advanced driver assistance and headlighting systems. A total of 8,311,707 Model Year 2013–2019 vehicles were matched to police-reported crashes from 12 states. The quasi-induced exposure method was used to compare system-relevant and system-irrelevant (control) crash counts for equipped and unequipped vehicles. Logistic regression was used to adjust for ten covariates. Results indicated fusion/radar Automatic Emergency Braking, camera Automatic Emergency Braking, and Forward Collision Alert systems reduced rear-end striking crashes by 45%, 38%, and 20%, respectively. When restricting data to crashes in which someone in the General Motors striking vehicle was injured, these reductions were elevated to 59%, 54%, and 31%, respectively, providing evidence of additional crash mitigation benefits. Similarly, the Lane Keep Assist with Lane Departure Warning and Lane Departure Warning (alone) systems provided 12% and 10% reductions in lane departure crashes, respectively, with corresponding benefits in the injury analysis increasing to 19% and 18%, respectively. The Lane Change Alert with Side Blind Zone Alert system reduced lane change crashes by 16%. Reverse Automatic Braking, Rear Cross Traffic Alert, Rear Park Assist, and Rear Vision Camera (where each of these systems generally included all of the preceding systems) produced, respectively, an 82%, 55%, 36%, and 24% reduction in backing crashes. For Front Pedestrian Braking, a non-significant 14% reduction was observed for the limited set of available pedestrian crash cases. Intellibeam (auto high beam headlighting), High-Intensity Discharge headlights, and the combination of these two systems provided 26%, 11%, and 32% reductions (relative to halogen headlights) in a combined set of (unlighted) nighttime animal, pedestrian, and bicyclist crashes, respectively. These results provide widespread evidence of the substantial crash avoidance and injury reduction opportunities afforded by the production systems evaluated, as well as identify untapped system opportunities for moving toward a zero crashes vision.

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.

Lane detection under artificial colored light in tunnels and on highways: an IoT-based framework for smart city infrastructure

Lane detection (LD) under different illumination conditions is a vital part of lane departure warning system and vehicle localization which are current trends in the future smart cities. Recently, vision-based methods are proposed to detect lane markers in different road situations including abnormal marker cases. However, an inclusive framework for driverless cars has not been introduced yet. In this work, a novel LD and tracking method is proposed for the autonomous vehicle in the IoT-based framework (IBF). The IBF consists of three modules which are vehicle board (VB), cloud module (CM), and the vehicle remote controller. The LD and tracking are carried out initially by the VB, and then, in case of any failure, the whole set of data is passed to CM to be processed and the results are sent to the VB to perform the appropriate action. If the CM detects a lane departure, then the autonomous vehicle is driven remotely and the VB would be restarted. In addition to the proposed framework, an illumination invariance method is presented to detect lane markers under different light conditions. The simulation results with real-life data demonstrate lane-keeping rates of 95.3% and 95.2% in tunnels and on highways, respectively. The approximate processing time of the proposed method is 31 ms/frame which fulfills the real-time requirements.

Vision-based Lane Departure Warning System


 
 
 Vision-based Lane Departure Warning System (LDW) is a promising tool to avoid road accidents. In practice, it is exceptionally hard to accurately and efficiently detect lanes due a variety of complex noise such as environmental variability. However, image processing techniques have shown promising and reliable outcome in detecting lanes during non- ideal conditions. Lane detection and lane departure measurement are two important modules in LDW system. This paper explores the gaps and limitations of the existing method in the past 10 years concerning lane detection and departure warning for LDW system.
 
 

Using ADAS to Future-Proof Roads-Comparison of Fog Line Detection from an In-Vehicle Camera and Mobile Retroreflectometer.

Pavement markings are used to convey positioning information to both humans and automated driving systems. As automated driving is increasingly being adopted to support safety, it is important to understand how successfully sensor systems can interpret these markings. In this effort, an in-vehicle lane departure warning system was compared to data collected simultaneously from an externally mounted mobile retroreflectometer. The test, performed over 200 km of driving on three different routes in variable lighting conditions and road classes found that, depending on conditions, the retroreflectometer could predict whether the car’s lane departure systems would detect markings in 92% to 98% of cases. The test demonstrated that automated driving systems can be used to monitor the state of pavement markings and can provide input on how to design and maintain road infrastructure to support automated driving features. Since data about the condition of lane marking from multiple lane departure warning systems (crowd-sourced data) can provide input into the pavement marking management systems operated by many road owners, these findings also indicate that these automated driving sensors have an important role in enhancing the maintenance of pavement markings.

Modern methods of field tests of driver assist systems

In view of stringent vehicle safety requirements the automakers are urged to develop and implement electronic driver assist systems (ADAS). However, before starting the mass production, one has to make sure that these systems function correctly and efficiently. The current level of technologies, the simulation modelling allows debugging and testing of operation algorithms for electronic ‘assistants’ in laboratory conditions thereby reducing the costs of the prototype production. This approach is employed at intermediate development stages of the system. At the final stage the ‘traditional’ approach (field tests) is used by the automobile manufacturers, the reason being that the algorithm operation has to be tested in real conditions, and the certification of vehicles with ADAS functionality using methods of simulation modelling is not provided in current state standards. Keeping this in view, the problem arises of creating a measuring unit for geolocation of the vehicle with precision accuracy and synchronized video recording from multiple cameras simultaneously. This article presents the solution developed by employees from NNSTU n.a. R. E. Alekseev as regards the development of such a test system: a schematic diagram of the system is developed; the system is installed on a light commercial vehicle being tested; the system efficiency is checked. The system performance was checked when testing blind spot detectors, lane departure warning system and parking assistant.

Implementation of Dark and Raining Environmental Conditions to Investigate Lane Support System Performance for Passenger Cars in Southeast Asia: Case Study for Malaysian Domestic Road

This paper presents a study on the implementation of dark and raining environment test conditions to investigate Lane Support System (LSS) performance for passenger cars in Southeast Asia. The case study has been performed for Malaysian domestic roads. LSS systems involved have been the Lane Departure Warning (LDW) and Lane Keep Assist (LKA). The literature review conducted has revealed that there is not yet a similar study performed for vehicle LSS system. The motivation of this study has been to identify the effect of both environmental conditions on the vehicle LSS performance. This pioneering work is also aimed to help in establishing a new LSS test protocol that could reflect better the driving situations in Southeast Asia countries. The experimental works have been carried out at state road in Melaka, Malaysia. LSS on-road test parameters have been adopted from LSS test protocols from the European New Car Assessment Programme (Euro NCAP) and the Japan National Agency for Automotive Safety and Victim’s Aid (NASVA). A new test procedure to carry out the study has been also developed in this study in order to complement the referred test protocols, including customized rain-making testing equipment to simulate the raining environment conditions. Results from the study have showed that both LDW and LKA systems performance could successfully be evaluated when subjected to dark and raining environment conditions using the new test procedure. Furthermore, the new test procedure developed in this study is also highly applicable for implementation in future LSS on-road tests involving any type of road category (both domestic and highway) with minimal setting up process.

MTSAN: Multi-Task Semantic Attention Network for ADAS Applications

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.

Influence of Difference in Luminance between Traffic Lane Dividing Lines and Road Surface on Detection Performance of Lane Departure Warning System

Influence of Difference in Luminance between Traffic Lane Dividing Lines and Road Surface on Detection Performance of Lane Departure Warning System

Fast and robust approaches for lane detection using multi‐camera fusion in complex scenes

Due to the limited sensing ability with the single-view camera and the real-time requirement for multi-view scenarios or deep learning-based methods in complex scenes, the output of lane detection is not applicable for the actual lane departure warning system. To tackle this challenge, the authors propose a fast and robust approach for lane detection based on well-designed multi-camera fusion, integrating vanishing point estimation, and specified feature fitting strategies. To meet real-time demand, several simple but effective image processing means are introduced and improved. Concretely, on account of statistical information, the authors’ method carries out an improved region of interest selection to speed up the detection. Afterwards, they used the B-spline fitting lane line on the strength of the RANdom SAmple consensus algorithm for the front view image detection and improved the Hough algorithm for the two rear-view images correspondingly. Using coordinate conversion and self-designed fusion strategy, they get the robust lane information based on symmetrical lane detection from the left/right sides of both front and side views. Experimental results in newly introduced multi-camera scenarios show that their multi-camera fusion framework contributes to significant improvement in accuracy and robustness in comparison with traditional methods.

Innovative lane detection method to increase the accuracy of lane departure warning system

Lane departure warning is one important feature in Advanced Driver Assistance Systems (ADAS), which aims to improve overall safety on the road. However, challenges such as inconsistent shadows and fading lane markings often plague the road surface and cause the lane detection system to produce false warnings. Users are aggravated by the warning and tend to disable this safety feature. This paper proposes an efficient Gabor filtering-based lane detection method to overcome the aforementioned conditions and improves the accuracy of lane departure warning system. Furthermore, it serves as a cost-effective solution to a lane departure warning problem, allowing it to be widely deployed. It is heuristically found that lane marking has a general directional property, which can be further enhanced by Gabor filter while suppressing inconsistent road shadows and road markers. Enhanced lane markings are then subjected to adaptive canny edge detection to extract distinct edge markings. Lastly, Hough transformation is applied to label the correct lane candidates on the road surface. Furthermore, we generate a dataset of Malaysia road with various driving conditions. As a proof of concept, a lane departure warning system is built based on the proposed lane detection method, which is able to achieve an accuracy of 93.67% for lane detection and 95.24% for lane departure warning tested on our challenging dataset. The codes are implemented on Raspberry pi 3B and installed in a vehicle for real-time application. The codes are multithreaded and found to achieve a desirable frame speed of 20 fps at 75% CPU utilization.

Rumble Strips: A Human Factors Perspective towards a Sustainable Road System

Prior research substantiates the belief that human factors contribute to up to 90% of all traffic accidents. The failure to consider cognitive ergonomics in road safety initiatives will continue to cause traffic fatality, especially on straight roads. Since drivers and road safety practitioners cannot wholly avoid driver’s non-compliance, skill-based errors, and mistakes, road designs should aim to reduce the severity of repercussions resulting from human errors. For example, in the case of a momentary lapse of attention leading to lane departure, drivers should be able to correct their maneuvers. A human-centered traffic system approach of road design may reduce the severity of accidents caused by human error. An investigation of road crashes in Malaysia conducted by the Malaysian Institute of Road Safety Research revealed that 66% of road crashes in Malaysia are opposite-direction head-on crashes and run-off-road (roadway departure) crashes. Installing Lane Departure Warning System such as Centerline Rumble Strips (CLRS) and Shoulder Rumble Strips (SRS) can reduce these types of crashes and compensate human errors on the road. Rumble strips alert drivers that they are deviating from their lane by providing both tactile and auditory warnings. Although the effectiveness of rumble strips is well documented in prior researches, the practice of installing rumble strips is still scarce in Malaysia. This paper highlights how rumble strips can mitigate the consequences of the human errors, in the hope that the information can help road safety researchers, authorities, and practitioners move forward in the implementation of interventions towards sustainable road system.

Lane Departure Warning and Lane Keep Assist Assessment based on Southeast Asian Environmental Conditions: Preliminary Investigation


 
 
 Lane Departure Warning (LDW) and Lane Keep Assist (LKA) systems are part of the Advanced Driver-Assistance Systems (ADAS), which are equipped in the latest passenger vehicles sold in the Southeast Asia (SEA) countries. Both technologies are very beneficial to gain improved safety performance for vehicle occupants and benefiting other road users such as pedestrians and cyclists by alerting the driver and making automatic trajectory correction when the vehicle is deviating away from the correct path while in motion. Nevertheless, there is yet any test protocol established by the New Car Assessment Program for Southeast Asian Countries (ASEAN NCAP) to evaluate both technologies tailored to the SEA’s environmental conditions. Hence, this is a preliminary investigation of the new test protocol developed for LDW and LKA based on SEA’s environmental conditions. The proposed protocol incorporated the effect of both dry and wet conditions, which is unique to simulate the main weather elements in the region. On-road tests using actual passenger vehicles were conducted using a rain simulator to simulate the rainy weather. The preliminary tests were performed on straight road conditions. Results show that the proposed protocol was able to assess the effectiveness of LDW and LKA in both dry and wet conditions. Further actions shall be carried out in the later stage of this project to validate the proposed protocol using other vehicle models sold in SEA that equipped with similar technologies.
 
 

Design of Lane Departure Warning System Based on Fuzzy Control Mode of Android System

Aiming at the unconscious lane departure behavior in the process of driving, a design scheme of lane departure warning system based on Android is proposed. STM32F103C8T6 is selected as the main control chip and CAN bus communication technology is used to collect vehicle information such as vehicle speed, steering angle and steering signal. Then Bluetooth module is used to transmit the data to the mobile phone for real-time processing. Taking GB/T 26773-2011 (Performance Requirements and Test Methods for Lane Departure Alarm System) as the design standard, the lane departure rate ε and the time T when the right front wheel crosses the lane line are considered as the input of the two-dimensional fuzzy controller, and the early warning level W is considered as the output. When the driving deviation angle is 5°, the interval of the lane departure rate ε is [0.75,1.35], and the interval of T is [0,1.5]. After normalized parameter processing, a certain fuzzy interval is set according to the driving habits of different vehicle drivers, and the fuzzy control algorithm with improved membership function is adopted for control, so as to improve the recognition rate of lane lines, reduce the early warning misjudgement rate and reduce the incidence of traffic accidents.

Advanced Driver Assistance System

The prime motive of the automobile industry is to improve safety in driving machines and avoid accidents. Traffic rules and regulations drafted by the law aren’t followed by many citizens. This is another reason for an accident. Accidents sometimes are unintentional. Some serious acts like drunk and drive, ignoring the signboards, and over speeding might result in severe causalities. To prevent situations like these we seek the Advanced Driver Assistance System (ADAS). ADAS has the potential to increase safety and provide comfort driving. Driving situations are electronically controlled and decisions are simplified for the driver. Old people may also receive plenty of benefits from this technology. ADAS is designed with a human-machine interface which tends to improve road safety marginally. Accidents caused by human error can also be minimized. ADAS helps the driver to automate, adapt and enhance the vehicle system for safe driving. Passive safety technologies like wearing seatbelts and airbags cannot prevent road fatalities. Modern technology like ADAS is different from traditional and passive technology and minimizes the fatalities consistently. ADAS also alert the driver of potential problems and helps in maintaining the stability of the vehicle under critical circumstances. Safety features are implemented to take control of the vehicle during collisions. ADAS relies on inputs from multiple sources like the brake assistant, pressure control system, lane departure warning system, road sign identification, etc. Additional features can also be customized based on the needs of the driver. In this paper methods to prevent over speeding, vehicle collisions, and driver alertness systems are discussed. RFID readers are used for sensing the speed limit in the signboards. The speed of the vehicle is managed based on the reading obtained from the tags. Sensors like ultrasonic, alcohol detector, gas sensor, temperature sensor are used to measure other parameters to enhance the safety measure while driving.

Test Scenario Generation and Optimization Technology for Intelligent Driving Systems

In this paper, we propose a new scenario generation algorithm called Combinatorial Testing Based on Complexity (CTBC) based on both combinatorial testing (CT) method and Test Matrix (TM) technique for intelligent driving systems. To guide the generation procedure in the algorithm and evaluate the validity of the generated scenarios, we further propose a concept of complexity of test scenario. CTBC considers both overall scenario complexity and cost of testing, and the reasonable balance between them can be found by using the Bayesian optimization algorithm on account of the black box property of CTBC. The effectiveness of this method is validated by applying it to the lane departure warning (LDW) system on a hardware-in-the-loop (HIL) test platform. The result shows that the bigger the complexity index is, the easier it is to reveal system defects. Furthermore, the proposed algorithm can significantly improve the integrated complexity of the generated test scenarios while ensuring the coverage, which can help to find potential faults of the system more and faster, and further enhance the test efficiency.