RESUMO
Effective lane detection technology plays an important role in the current autonomous driving system. Although deep learning models, with their intricate network designs, have proven highly capable of detecting lanes, there persist key areas requiring attention. Firstly, the symmetry inherent in visuals captured by forward-facing automotive cameras is an underexploited resource. Secondly, the vast potential of position information remains untapped, which can undermine detection precision. In response to these challenges, we propose FF-HPINet, a novel approach for lane detection. We introduce the Flipped Feature Extraction module, which models pixel pairwise relationships between the flipped feature and the original feature. This module allows us to capture symmetrical features and obtain high-level semantic feature maps from different receptive fields. Additionally, we design the Hierarchical Position Information Extraction module to meticulously mine the position information of the lanes, vastly improving target identification accuracy. Furthermore, the Deformable Context Extraction module is proposed to distill vital foreground elements and contextual nuances from the surrounding environment, yielding focused and contextually apt feature representations. Our approach achieves excellent performance with the F1 score of 97.00% on the TuSimple dataset and 76.84% on the CULane dataset.
RESUMO
Nowadays, most trajectory prediction algorithms have difficulty simulating actual traffic behavior, and there is still a problem of large prediction errors. Therefore, this paper proposes a multi-object trajectory prediction algorithm based on lane information and foresight information. A Hybrid Dilated Convolution module based on the Channel Attention mechanism (CA-HDC) is developed to extract features, which improves the lane feature extraction in complicated environments and solves the problem of poor robustness of the traditional PINet. A lane information fusion module and a trajectory adjustment module based on the foresight information are developed. A socially acceptable trajectory with Generative Adversarial Networks (S-GAN) is developed to reduce the error of the trajectory prediction algorithm. The lane detection accuracy in special scenarios such as crowded, shadow, arrow, crossroad, and night are improved on the CULane dataset. The average F1-measure of the proposed lane detection has been increased by 4.1% compared to the original PINet. The trajectory prediction test based on D2-City indicates that the average displacement error of the proposed trajectory prediction algorithm is reduced by 4.27%, and the final displacement error is reduced by 7.53%. The proposed algorithm can achieve good results in lane detection and multi-object trajectory prediction tasks.
RESUMO
Lane detection plays a pivotal role in the successful implementation of Advanced Driver Assistance Systems (ADASs), which are essential for detecting the road's lane markings and determining the vehicle's position, thereby influencing subsequent decision making. However, current deep learning-based lane detection methods encounter challenges. Firstly, the on-board hardware limitations necessitate an exceptionally fast prediction speed for the lane detection method. Secondly, improvements are required for effective lane detection in complex scenarios. This paper addresses these issues by enhancing the row-anchor-based lane detection method. The Transformer encoder-decoder structure is leveraged as the row classification enhances the model's capability to extract global features and detect lane lines in intricate environments. The Feature-aligned Pyramid Network (FaPN) structure serves as an auxiliary branch, complemented by a novel structural loss with expectation loss, further refining the method's accuracy. The experimental results demonstrate our method's commendable accuracy and real-time performance, achieving a rapid prediction speed of 129 FPS (the single prediction time of the model on RTX3080 is 15.72 ms) and a 96.16% accuracy on the Tusimple dataset-a 3.32% improvement compared to the baseline method.
RESUMO
As an indispensable part of the vehicle environment perception task, road traffic marking detection plays a vital role in correctly understanding the current traffic situation. However, the existing traffic marking detection algorithms still have some limitations. Taking lane detection as an example, the current detection methods mainly focus on the location information detection of lane lines, and they only judge the overall attribute of each detected lane line instance, thus lacking more fine-grained dynamic detection of lane line attributes. In order to meet the needs of intelligent vehicles for the dynamic attribute detection of lane lines and more perfect road environment information in urban road environment, this paper constructs a fine-grained attribute detection method for lane lines, which uses pixel-level attribute sequence points to describe the complete attribute distribution of lane lines and then matches the detection results of the lane lines. Realizing the attribute judgment of different segment positions of lane instances is called the fine-grained attribute detection of lane lines (Lane-FGA). In addition, in view of the lack of annotation information in the current open-source lane data set, this paper constructs a lane data set with both lane instance information and fine-grained attribute information by combining manual annotation and intelligent annotation. At the same time, a cyclic iterative attribute inference algorithm is designed to solve the difficult problem of lane attribute labeling in areas without visual cues such as occlusion and damage. In the end, the average accuracy of the proposed algorithm reaches 97% on various types of lane attribute detection.
RESUMO
Lane detection is a vital component of intelligent driving systems, offering indispensable functionality to keep the vehicle within its designated lane, thereby reducing the risk of lane departure. However, the complexity of the traffic environment, coupled with the rapid movement of vehicles, creates many challenges for detection tasks. Current lane detection methods suffer from issues such as low feature extraction capability, poor real-time detection, and inadequate robustness. Addressing these issues, this paper proposes a lane detection algorithm that combines an online re-parameterization ResNet with a hybrid attention mechanism. Firstly, we replaced standard convolution with online re-parameterization convolution, simplifying the convolutional operations during the inference phase and subsequently reducing the detection time. In an effort to enhance the performance of the model, a hybrid attention module is incorporated to enhance the ability to focus on elongated targets. Finally, a row anchor lane detection method is introduced to analyze the existence and location of lane lines row by row in the image and output the predicted lane positions. The experimental outcomes illustrate that the model achieves F1 scores of 96.84% and 75.60% on the publicly available TuSimple and CULane lane datasets, respectively. Moreover, the inference speed reaches a notable 304 frames per second (FPS). The overall performance outperforms other detection models and fulfills the requirements of real-time responsiveness and robustness for lane detection tasks.
RESUMO
Lane detection is a crucial task in the field of autonomous driving, as it enables vehicles to safely navigate on the road by interpreting the high-level semantics of traffic signs. Unfortunately, lane detection is a challenging problem due to factors such as low-light conditions, occlusions, and lane line blurring. These factors increase the perplexity and indeterminacy of the lane features, making them hard to distinguish and segment. To tackle these challenges, we propose a method called low-light enhancement fast lane detection (LLFLD) that integrates the automatic low-light scene enhancement network (ALLE) with the lane detection network to improve lane detection performance under low-light conditions. Specifically, we first utilize the ALLE network to enhance the input image's brightness and contrast while reducing excessive noise and color distortion. Then, we introduce symmetric feature flipping module (SFFM) and channel fusion self-attention mechanism (CFSAT) to the model, which refine the low-level features and utilize more abundant global contextual information, respectively. Moreover, we devise a novel structural loss function that leverages the inherent prior geometric constraints of lanes to optimize the detection results. We evaluate our method on the CULane dataset, a public benchmark for lane detection in various lighting conditions. Our experiments show that our approach surpasses other state of the arts in both daytime and nighttime settings, especially in low-light scenarios.
RESUMO
Lane detection is one of the most fundamental problems in the rapidly developing field of autonomous vehicles. With the dramatic growth of deep learning in recent years, many models have achieved a high accuracy for this task. However, most existing deep-learning methods for lane detection face two main problems. First, most early studies usually follow a segmentation approach, which requires much post-processing to extract the necessary geometric information about the lane lines. Second, many models fail to reach real-time speed due to the high complexity of model architecture. To offer a solution to these problems, this paper proposes a lightweight convolutional neural network that requires only two small arrays for minimum post-processing, instead of segmentation maps for the task of lane detection. This proposed network utilizes a simple lane representation format for its output. The proposed model can achieve 93.53% accuracy on the TuSimple dataset. A hardware accelerator is proposed and implemented on the Virtex-7 VC707 FPGA platform to optimize processing time and power consumption. Several techniques, including data quantization to reduce data width down to 8-bit, exploring various loop-unrolling strategies for different convolution layers, and pipelined computation across layers, are optimized in the proposed hardware accelerator architecture. This implementation can process at 640 FPS while consuming only 10.309 W, equating to a computation throughput of 345.6 GOPS and energy efficiency of 33.52 GOPS/W.
RESUMO
Lane detection in driving situations is a critical module for advanced driver assistance systems (ADASs) and automated cars. Many advanced lane detection algorithms have been presented in recent years. However, most approaches rely on recognising the lane from a single or several images, which often results in poor performance when dealing with extreme scenarios such as intense shadow, severe mark degradation, severe vehicle occlusion, and so on. This paper proposes an integration of steady-state dynamic equations and Model Predictive Control-Preview Capability (MPC-PC) strategy to find key parameters of the lane detection algorithm for automated cars while driving on clothoid-form roads (structured and unstructured roads) to tackle issues such as the poor detection accuracy of lane identification and tracking in occlusion (e.g., rain) and different light conditions (e.g., night vs. daytime). First, the MPC preview capability plan is designed and applied in order to maintain the vehicle on the target lane. Second, as an input to the lane detection method, the key parameters such as yaw angle, sideslip, and steering angle are calculated using a steady-state dynamic and motion equations. The developed algorithm is tested with a primary (own dataset) and a secondary dataset (publicly available dataset) in a simulation environment. With our proposed approach, the mean detection accuracy varies from 98.7% to 99%, and the detection time ranges from 20 to 22 ms under various driving circumstances. Comparison of our proposed algorithm's performance with other existing approaches shows that the proposed algorithm has good comprehensive recognition performance in the different dataset, thus indicating desirable accuracy and adaptability. The suggested approach will help advance intelligent-vehicle lane identification and tracking and help to increase intelligent-vehicle driving safety.
RESUMO
For autonomous driving, it is imperative to perform various high-computation image recognition tasks with high accuracy, utilizing diverse sensors to perceive the surrounding environment. Specifically, cameras are used to perform lane detection, object detection, and segmentation, and, in the absence of lidar, tasks extend to inferring 3D information through depth estimation, 3D object detection, 3D reconstruction, and SLAM. However, accurately processing all these image recognition operations in real-time for autonomous driving under constrained hardware conditions is practically unfeasible. In this study, considering the characteristics of image recognition tasks performed by these sensors and the given hardware conditions, we investigated MTL (multi-task learning), which enables parallel execution of various image recognition tasks to maximize their processing speed, accuracy, and memory efficiency. Particularly, this study analyzes the combinations of image recognition tasks for autonomous driving and proposes the MDO (multi-task decision and optimization) algorithm, consisting of three steps, as a means for optimization. In the initial step, a MTS (multi-task set) is selected to minimize overall latency while meeting minimum accuracy requirements. Subsequently, additional training of the shared backbone and individual subnets is conducted to enhance accuracy with the predefined MTS. Finally, both the shared backbone and each subnet undergo compression while maintaining the already secured accuracy and latency performance. The experimental results indicate that integrated accuracy performance is critically important in the configuration and optimization of MTL, and this integrated accuracy is determined by the ITC (inter-task correlation). The MDO algorithm was designed to consider these characteristics and construct multi-task sets with tasks that exhibit high ITC. Furthermore, the implementation of the proposed MDO algorithm, coupled with additional SSL (semi-supervised learning) based training, resulted in a significant performance enhancement. This advancement manifested as approximately a 12% increase in object detection mAP performance, a 15% improvement in lane detection accuracy, and a 27% reduction in latency, surpassing the results of previous three-task learning techniques like YOLOP and HybridNet.
RESUMO
For self-driving systems or autonomous vehicles (AVs), accurate lane-level localization is a important for performing complex driving maneuvers. Classical GNSS-based methods are usually not accurate enough to have lane-level localization to support the AV's maneuvers. LiDAR-based localization can provide accurate localization. However, the price of LiDARs is still one of the big issues preventing this kind of solution from becoming wide-spread commodity. Therefore, in this work, we propose a low-cost solution for lane-level localization using a vision-based system and a low-cost GPS to achieve high precision lane-level localization. Experiments in real-world and real-time demonstrate that the proposed method achieves good lane-level localization accuracy, outperforming solutions based on only GPS.
RESUMO
Lane detection plays a vital role in making the idea of the autonomous car a reality. Traditional lane detection methods need extensive hand-crafted features and post-processing techniques, which make the models specific feature-oriented, and susceptible to instability for the variations on road scenes. In recent years, Deep Learning (DL) models, especially Convolutional Neural Network (CNN) models have been proposed and utilized to perform pixel-level lane segmentation. However, most of the methods focus on achieving high accuracy while considering structured roads and good weather conditions and do not put emphasis on testing their models on defected roads, especially ones with blurry lane lines, no lane lines, and cracked pavements, which are predominant in the real world. Moreover, many of these CNN-based models have complex structures and require high-end systems to operate, which makes them quite unsuitable for being implemented in embedded devices. Considering these shortcomings, in this paper, we have introduced a novel CNN model named LLDNet based on an encoder-decoder architecture that is lightweight and has been tested in adverse weather as well as road conditions. A channel attention and spatial attention module are integrated into the designed architecture to refine the feature maps for achieving outstanding results with a lower number of parameters. We have used a hybrid dataset to train our model, which was created by combining two separate datasets, and have compared the model with a few state-of-the-art encoder-decoder architectures. Numerical results on the utilized dataset show that our model surpasses the compared methods in terms of dice coefficient, IoU, and the size of the models. Moreover, we carried out extensive experiments on the videos of different roads in Bangladesh. The visualization results exhibit that our model can detect the lanes accurately in both structured and defected roads and adverse weather conditions. Experimental results elicit that our designed method is capable of detecting lanes accurately and is ready for practical implementation.
Assuntos
Automóveis , Aprendizado Profundo , Processamento de Imagem Assistida por Computador/métodos , Redes Neurais de Computação , Análise Espectral Raman , Tempo (Meteorologia)RESUMO
Accurate lane detection is an essential function of dynamic traffic perception. Though deep learning (DL) based methods have been widely applied to lane detection tasks, such models rarely achieve sufficient accuracy in low-light weather conditions. To improve the model accuracy in foggy conditions, a new approach was proposed based on monocular depth prediction and an atmospheric scattering model to generate fog artificially. We applied our method to the existing CULane dataset collected in clear weather and generated 107,451 labeled foggy lane images under three different fog densities. The original and generated datasets were then used to train state-of-the-art (SOTA) lane detection networks. The experiments demonstrate that the synthetic dataset can significantly increase the lane detection accuracy of DL-based models in both artificially generated foggy lane images and real foggy scenes. Specifically, the lane detection model performance (F1-measure) was increased from 11.09 to 70.41 under the heaviest foggy conditions. Additionally, this data augmentation method was further applied to another dataset, VIL-100, to test the adaptability of this approach. Similarly, it was found that even when the camera position or level of brightness was changed from one dataset to another, the foggy data augmentation approach is still valid to improve model performance under foggy conditions without degrading accuracy on other weather conditions. Finally, this approach also sheds light on practical applications for other complex scenes such as nighttime and rainy days.
Assuntos
Condução de Veículo , Acidentes de Trânsito , Algoritmos , Coleta de Dados , Tempo (Meteorologia)RESUMO
(1) Background: Due to its high safety potential, one of the most common ADAS technologies is the lane support system (LSS). The main purpose of LSS is to prevent road accidents caused by road departure or entrance in the lane of other vehicles. Such accidents are especially common on rural roads during nighttime. In order for LSS to function properly, road markings should be properly maintained and have an adequate level of visibility. During nighttime, the visibility of road markings is determined by their retroreflectivity. The aim of this study is to investigate how road markings' retroreflectivity influences the detection quality and the view range of LSS. (2) Methods: An on-road investigation comprising measurements using Mobileye and a dynamic retroreflectometer was conducted on four rural roads in Croatia. (3) Results: The results show that, with the increase of markings' retroreflection, the detection quality and the range of view of Mobileye increase. Additionally, it was determined that in "ideal" conditions, the minimal value of retroreflection for a minimum level 2 detection should be above 55 mcd/lx/m2 and 88 mcd/lx/m2 for the best detection quality (level 3). The results of this study are valuable to researchers, road authorities and policymakers.
Assuntos
Acidentes de Trânsito , Condução de Veículo , Acidentes de Trânsito/prevenção & controle , Croácia , Coleta de Dados , TecnologiaRESUMO
With the emerging interest of autonomous vehicles (AV), the performance and reliability of the land vehicle navigation are also becoming important. Generally, the navigation system for passenger car has been heavily relied on the existing Global Navigation Satellite System (GNSS) in recent decades. However, there are many cases in real world driving where the satellite signals are challenged; for example, urban streets with buildings, tunnels, or even underpasses. In this paper, we propose a novel method for simultaneous vehicle dead reckoning, based on the lane detection model in GNSS-denied situations. The proposed method fuses the Inertial Navigation System (INS) with learning-based lane detection model to estimate the global position of vehicle, and effectively bounds the error drift compared to standalone INS. The integration of INS and lane model is accomplished by UKF to minimize linearization errors and computing time. The proposed method is evaluated through the real-vehicle experiments on highway driving, and the comparative discussions for other dead-reckoning algorithms with the same system configuration are presented.
Assuntos
Condução de Veículo , Sistemas de Informação Geográfica , Algoritmos , Reprodutibilidade dos TestesRESUMO
It is desirable to maintain high accuracy and runtime efficiency at the same time in lane detection. However, due to the long and thin properties of lanes, extracting features with both strong discrimination and perception abilities needs a huge amount of calculation, which seriously slows down the running speed. Therefore, we design a more efficient way to extract the features of lanes, including two phases: (1) Local feature extraction, which sets a series of predefined anchor lines, and extracts the local features through their locations. (2) Global feature aggregation, which treats local features as the nodes of the graph, and builds a fully connected graph by adaptively learning the distance between nodes, the global feature can be aggregated through weighted summing finally. Another problem that limits the performance is the information loss in feature compression, mainly due to the huge dimensional gap, e.g., from 512 to 8. To handle this issue, we propose a feature compression module based on decoupling representation learning. This module can effectively learn the statistical information and spatial relationships between features. After that, redundancy is greatly reduced and more critical information is retained. Extensional experimental results show that our proposed method is both fast and accurate. On the Tusimple and CULane benchmarks, with a running speed of 248 FPS, F1 values of 96.81% and 75.49% were achieved, respectively.
Assuntos
BenchmarkingRESUMO
Lane detection is a significant technology for autonomous driving. In recent years, a number of lane detection methods have been proposed. However, the performance of fast and slim methods is not satisfactory in sophisticated scenarios and some robust methods are not fast enough. Consequently, we proposed a fast and robust lane detection method by combining a semantic segmentation network and an optical flow estimation network. Specifically, the whole research was divided into three parts: lane segmentation, lane discrimination, and mapping. In terms of lane segmentation, a robust semantic segmentation network was proposed to segment key frames and a fast and slim optical flow estimation network was used to track non-key frames. In the second part, density-based spatial clustering of applications with noise (DBSCAN) was adopted to discriminate lanes. Ultimately, we proposed a mapping method to map lane pixels from pixel coordinate system to camera coordinate system and fit lane curves in the camera coordinate system that are able to provide feedback for autonomous driving. Experimental results verified that the proposed method can speed up robust semantic segmentation network by three times at most and the accuracy fell 2% at most. In the best of circumstances, the result of the lane curve verified that the feedback error was 3%.
RESUMO
The quality of detected lane lines has a great influence on the driving decisions of unmanned vehicles. However, during the process of unmanned vehicle driving, the changes in the driving scene cause much trouble for lane detection algorithms. The unclear and occluded lane lines cannot be clearly detected by most existing lane detection models in many complex driving scenes, such as crowded scene, poor light condition, etc. In view of this, we propose a robust lane detection model using vertical spatial features and contextual driving information in complex driving scenes. The more effective use of contextual information and vertical spatial features enables the proposed model more robust detect unclear and occluded lane lines by two designed blocks: feature merging block and information exchange block. The feature merging block can provide increased contextual information to pass to the subsequent network, which enables the network to learn more feature details to help detect unclear lane lines. The information exchange block is a novel block that combines the advantages of spatial convolution and dilated convolution to enhance the process of information transfer between pixels. The addition of spatial information allows the network to better detect occluded lane lines. Experimental results show that our proposed model can detect lane lines more robustly and precisely than state-of-the-art models in a variety of complex driving scenarios.
RESUMO
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.
RESUMO
There are over four million miles of roads in the United States, and the prioritization of locations to perform maintenance activities typically relies on human inspection or semi-automated dedicated vehicles. Pavement markings are used to delineate the boundaries of the lane the vehicle is driving within. These markings are also used by original equipment manufacturers (OEM) for implementing advanced safety features such as lane keep assist (LKA) and eventually autonomous operation. However, pavement markings deteriorate over time due to the fact of weather and wear from tires and snowplow operations. Furthermore, their performance varies depending upon lighting (day/night) as well as surface conditions (wet/dry). This paper presents a case study in Indiana where over 5000 miles of interstate were driven and LKA was used to classify pavement markings. Longitudinal comparisons between 2020 and 2021 showed that the percentage of lanes with both lines detected increased from 80.2% to 92.3%. This information can be used for various applications such as developing or updating standards for pavement marking materials (infrastructure), quantifying performance measures that can be used by automotive OEMs to warn drivers of potential problems with identifying pavement markings, and prioritizing agency pavement marking maintenance activities.
Assuntos
Acidentes de Trânsito , Condução de Veículo , Acidentes de Trânsito/prevenção & controle , Humanos , Tempo (Meteorologia)RESUMO
Lane detection and tracking in a complex road environment is one of the most important research areas in highly automated driving systems. Studies on lane detection cover a variety of difficulties, such as shadowy situations, dimmed lane painting, and obstacles that prohibit lane feature detection. There are several hard cases in which lane candidate features are not easily extracted from image frames captured by a driving vehicle. We have carefully selected typical scenarios in which the extraction of lane candidate features can be easily corrupted by road vehicles and road markers that lead to degradations in the understanding of road scenes, resulting in difficult decision making. We have introduced two main contributions to the interpretation of road scenes in dense traffic environments. First, to obtain robust road scene understanding, we have designed a novel framework combining a lane tracker method integrated with a camera and a radar forward vehicle tracker system, which is especially useful in dense traffic situations. We have introduced an image template occupancy matching method with the integrated vehicle tracker that makes it possible to avoid extracting irrelevant lane features caused by forward target vehicles and road markers. Second, we present a robust multi-lane detection by a tracking algorithm that incudes adjacent lanes as well as ego lanes. We verify a comprehensive experimental evaluation with a real dataset comprised of problematic road scenarios. Experimental result shows that the proposed method is very reliable for multi-lane detection at the presented difficult situations.