Search

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. [ABSTRACT FROM AUTHOR]

Lane detection is a crucial visual perception task in the field of autonomous driving, serving as one of the core modules in advanced driver assistance systems (ADASs).To address the insufficient real-time performance of current segmentation-based models and the conflict between the demand for high inference speed and the excessive parameters in resource-constrained edge devices (such as onboard hardware, mobile terminals, etc.) in complex real-world scenarios, this paper proposes an efficient and lightweight auxiliary branch network (CBGA-Auxiliary) to tackle these issues. Firstly, to enhance the model's capability to extract feature information in complex scenarios, a row anchor-based feature extraction method based on global features was adopted. Secondly, employing ResNet as the backbone network and CBGA (Conv-Bn-GELU-SE Attention) as the fundamental module, we formed the auxiliary segmentation network, significantly enhancing the segmentation training speed of the model. Additionally, we replaced the standard convolutions in the branch network with lightweight GhostConv convolutions. This reduced the parameters and computational complexity while maintaining accuracy. Finally, an additional enhanced structural loss function was introduced to compensate for the structural defect loss issue inherent in the row anchor-based method, further improving the detection accuracy. The model underwent extensive experimentation on the Tusimple dataset and the CULane dataset, which encompass various road scenarios. The experimental results indicate that the model achieved the highest F1 scores of 96.1% and 71.0% on the Tusimple and CULane datasets, respectively. At a resolution of 288 × 800, the ResNet18 and ResNet34 models achieved maximum inference speeds of 410FPS and 280FPS, respectively. Compared to existing SOTA models, it demonstrates a significant advantage in terms of inference speed. The model achieved a good balance between accuracy and inference speed, making it suitable for deployment on edge devices and validates the effectiveness of the model. [ABSTRACT FROM AUTHOR]

Decision-level information fusion methods using radar and vision usually suffer from low target matching success rates and imprecise multi-target detection accuracy. Therefore, a robust target detection algorithm based on the fusion of frequency-modulated continuous wave (FMCW) radar and a monocular camera is proposed to address these issues in this paper. Firstly, a lane detection algorithm is used to process the image to obtain lane information. Then, two-dimensional fast Fourier transform (2D-FFT), constant false alarm rate (CFAR), and density-based spatial clustering of applications with noise (DBSCAN) are used to process the radar data. Furthermore, the YOLOv5 algorithm is used to process the image. In addition, the lane lines are utilized to filter out the interference targets from outside lanes. Finally, multi-sensor information fusion is performed for targets in the same lane. Experiments show that the balanced score of the proposed algorithm can reach 0.98, which indicates that it has low false and missed detections. Additionally, the balanced score is almost unchanged in different environments, proving that the algorithm is robust. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

In this paper, we introduce PortLaneNet, an optimized lane detection model specifically designed for the unique challenges of enclosed container terminal environments. Unlike conventional lane detection scenarios, this model addresses complexities such as intricate ground markings, tire crane lane lines, and various types of regional lines that significantly complicate detection tasks. Our approach includes the novel Scene Prior Perception Module, which leverages pre-training to provide essential prior information for more accurate lane detection. This module capitalizes on the enclosed nature of container terminals, where images from similar area scenes offer effective prior knowledge to enhance detection accuracy. Additionally, our model significantly improves understanding by integrating both high- and low-level image features through attention mechanisms, focusing on the critical components of lane detection. Through rigorous experimentation, PortLaneNet has demonstrated superior performance in port environments, outperforming traditional lane detection methods. The results confirm the effectiveness and superiority of our model in addressing the complex challenges of lane detection in such specific settings. Our work provides a valuable reference for solving lane detection issues in specialized environments and proposes new ideas and directions for future research. [ABSTRACT FROM AUTHOR]

Recent advancements in optical and electronic sensor technologies, coupled with the proliferation of computing devices (such as GPUs), have enabled real-time autonomous driving systems to become a reality. Hence, research in algorithmic advancements for advanced driver assistance systems (ADASs) is rapidly expanding, with a primary focus on enhancing robust lane detection capabilities to ensure safe navigation. Given the widespread adoption of cameras on the market, lane detection relies heavily on image data. Recently, CNN-based methods have attracted attention due to their effective performance in lane detection tasks. However, with the expansion of the global market, the endeavor to achieve reliable lane detection has encountered challenges presented by diverse environmental conditions and road scenarios. This paper presents an approach that focuses on detecting lanes in road areas traversed by vehicles equipped with cameras. In the proposed method, a U-Net based framework is employed for training, and additional lane-related information is integrated into a four-channel input data format that considers lane characteristics. The fourth channel serves as the edge attention map (E-attention map), helping the modules achieve more specialized learning regarding the lane. Additionally, the proposition of an approach to assign weights to the loss function during training enhances the stability and speed of the learning process, enabling robust lane detection. Through ablation experiments, the optimization of each parameter and the efficiency of the proposed method are demonstrated. Also, the comparative analysis with existing CNN-based lane detection algorithms shows that the proposed training method demonstrates superior performance. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Lane detection, a crucial component of autonomous driving systems, is in charge of precise lane location to ensure that cars navigate lanes appropriately. However, in challenging conditions like shadows and extreme lighting, lanes may become obstructed or blurred, posing a significant challenge to the lane-detection task as the model struggles to extract sufficient visual information from the image. The current anchor-based lane-detection network detects lanes in complex scenes by mapping anchors to images to extract features and calculating the relationship between each anchor and other anchors for feature fusion. However, it is insufficient for anchors to extract subtle features from images, and there is no guarantee that the information carried by each anchor is valid. Therefore, this study proposes the adaptive cross-scale ROI fusion network (ACSNet) to fully extract the features in the image so that the anchor carries more useful information. ACSNet selects important anchors in an adaptive manner and fuses these important anchors with the original anchors across scales. Through this feature extraction method, the features of different field-of-view ranges under complex road surfaces can be learned, and diversified features can be integrated to ensure that lanes can be well detected under complex road surfaces such as shadows and extreme lighting. Furthermore, due to the slender structure of lane lines, there are relatively few useful features in the images. Therefore, this study also proposes a Three-dimensional Coordinate Attention Mechanism (TDCA) to enhance image features. The Three-dimensional Coordinate Attention Mechanism extensively explores relationships among features in the row, column, and spatial dimensions. It calculates feature weights for each of these dimensions and ultimately performs element-wise multiplication with the entire feature map. Experimental results demonstrate that our network achieves excellent performance on the existing public datasets, CULane and Tusimple. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

In order to address the issue of environmental perception in autonomous driving on structured roads, we propose MultiNet-GS, a convolutional neural network model based on an encoder–decoder architecture that tackles multiple tasks simultaneously. We use the main structure of the latest object detection model, the YOLOv8 model, as the encoder structure of our model. We introduce a new dynamic sparse attention mechanism, BiFormer, in the feature extraction part of the model to achieve more flexible computing resource allocation, which can significantly improve the computational efficiency and occupy a small computational overhead. We introduce a lightweight convolution, GSConv, in the feature fusion part of the network, which is used to build the neck part into a new slim-neck structure so as to reduce the computational complexity and inference time of the detector. We also add an additional detector for tiny objects to the conventional three-head detector structure. Finally, we introduce a lane detection method based on guide lines in the lane detection part, which can aggregate the lane feature information into multiple key points, obtain the lane heat map response through conditional convolution, and then describe the lane line through the adaptive decoder, which effectively makes up for the shortcomings of the traditional lane detection method. Our comparative experiments on the BDD100K dataset on the embedded platform NVIDIA Jetson TX2 show that compared with SOTA(YOLOPv2), the mAP@0.5 of the model in traffic object detection reaches 82.1%, which is increased by 2.7%. The accuracy of the model in drivable area detection reaches 93.2%, which is increased by 0.5%. The accuracy of the model in lane detection reaches 85.7%, which is increased by 4.3%. The Params and FLOPs of the model reach 47.5 M and 117.5, which are reduced by 6.6 M and 8.3, respectively. The model achieves 72 FPS, which is increased by 5. Our MultiNet-GS model has the highest detection accuracy among the current mainstream models while maintaining a good detection speed and has certain superiority. [ABSTRACT FROM AUTHOR]

The autonomous driving market has experienced rapid growth in recent times. From systems that assist drivers in keeping within their lanes to systems that recognize obstacles using sensors and then handle those obstacles, there are various types of systems in autonomous driving. The sensors used in autonomous driving systems include infrared detection devices, lidar, ultrasonic sensors, and cameras. Among these sensors, cameras are widely used. This paper proposes a method for stable lane detection from images captured by camera sensors in diverse environments. First, the system utilizes a bilateral filter and multiscale retinex (MSR) with experimentally optimized set parameters to suppress image noise while increasing contrast. Subsequently, the Canny edge detector is employed to detect the edges of the lane candidates, followed by utilizing the Hough transform to make straight lines from the land candidate images. Then, using a proposed restriction system, only the two lines that the current vehicle is actively driving within are detected from the candidate lines. Furthermore, the lane position information from the previous frame is combined with the lane information from the current frame to correct the current lane position. The Kalman filter is then used to predict the lane position in the next frame. The proposed lane-detection method was evaluated in various scenarios, including rainy conditions, low-light nighttime environments with minimal street lighting, scenarios with interfering guidelines within the lane area, and scenarios with significant noise caused by water droplets on the camera. Both qualitative and quantitative experimental results demonstrate that the lane-detection method presented in this paper effectively suppresses noise and accurately detects the two active lanes during driving. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Lane detection is a common task in computer vision that involves identifying the boundaries of lanes on a road from an image or a video. Improving the accuracy of lane detection is of great help to advanced driver assistance systems and autonomous driving that help cars to identify and keep in the correct lane. Current high-accuracy models of lane detection are mainly based on artificial neural networks. Among them, CLRNet is the latest famous model, which attains high lane detection accuracy. However, in some scenarios, CLRNet attains lower lane detection accuracy, and we revealed that this is caused by insufficient global dependence information. In this study, we enhanced CLRNet and proposed a new model called NonLocal CLRNet (NLNet). NonLocal is an algorithmic mechanism that captures long-range dependence. NLNet employs NonLocal to acquire more long-range dependence information or global information and then applies the acquired information to a Feature Pyramid Network (FPN) in CLRNet for improving lane detection accuracy. Using the CULane dataset, we trained NLNet. The experimental results showed that NLNet outperformed state-of-the-art models in terms of accuracy in most scenarios, particularly in the no-line scenario and night scenario. This study is very helpful for developing more accurate lane detection models. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Semantic image segmentation is used to analyse visual content and carry out real-time decision-making. This narrative literature analysis evaluates the multiple innovations and advancements in the semantic algorithm-based architecture by presenting an overview of the algorithms used in medical image analysis, lane detection, and face recognition. Numerous groundbreaking works are examined from a variety of angles (e.g., network structures, algorithms, and the problems addressed). A review of the recent development in semantic segmentation networks, such as U-Net, ResNet, SegNet, LCSegnet, FLSNet, and GNet, is presented with evaluation metrics across a range of applications to facilitate new research in this field. [ABSTRACT FROM AUTHOR]

Container terminal automation offers many potential benefits, such as increased productivity, reduced cost, and improved safety. Autonomous trucks can lead to more efficient container transport. A novel lane detection method is proposed using score-based generative modeling through stochastic differential equations for image-to-image translation. Image processing techniques are combined with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Genetic Algorithm (GA) to ensure fast and accurate lane positioning. A robust lane detection method can deal with complicated detection problems in realistic road scenarios. The proposed method is validated by a dataset collected from the port terminals under different environmental conditions; in addition, the robustness of the lane detection method with stochastic noise is tested. [ABSTRACT FROM AUTHOR]

Lane detection is necessary for developing intelligent Autonomous Vehicles (AVs). Using vision-based lane detection is more cost-effective, requiring less operational power. Images captured by the moving vehicle include varying brightness, blur, and occlusion caused due to diverse locations. We propose a Vision-based Ingenious Lane Departure Warning System (VILDS) for AV to address these challenges. The Generative Adversarial Networks (GAN) of the VILDS choose the most precise features to create images that are identical to the original but have better clarity. The system also uses Long Short-Term Memory (LSTM) to learn the average behavior of the samples to forecast lanes based on a live feed of processed images, which predicts incomplete lanes and increases the reliability of the AV's trajectory. Further, we devise a strategy to improve the Lane Departure Warning System (LDWS) by determining the angle and direction of deviation to predict the AV's Lane crossover. An extensive evaluation of the proposed VILDS system demonstrated the effective working of the lane detection and departure warning system modules with an accuracy of 98.2% and 96.5%, respectively. [ABSTRACT FROM AUTHOR]

Visual navigation is an important guidance method for industrial automated guided vehicles (AGVs). In the actual guidance, the overexposure environment may be encountered by the AGV lane image, which seriously reduces the accuracy of lane detection. Although the image segmentation method based on deep learning is widely used in lane detection, it cannot solve the problem of overexposure of lane images. At the same time, the requirements of segmentation accuracy and inference speed cannot be met simultaneously by existing segmentation networks. Aiming at the problem of incomplete lane segmentation in an overexposure environment, a lane detection method combining image inpainting and image segmentation is proposed. In this method, the overexposed lane image is repaired and reconstructed by the MAE network, and then the image is input into the image segmentation network for lane segmentation. In addition, a convolutional skip triple attention (CSTA) image segmentation network is proposed. CSTA improves the inference speed of the model under the premise of ensuring high segmentation accuracy. Finally, the lane segmentation performance of the proposed method is evaluated in three image segmentation evaluation metrics (IoU, F1-score, and PA) and inference time. Experimental results show that the proposed CSTA network has higher segmentation accuracy and faster inference speed. [ABSTRACT FROM AUTHOR]

Lane detection is an essential module for the safe navigation of autonomous vehicles (AVs). Estimating the vehicle's position and trajectory on the road is critical; however, several environmental variables can affect this task. State-of-the-art lane detection methods utilize convolutional neural networks (CNNs) as feature extractors to obtain relevant features through training using multiple kernel layers. It makes them vulnerable to any statistical change in the input data or noise affecting the spatial characteristics. In this paper, we compare six different CNN architectures to analyze the effect of various adverse conditions, including harsh weather, illumination variations, and shadows/occlusions, on lane detection. Among all the aforementioned adverse conditions, harsh weather in general and snowy night conditions particularly affect the performance by a large margin. The average detection accuracy of the networks decreased by 75.2%, and the root mean square error (RMSE) increased by 301.1%. Overall, the results show a noticeable drop in the networks' accuracy for all adverse conditions because the features' stochastic distributions change for each state. [ABSTRACT FROM AUTHOR]

Around 1.3 million people worldwide die each year because of road traffic crashes. There are many reasons which cause accidents, and driving in the wrong direction is one of them. In our research, we developed an autonomous framework called WrongWay-LVDC that detects wrong-way driving vehicles from closed-circuit television (CCTV) videos. The proposed WrongWay-LVDC provides several helpful features such as lane detection, correct direction validation, detecting wrong-way driving vehicles, and image capturing features. In this work, we proposed three main contributions: first, the improved algorithm for road lane boundary detection on CCTV (called improved RLB-CCTV) using the image processing technique. Second is the Distance-Based Direction Detection (DBDD) algorithm that uses the deep learning method, where the system validates and detects wrong-driving vehicles. Lastly, the Inside Boundary Image (IBI) capturing feature algorithm captures the most precise shot of the wrong-way-of-driving vehicles. As a result, the framework can run continuously and output the reports for vehicles' driving behaviors in each area. The accuracy of our framework is 95.23%, as we tested with several CCTV videos. Moreover, the framework can be implemented on edge devices with real-time speed for functional implementation and detection in various areas. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Lane detection is one of the most basic and essential tasks for autonomous vehicles. Therefore, the fast and accurate recognition of lanes has become a hot topic in industry and academia. Deep learning based on a neural network is also a common method for lane detection. However, due to the huge computational burden of the neural network, its real-time performance is often difficult to meet the requirements in the fast-changing actual driving scenes. A lightweight network combining the Squeeze-and-Excitation block and the Self-Attention Distillation module is proposed in this paper, which is based on the existing deeplabv3plus network and specifically improves its real-time performance. After experimental verification, the proposed network achieved 97.49% accuracy and 60.0% MIOU at a run time of 8.7 ms, so the network structure achieves a good trade-off between real-time performance and accuracy. [ABSTRACT FROM AUTHOR]

Lane detection, as a basic environmental perception task, plays a significant role in the safety of automatic driving. Modern lane detection methods have obtained a better performance in most scenarios, but many are unsatisfactory in various scenarios, with a weak appearance (e.g., serious vehicle occlusion, dark shadows, ambiguous markings, etc.), and have issues in simplifying model predictions and flexibly detecting lanes of a non-fixed structure and number. In this work, we abstracted the lane lines as a series of discrete key points and proposed a lane detection method of parallel multi-scale feature aggregation based on key points, FPLane. The main task of FPLane is to focus on the precise location of key points in the global lanes and aggregate the global detection results into the local geometric modeling of lane lines by using the idea of association embedding. Furthermore, this work proposes the parallel Multi-scale Feature Aggregation network (MFANet) in FPLane integrating the context information of multi-scale feature mappings to take full advantage of the prior information of adjacent positions. In addition, MFANet incorporates the Double-headed Attention Feature Fusion Up-sampling module, which can facilitate the network to accurately recognize and detect objects under extreme scale variation. Finally, our method is tested on Tusimple and CULane lane detection datasets; the results show that the proposed method outperforms the current mainstream methods: the accuracy and F1-score of the model are 96.82% and 75.6%, respectively, and the real-time detection efficiency of the model can maintain 28 ms. [ABSTRACT FROM AUTHOR]

Automotive companies have studied the development of lane support systems in order to secure the Euro New Car Assessment Program (NCAP)'s high score. A front camera module is applied with safety assistance systems in an intelligent vehicle. However, the front camera module has limitations in terms of backlight conditions, entering or exiting tunnels, and night driving because of lower image quality. In this paper, we propose an integrated camera with dual light sensor for improving lane detection performance under the worst conditions. We include a new algorithm to enhance image data quality and improve edge detection and lane tracking using illumination information. We evaluate the tests under various conditions on a real road. These tests are performed on 728 km of road (under various external situations and lane types) for false alarm rates. The experimental results show that the system is promising in terms of reliability, enhancement, and improvements. [ABSTRACT FROM AUTHOR]

Lane detection is an important and challenging part of autonomous driver assistance systems and other advanced assistance systems. The presence of road potholes and obstacles, complex road environments (illumination, occlusion, etc.) are ubiquitous, will cause the blur of images, which is captured by the vision perception system in the lane detection task. To improve the lane detection accuracy of blurred images, a network (Lane-GAN) for lane line detection is proposed in the paper, which is robust to blurred images. First, real and complex blur kernels are simulated to construct a blurred image dataset, and the improved GAN network is used to reinforce the lane features of the blurred image, and finally the feature information is further enriched with a recurrent feature transfer aggregator. Extensive experimental results demonstrate that the proposed network can get robust detection results in complex environments, especially for blurred lane lines. Compared with the SOTA detector, the proposed detector achieves a larger gain. The proposed method can enhance the lane detail features of the blurred image, improving the detection accuracy of the blurred lane effectively, in the driver assistance system in high speed and complex road conditions. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Featured Application: The system proposed in this paper provides a new idea for the recognition algorithm of road environments in safety-assisted driving systems, and subsequently improves the existing algorithm to reduce the computational cost and improve accuracy. With recent developments in the field of autonomous driving, recognition algorithms for road environments are being developed very rapidly. Currently, most of the network models have good recognition rates, but as the accuracy rate increases, the models become more complex and thus lack real-time performance. Therefore, there is an urgent need to propose a lightweight recognition system for road environments to assist autonomous driving. We propose a lightweight road environment recognition system with two different detection routes based on the same backbone network for objects and lane lines. The proposed approach uses MobileNet as the backbone network to acquire the feature layer, and our improved YOLOv4 and U-Net allows the number of parameters of the model to be greatly reduced and combined with the improved attention mechanism. The lightweight residual convolutional attention network (LRCA-Net) proposed in this work allows the network to adaptively pay attention to the feature details that need attention, which improves the detection accuracy. Finally, the object detection model and the lane line detection model of this lightweight road environment detection system evaluated on the PASCAL VOC dataset and the Highway Driving dataset show that their mAP and mIoU reach 93.2% and 93.3%, respectively, achieving excellent performance compared to other methods. [ABSTRACT FROM AUTHOR]

Road markings are beneficial to human drivers, advanced driver assistance systems (ADAS), and automated driving systems (ADS); on the contrary, snow coverage on roads poses a challenge to all three of these groups with respect to lane detection, as white road markings are difficult to distinguish from snow. Indeed, yellow road markings provide a visual contrast to snow that can increase a human drivers' visibility. Yet, in spite of this fact, yellow road markings are becoming increasingly rare in Europe due to the high costs of painting and maintaining two road marking colors. More importantly, in conjunction with our increased reliance on automated driving, the question of whether yellow road markings are of value to automatic lane detection functions arises. To answer this question, images from snowy conditions are assessed to see how different representations of colors in images (color spaces) affect the visibility levels of white and yellow road markings. The results presented in this paper suggest that yellow markings provide a certain number of benefits for automated driving, offering recommendations as to what the most appropriate color spaces are for detecting lanes in snowy conditions. To obtain the safest and most cost-efficient roads in the future, both human and automated drivers' actions must be considered. Road authorities and car manufacturers also have a shared interest in discovering how road infrastructure design, including road marking, can be adapted to support automated driving. [ABSTRACT FROM AUTHOR]

Self-driving cars are a hot research topic in science and technology, which has a great influence on social and economic development. Deep learning is one of the current key areas in the field of artificial intelligence research. It has been widely applied in image processing, natural language understanding, and so on. In recent years, more and more deep learning-based solutions have been presented in the field of self-driving cars and have achieved outstanding results. This paper presents a review of recent research on theories and applications of deep learning for self-driving cars. This survey provides a detailed explanation of the developments of self-driving cars and summarizes the applications of deep learning methods in the field of self-driving cars. Then the main problems in self-driving cars and their solutions based on deep learning methods are analyzed, such as obstacle detection, scene recognition, lane detection, navigation and path planning. In addition, the details of some representative approaches for self-driving cars using deep learning methods are summarized. Finally, the future challenges in the applications of deep learning for self-driving cars are given out. [ABSTRACT FROM AUTHOR]

A novel lane detection approach, based on the dynamic region of interest (DROI) selection in the horizontal and vertical safety vision, is proposed to improve the accuracy of lane detection in this paper. The curvature of each point on the edge of the road and the maximum safe distance, which are solved by the lane line equation and vehicle speed data of the previous frame, are used to accurately select the DROI at the current moment. Next, the global search of DROI is applied to identify the lane line feature points. Subsequently, the discontinuous points are processed by interpolation. To fulfill fast and accurate matching of lane feature points and mathematical equations, the lane line is fitted in the polar coordinate equation. The proposed approach was verified by the Caltech database, under the premise of ensuring real-time performance. The accuracy rate was 99.21% which is superior to other mainstream methods described in the literature. Furthermore, to test the robustness of the proposed method, it was tested in 5683 frames of complicated real road pictures, and the positive detection rate was 99.07%. [ABSTRACT FROM AUTHOR]

The purpose of the self-driving car is to minimize the number casualties of traffic accidents. One of the effects of traffic accidents is an improper speed of a car, especially at the road turn. If we can make the anticipation of the road turn, it is possible to avoid traffic accidents. This paper presents a cutting edge curve lane detection algorithm based on the Kalman filter for the self-driving car. It uses parabola equation and circle equation models inside the Kalman filter to estimate parameters of a using curve lane. The proposed algorithm was tested with a self-driving vehicle. Experiment results show that the curve lane detection algorithm has a high success rate. The paper also presents simulation results of the autonomous vehicle with the feature to control steering and speed using the results of the full curve lane detection algorithm. [ABSTRACT FROM AUTHOR]

Lane boundary detection technology has progressed rapidly over the past few decades. However, many challenges that often lead to lane detection unavailability remain to be solved. In this paper, we propose a spatial-temporal knowledge filtering model to detect lane boundaries in videos. To address the challenges of structure variation, large noise and complex illumination, this model incorporates prior spatial-temporal knowledge with lane appearance features to jointly identify lane boundaries. The model first extracts line segments in video frames. Two novel filters—the Crossing Point Filter (CPF) and the Structure Triangle Filter (STF)—are proposed to filter out the noisy line segments. The two filters introduce spatial structure constraints and temporal location constraints into lane detection, which represent the spatial-temporal knowledge about lanes. A straight line or curve model determined by a state machine is used to fit the line segments to finally output the lane boundaries. We collected a challenging realistic traffic scene dataset. The experimental results on this dataset and other standard dataset demonstrate the strength of our method. The proposed method has been successfully applied to our autonomous experimental vehicle. [ABSTRACT FROM AUTHOR]

This research proposes an accurate vehicular positioning system which can achieve lane-level performance in urban canyons. Multiple passive sensors, which include Global Navigation Satellite System (GNSS) receivers, onboard cameras and inertial sensors, are integrated in the proposed system. As the main source for the localization, the GNSS technique suffers from Non-Line-Of-Sight (NLOS) propagation and multipath effects in urban canyons. This paper proposes to employ a novel GNSS positioning technique in the integration. The employed GNSS technique reduces the multipath and NLOS effects by using the 3D building map. In addition, the inertial sensor can describe the vehicle motion, but has a drift problem as time increases. This paper develops vision-based lane detection, which is firstly used for controlling the drift of the inertial sensor. Moreover, the lane keeping and changing behaviors are extracted from the lane detection function, and further reduce the lateral positioning error in the proposed localization system. We evaluate the integrated localization system in the challenging city urban scenario. The experiments demonstrate the proposed method has sub-meter accuracy with respect to mean positioning error. [ABSTRACT FROM AUTHOR]

This work develops a new current-mode mixed signal Complementary Metal- Oxide-Semiconductor (CMOS) imager, which can capture images and simultaneously produce vehicle lane maps. The adopted lane detection algorithm, which was modified to be compatible with hardware requirements, can achieve a high recognition rate of up to approximately 96% under various weather conditions. Instead of a Personal Computer (PC) based system or embedded platform system equipped with expensive high performance chip of Reduced Instruction Set Computer (RISC) or Digital Signal Processor (DSP), the proposed imager, without extra Analog to Digital Converter (ADC) circuits to transform signals, is a compact, lower cost key-component chip. It is also an innovative component device that can be integrated into intelligent automotive lane departure systems. The chip size is 2,191.4 × 2,389.8 μm, and the package uses 40 pin Dual-In-Package (DIP). The pixel cell size is 18.45 × 21.8 μm and the core size of photodiode is 12.45 × 9.6 μm; the resulting fill factor is 29.7%. [ABSTRACT FROM AUTHOR]

(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. [ABSTRACT FROM AUTHOR]

With the development of autonomous driving technology, the requirements for machine perception have increased significantly. In particular, camera-based lane detection plays an essential role in autonomous vehicle trajectory planning. However, lane detection is subject to high complexity, and it is sensitive to illumination variation, appearance, and age of lane marking. In addition, the sheer infinite number of test cases for highly automated vehicles requires an increasing portion of test and validation to be performed in simulation and X-in-the-loop testing. To model the complexity of camera-based lane detection, physical models are often used, which consider the optical properties of the imager as well as image processing itself. This complexity results in high efforts for the simulation in terms of modelling as well as computational costs. This paper presents a Phenomenological Lane Detection Model (PLDM) to simulate camera performance. The innovation of the approach is the modelling technique using Multi-Layer Perceptron (MLP), which is a class of Neural Network (NN). In order to prepare input data for our neural network model, massive driving tests have been performed on the M86 highway road in Hungary. The model's inputs include vehicle dynamics signals (such as speed and acceleration, etc.). In addition, the difference between the reference output from the digital-twin map of the highway and camera lane detection results is considered as the target of the NN. The network consists of four hidden layers, and scaled conjugate gradient backpropagation is used for training the network. The results demonstrate that PLDM can sufficiently replicate camera detection performance in the simulation. The modelling approach improves the realism of camera sensor simulation as well as computational effort for X-in-the-loop applications and thereby supports safety validation of camera-based functionality in automated driving, which decreases the energy consumption of vehicles. [ABSTRACT FROM AUTHOR]

Modern vehicles rely on a multitude of sensors and cameras to both understand the environment around them and assist the driver in different situations. Lane detection is an overall process as it can be used in safety systems such as the lane departure warning system (LDWS). Lane detection may be used in steering assist systems, especially useful at night in the absence of light sources. Although developing such a system can be done simply by using global positioning system (GPS) maps, it is dependent on an internet connection or GPS signal, elements that may be absent in some locations. Because of this, such systems should also rely on computer vision algorithms. In this paper, we improve upon an existing lane detection method, by changing two distinct features, which in turn leads to better optimization and false lane marker rejection. We propose using a probabilistic Hough transform, instead of a regular one, as well as using a parallelogram region of interest (ROI), instead of a trapezoidal one. By using these two methods we obtain an increase in overall runtime of approximately 30%, as well as an increase in accuracy of up to 3%, compared to the original method. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Autonomous vehicles and advanced driver assistance systems are predicted to provide higher safety and reduce fuel and energy consumption and road traffic emissions. Lane detection and tracking are the advanced key features of the advanced driver assistance system. Lane detection is the process of detecting white lines on the roads. Lane tracking is the process of assisting the vehicle to remain in the desired path, and it controls the motion model by using previously detected lane markers. There are limited studies in the literature that provide state-of-art findings in this area. This study reviews previous studies on lane detection and tracking algorithms by performing a comparative qualitative analysis of algorithms to identify gaps in knowledge. It also summarizes some of the key data sets used for testing algorithms and metrics used to evaluate the algorithms. It is found that complex road geometries such as clothoid roads are less investigated, with many studies focused on straight roads. The complexity of lane detection and tracking is compounded by the challenging weather conditions, vision (camera) quality, unclear line-markings and unpaved roads. Further, occlusion due to overtaking vehicles, high-speed and high illumination effects also pose a challenge. The majority of the studies have used custom based data sets for model testing. As this field continues to grow, especially with the development of fully autonomous vehicles in the near future, it is expected that in future, more reliable and robust lane detection and tracking algorithms will be developed and tested with real-time data sets. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Computer simulation based on digital twin is an essential process when designing self-driving cars. However, designing a simulation program that is exactly equivalent to real phenomena can be arduous and cost-ineffective because too many things must be implemented. In this paper, we propose the method using the online game GTA5 (Grand Theft Auto5), as a groundwork for autonomous vehicle simulation. As GTA5 has a variety of well-implemented objects, people, and roads, it can be considered a suitable tool for simulation. By using OpenCV (Open source computer vision) to capture the GTA5 game screen and analyzing images with YOLO (You Only Look Once) and TensorFlow based on Python, we can build a quite accurate object recognition system. This can lead to writing of algorithms for object avoidance and lane recognition. Once these algorithms have been completed, vehicles in GTA5 can be controlled through codes composed of the basic functions of autonomous driving, such as collision avoidance and lane-departure prevention. In addition, the algorithm tested with GTA5 has been implemented with a programmable RC car (Radio control car), DonkeyCar, to increase reliability. By testing those algorithms, we can ensure that the algorithms can be conducted in real time and they cost low power and low memory size. Therefore, we have found a way to approach digital twin technology one step more easily. [ABSTRACT FROM AUTHOR]

Lateral support systems in vehicles have a high potential for reduction of lane departure crashes. To profit from their full potential, such systems should function properly in adverse conditions. Literature indicates that their accuracy varies between day and night-time. However, detailed quantifications of the systems' performance in these conditions are rare. The aim of this study is to investigate the differences in detection quality and view range of Mobileye 630 in dry daytime and night-time conditions. On-road tests on four rural road sections in Croatia were conducted. Wilcoxon signed-rank test was used to test the difference between the number of quality rankings while absolute average, average difference and standard deviation were used to analyse the view range. Also, a paired samples t-test was used to test the difference between conditions for each line on each road. The overall results confirm that a significant difference in lane detection quality view range exists between tested conditions. "Medium" and "high" detection confidence (quality level 3 and 2), increased by 5% and 8% during night-time compared to daytime while level 0 ("nothing detected") decreased by 12%. The view range increased (almost 16% for middle line) during daytime compared to night-time. The findings of this study expand the existing knowledge and are valuable for research and development of machine-vision systems but also for road authorities to optimize the markings' quality performance. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]