Accurate Lane Detection Research Articles

Effective lane detection on complex roads with convolutional attention mechanism in autonomous vehicles

Autonomous Vehicles (AV’s) have achieved more popularity in vehicular technology in recent years. For the development of secure and safe driving, these AV’s help to reduce the uncertainties such as crashes, heavy traffic, pedestrian behaviours, random objects, lane detection, different types of roads and their surrounding environments. In AV’s, Lane Detection is one of the most important aspects which helps in lane holding guidance and lane departure warning. From Literature, it is observed that existing deep learning models perform better on well maintained roads and in favourable weather conditions. However, performance in extreme weather conditions and curvy roads need focus. The proposed work focuses on presenting an accurate lane detection approach on poor roads, particularly those with curves, broken lanes, or no lane markings and extreme weather conditions. Lane Detection with Convolutional Attention Mechanism (LD-CAM) model is proposed to achieve this outcome. The proposed method comprises an encoder, an enhanced convolution block attention module (E-CBAM), and a decoder. The encoder unit extracts the input image features, while the E-CBAM focuses on quality of feature maps in input images extracted from the encoder, and the decoder provides output without loss of any information in the original image. The work is carried out using the distinct data from three datasets called Tusimple for different weather condition images, Curve Lanes for different curve lanes images and Cracks and Potholes for damaged road images. The proposed model trained using these datasets showcased an improved performance attaining an Accuracy of 97.90%, Precision of 98.92%, F1-Score of 97.90%, IoU of 98.50% and Dice Co-efficient as 98.80% on both structured and defective roads in extreme weather conditions.

Enhanced Safety in Multi-Lane Automated Driving Through Semantic Features

Accurate lane detection is crucial for the safety and reliability of multi-lane automated driving, where the complexity of traffic scenarios is significantly heightened. Leveraging the semantic segmentation capabilities of deep learning, we develop a modified U-Net architecture tailored for the precise identification of lane lines. Our model is trained and validated on a robust dataset from Kaggle, comprising 2975 annotated training images and 500 test images with masks. Empirical results demonstrate the model's proficiency, achieving a peak accuracy of 95.19% and a Dice score of 0.928, indicating exceptional precision in segmenting lanes. These results represent a notable contribution to the enhancement of safety in automated driving systems.

PortLaneNet: A Scene-Aware Model for Robust Lane Detection in Container Terminal Environments

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.

A Fast and Accurate Lane Detection Method Based on Row Anchor and Transformer Structure.

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.

Sketch and Refine: Towards Fast and Accurate Lane Detection

Lane detection is to determine the precise location and shape of lanes on the road. Despite efforts made by current methods, it remains a challenging task due to the complexity of real-world scenarios. Existing approaches, whether proposal-based or keypoint-based, suffer from depicting lanes effectively and efficiently. Proposal-based methods detect lanes by distinguishing and regressing a collection of proposals in a streamlined top-down way, yet lack sufficient flexibility in lane representation. Keypoint-based methods, on the other hand, construct lanes flexibly from local descriptors, which typically entail complicated post-processing. In this paper, we present a “Sketch-and-Refine” paradigm that utilizes the merits of both keypoint-based and proposal-based methods. The motivation is that local directions of lanes are semantically simple and clear. At the “Sketch” stage, local directions of keypoints can be easily estimated by fast convolutional layers. Then we can build a set of lane proposals accordingly with moderate accuracy. At the “Refine” stage, we further optimize these proposals via a novel Lane Segment Association Module (LSAM), which allows adaptive lane segment adjustment. Last but not least, we propose multi-level feature integration to enrich lane feature representations more efficiently. Based on the proposed “Sketch-and-Refine” paradigm, we propose a fast yet effective lane detector dubbed “SRLane”. Experiments show that our SRLane can run at a fast speed (i.e., 278 FPS) while yielding an F1 score of 78.9%. The source code is available at: https://github.com/passerer/SRLane.

Lanesense: A Computer Vision Marvel for Accurate Lane Detection

Lanesense: A Computer Vision Marvel for Accurate Lane Detection

The lane detection algorithm based on multiscale aggregated attention fusion network

High accuracy and high stability are key elements of the lane detection algorithm in an autonomous driving system. Traditional algorithms are having difficulty extracting detailed features due to the complex geometric structure and background interference of lanes in real scenarios. Therefore, this paper proposes a Multiscale Aggregated Attention Fusion (MAAF) network, which integrates attention mechanisms to improve the accuracy and robustness of lane detection. Firstly, the Recurrent Feature-Shift Aggregator for Lane Detection (RESA) is improved to increase the effective sensory field and improve the efficiency of feature aggregation. Then, the ECANet attention module is used to extract features across channels, enhancing the model's focus on lane details. Finally, a spatial attention mechanism is incorporated to make the network more attentive to lane features, acquire more semantic information, and reduce the influence of background interference and clutter. Experimental results show that this method achieves 96.84% and 76.5% metrics on the TuSimple and CuLane datasets, respectively, surpassing the baseline network. Furthermore, it demonstrates good generalization and robustness, enabling accurate lane detection in complex road environments.

Robust Accurate Lane Detection and Tracking for Automated Rubber-Tired Gantries in a Container Terminal

Lane detection and tracking technique is the autonomous driving basis for Rubber-Tired Gantries (RTGs), vital to the automation and intelligence updating of man-driven container terminals. However, the existing lane detection methods developed for common road scenarios cannot meet the high-precision and robust all-weather requirements of RTG autonomous driving. In this article, we propose an Adaptive Edge-based Lane Detection and Tracking method considering RTG lanes’ characteristics in this paper. First, the candidate edges of lane lines are detected and paired based on the enhanced gradient features. Next, inverse perspective mapping is employed to search the right edges, followed by an adaptive sliding-window method. Ultimately, we develop an adaptive Kalman filter to track lane lines robustly, detecting confidence weighting by relaxing the constraint of lane line width. The proposed method is tested in an actual container yard, the lane centerline’s average position error is 2.051 pixels, and the detection success rate is close to 100%.

Improving the Accuracy of Lane Detection by Enhancing the Long-Range Dependence

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.

G-NET: Accurate Lane Detection Model for Autonomous Vehicle

G-NET: Accurate Lane Detection Model for Autonomous Vehicle

Combining Low-Light Scene Enhancement for Fast and Accurate Lane Detection

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.

Foggy Lane Dataset Synthesized from Monocular Images for Lane Detection Algorithms.

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.

Low Complexity Lane Detection Methods for Light Photometry System

The aim of the paper was to analyze effective solutions for accurate lane detection on the roads. We focused on effective detection of airport runways and taxiways in order to drive a light-measurement trailer correctly. Three techniques for video-based line extracting were used for specific detection of environment conditions: (i) line detection using edge detection, Scharr mask and Hough transform, (ii) finding the optimal path using the hyperbola fitting line detection algorithm based on edge detection and (iii) detection of horizontal markings using image segmentation in the HSV color space. The developed solutions were tuned and tested with the use of embedded devices such as Raspberry Pi 4B or NVIDIA Jetson Nano.

Fast and Accurate Lane Detection via Graph Structure and Disentangled Representation Learning.

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.

A novel deep learning network for accurate lane detection in low-light environments

Lane detection algorithms play a key role in Advanced Driver Assistance Systems (ADAS), which are however unable to achieve accurate lane recognition in low-light environments. This paper presents a novel deep network structure, namely LLSS-Net (low-light images semantic segmentation), to achieve accurate lane detection in low-light environments. The method integrates a convolutional neural network for low-light image enhancement and a semantic segmentation network for lane detection. The image quality is firstly improved by a low-light image enhancement network and lane features are then extracted using semantic segmentation. Fast lane clustering is finally performed by using the KD tree models. Cityscapes and Tusimple datasets are utilized to demonstrate the robustness of the proposed method. The experimental results show that the proposed method has an excellent performance for lane detection in low-light roads.

Training a thin and shallow lane detection network with self-knowledge distillation

With modern science and technology development, vehicles are equipped with intelligent driver assistant systems, of which lane detection is a key function. These complex detection structures (either wide or deep) are investigated to boost the accuracy and overcome the challenges in complicated scenarios. However, the computation and memory storage cost will increase sharply, and the response time will also increase. For resource-constrained devices, lane detection networks with a low cost and short inference time should be implemented. To get more accurate lane detection results, the large (deep and wide) detection structure is framed for high-dimensional and highly robust features, and deep supervision loss is applied on different resolutions and stages. Despite the high-precision advantage, the large detection network cannot be used for embedded devices directly because of the demand for memory and computation. To make the network thinner and lighter, a general training strategy, called self-knowledge distillation (SKD), is proposed. It is different from classical knowledge distillation; there are no independent teacher-student networks, and the knowledge is distilled itself. To evaluate more comprehensively and precisely, a new lane data set is collected. The Caltech Lane date set and TuSimple lane data set are also used for evaluation. Experiments further prove that a small student network and large teacher network have a similar detection accuracy via SKD, and the student network has a shorter inference time and lower memory usage. Thus it can be applied for resource-limited devices flexibly.

Deep reinforcement learning based lane detection and localization

Recently, deep-learning based lane detection methods effectively boost the development of Advanced Driver Assistance Systems (ADAS) and Self-Driving Systems. However, these methods only detect lane lines with sketchy bounding boxes while ignore the shape of specific curved lanes. To address the above problems, this paper introduces deep reinforcement learning into cursory lane detection models for accurate lane detection and localization. This model consists of two stages, namely the bounding box detector and landmark point localizer. To be specific, a bounding box level convolution neural network lane detector outputs the preliminary location of lanes in the form of bounding boxes. Then, a reinforcement based Deep Q-Learning Localizer (DQLL) accurately localizes the lanes as a group of landmarks to achieve better representation of curved lanes. Moreover, a pixel-level lane detection dataset named NWPU Lanes Dataset is constructed and released. It contains a variety of real traffic scenes and accurate masks of the lane lines. This approach achieves competitive performance in the released dataset and TuSimple Lane dataset. Furthermore, the codes and dataset will be released on https://github.com/tuzixini/DQLL.

Accurate Lane Detection for Self-Driving Cars: An Approach Based on Color Filter Adjustment and K-Means Clustering Filter

Lane detection is a crucial factor for self-driving cars to achieve a fully autonomous mode. Due to its importance, lane detection has drawn wide attention in recent years for autonomous driving. One challenge for accurate lane detection is to deal with noise appearing in the input image, such as object shadows, brake marks, breaking lane lines. To address this challenge, we propose an effective road detection algorithm. We leverage the strength of color filters to find a rough localization of the lane marks and employ a K-means clustering filter to screen out the embedded noises. We use an extensive experiment to verify the effectiveness of our method. The result indicates that our approach is robust to process noises appearing in input image, which improves the accuracy in lane detection.

Lane detection algorithm based on Hough transform for high-speed self driving vehicles

This study proposes a lane detection method based on expressway driving videos through a computer vision-based image processing system without using sensors. Both straight and curved sections can occur on a road, and thus, lanes must be detected by quickly determining such sections. The proposed method detects straight and curved sections that are estimated to be lanes using the Hough transform. When lanes are detected from actual images, the scope of left and right lanes is limited to reduce computational load. In this paper, we propose a lane-detection algorithm using the colour space and a stepwise algorithm for accurate lane detection. To verify the proposed algorithms, we developed a small self-driving vehicle model using a TX-2 board. The experiment results when applying the proposed Hough transform algorithm and lane-detection algorithm using the colour space show that the lane detection rate of vehicles driving on curves at high speed is approximately 96%. Through the extensive simulation results, the proposed algorithm to vehicle black boxes or autonomous driving will help prevent lane departure and reduce accident rates.

A precise information extraction algorithm for lane lines

Lane line detection is a fundamental step in applications like autonomous driving and intelligent traffic monitoring. Emerging applications today have higher requirements for accurate lane detection. In this paper, we present a precise information extraction algorithm for lane lines. Specifically, with Gaussian Mixture Model (GMM), we solved the issue of lane line occlusion in multi-lane scenes. Then, Progressive Probabilistic Hough Transform (PPHT) was used for line segments detection. After K-Means clustering for line segments classification, we solved the problem of extracting precise information that includes left and right edges as well as endpoints of each lane line based on geometric characteristics. Finally, we fitted these solid and dashed lane lines respectively. Experimental results indicate that the proposed method performs better than the other methods in both single-lane and multi-lane scenarios.