Lane Detection Research Articles

Robust Lane Detection Algorithm for Autonomous Trucks in Container Terminals

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.

Lane Detection: A Survey with Evolving Methods

Lane Detection: A Survey with Evolving Methods

Lane detection techniques for self-driving vehicle: comprehensive review

Lane detection techniques for self-driving vehicle: comprehensive review

End-to-end lane detection with convolution and transformer

End-to-end lane detection with convolution and transformer

세그멘테이션 기반 차선 인식 네트워크를 위한 적응형 키포인트 추출 알고리즘

Deep-learning-based image segmentation is one of the most widely employed lane detection approaches, and it requires a post-process for extracting the key points on the lanes. A general approach for key-point extraction is using a fixed threshold defined by a user. However, finding the best threshold is a manual process requiring much effort, and the best one can differ depending on the target data set (or an image). We propose a novel key-point extraction algorithm that automatically adapts to the target image without any manual threshold setting. In our adaptive key-point extraction algorithm, we propose a line-level normalization method to distinguish the lane region from the background clearly. Then, we extract a representative key point for each lane at a line (row of an image) using a kernel density estimation. To check the benefits of our approach, we applied our method to two lane-detection data sets, including TuSimple and CULane. As a result, our method achieved up to 1.80%p and 17.27% better results than using a fixed threshold in the perspectives of accuracy and distance error between the ground truth key-point and the predicted point.

Multi-task panoramic driving perception algorithm based on improved YOLOv5

Panoramic driving perception algorithm is becoming more and more important in the field of autonomous driving. A multi-task panoramic driving perception algorithm can quickly help vehicles make reasonable decisions. Aiming at the real-time high-precision problem of a multi-task panoramic driving perception algorithm, a multi-task panoramic Driving perception algorithm based on YOLOv5 structure is proposed. The algorithm consists of a backbone network for feature extraction and two branch networks for specific tasks. The C3 module in the original backbone network of YOLOv5 is replaced with an inversion residual bottleneck module to reduce the computation amount of the network and improve the network recognition accuracy. This algorithm proposes a new branch network, which can simultaneously train the segmentation of driveable area and lane detection, and improve the speed of feature extraction. In BDD100K, the public data set of Berkeley AI Laboratory, the detection speed of the algorithm proposed in this paper reaches 110FPS, which is 19FPS higher than that of the algorithm before improvement. The detection accuracy of traffic target detection reaches 77.2%, and the detection accuracy of lane line detection reaches 71.1%. It can well meet the real-time requirements of panoramic driving perception.

Fast lane detection for extracting spatial location information

Fast lane detection for extracting spatial location information

CenterPNets: A Multi-Task Shared Network for Traffic Perception.

The importance of panoramic traffic perception tasks in autonomous driving is increasing, so shared networks with high accuracy are becoming increasingly important. In this paper, we propose a multi-task shared sensing network, called CenterPNets, that can perform the three major detection tasks of target detection, driving area segmentation, and lane detection in traffic sensing in one go and propose several key optimizations to improve the overall detection performance. First, this paper proposes an efficient detection head and segmentation head based on a shared path aggregation network to improve the overall reuse rate of CenterPNets and an efficient multi-task joint training loss function to optimize the model. Secondly, the detection head branch uses an anchor-free frame mechanism to automatically regress target location information to improve the inference speed of the model. Finally, the split-head branch fuses deep multi-scale features with shallow fine-grained features, ensuring that the extracted features are rich in detail. CenterPNets achieves an average detection accuracy of 75.8% on the publicly available large-scale Berkeley DeepDrive dataset, with an intersection ratio of 92.8% and 32.1% for driveableareas and lane areas, respectively. Therefore, CenterPNets is a precise and effective solution to the multi-tasking detection issue.

Lane Line Detection and Object Scene Segmentation Using Otsu Thresholding and the Fast Hough Transform for Intelligent Vehicles in Complex Road Conditions

An Otsu-threshold- and Canny-edge-detection-based fast Hough transform (FHT) approach to lane detection was proposed to improve the accuracy of lane detection for autonomous vehicle driving. During the last two decades, autonomous vehicles have become very popular, and it is constructive to avoid traffic accidents due to human mistakes. The new generation needs automatic vehicle intelligence. One of the essential functions of a cutting-edge automobile system is lane detection. This study recommended the idea of lane detection through improved (extended) Canny edge detection using a fast Hough transform. The Gaussian blur filter was used to smooth out the image and reduce noise, which could help to improve the edge detection accuracy. An edge detection operator known as the Sobel operator calculated the gradient of the image intensity to identify edges in an image using a convolutional kernel. These techniques were applied in the initial lane detection module to enhance the characteristics of the road lanes, making it easier to detect them in the image. The Hough transform was then used to identify the routes based on the mathematical relationship between the lanes and the vehicle. It did this by converting the image into a polar coordinate system and looking for lines within a specific range of contrasting points. This allowed the algorithm to distinguish between the lanes and other features in the image. After this, the Hough transform was used for lane detection, making it possible to distinguish between left and right lane marking detection extraction; the region of interest (ROI) must be extracted for traditional approaches to work effectively and easily. The proposed methodology was tested on several image sequences. The least-squares fitting in this region was then used to track the lane. The proposed system demonstrated high lane detection in experiments, demonstrating that the identification method performed well regarding reasoning speed and identification accuracy, which considered both accuracy and real-time processing and could satisfy the requirements of lane recognition for lightweight automatic driving systems.

Vision-Based Ingenious Lane Departure Warning System for Autonomous Vehicles

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.

Interpolation-Based Framework for Generation of Ground Truth Data for Testing Lane Detection Algorithm for Automated Vehicle

Automated vehicles, predicted to be fully electric in future, are expected to reduce road fatalities and road traffic emissions. The lane departure warning system, an important feature of automated vehicles, utilize lane detection and tracking algorithms. Researchers are constrained to test their lane detection algorithms because of the small publicly available datasets. Additionally, those datasets may not represent differences in road geometries, lane marking and other details unique to a particular geographic location. Existing methods to develop the ground truth datasets are time intensive. To address this gap, this study proposed a framework for an interpolation approach for quickly generating reliable ground truth data. The proposed method leverages the advantage of the existing manual and time-slice approaches. A detailed framework for the interpolation approach is presented and the performance of the approach is compared with the existing methods. Video datasets for performance evaluation were collected in Melbourne, Australia. The results show that the proposed approach outperformed four existing approaches with a reduction in time for generating ground truth data in the range from 4.8% to 87.4%. A reliable and quick method for generating ground truth data, as proposed in this study, will be valuable to researchers as they can use it to test and evaluate their lane detection and tracking algorithms.

Surrogate Evaluation Model for Assessing Lane Detection Reliability of Automated Vehicles in Complex Road Environments

The reliability of environmental perception is the key to ensuring the stability and safety of autonomous vehicles. Complex road environments pose attentional challenges to automated driving, especially for vehicle perception systems. Therefore, evaluating the performance of autonomous driving algorithms in complex road environments is of great significance. However, as road geometry is complex, with many factors, including curvature, slope, lane marking conditions, and so on, the existing approach in assessing an algorithm through detection tests is of low efficiency. Therefore, this study relies on failure prediction modeled by extreme gradient boosting and recursive feature elimination. An evaluation model that could accomplish a quick set of road evaluations is developed. The proposed model generates recognition reliability merely by such features as road design parameters. In addition, road curvature is the most significant environmental factor affecting the perception of autonomous vehicles. The failure rates of the algorithm in different scenarios demonstrate a negative correlation between the radius of curvature and failure perception. The partial dependence involving the radius of curvature and the perception ability is obtained. Furthermore, other features, such as missing lane lines and illumination conditions, are taken into consideration to explore the potential failure perception mode. The proposed method has a particular significance for finding the failure mode of an autonomous driving perception algorithm.

Comparison of GPU and FPGA Hardware Acceleration of Lane Detection Algorithm

Comparison of GPU and FPGA Hardware Acceleration of Lane Detection Algorithm

A computer vision-based lane detection technique using gradient threshold and hue-lightness-saturation value for an autonomous vehicle

<span lang="EN-US">Automatic lane detection for driver assistance is a significant component in developing advanced driver assistance systems and high-level application frameworks since it contributes to driver and pedestrian safety on roads and highways. However, due to several limitations that lane detection systems must rectify, such as the uncertainties of lane patterns, perspective consequences, limited visibility of lane lines, dark spots, complex background, illuminance, and light reflections, it remains a challenging task. The proposed method employs vision-based technologies to determine the lane boundary lines. We devised a system for correctly identifying lane lines on a homogeneous road surface. Lane line detection relies heavily on the gradient and hue lightness saturation (HLS) thresholding which detects the lane line in binary images. The lanes are shown, and a sliding window searching method is used to estimate the color lane. The proposed system achieved 96% accuracy in detecting lane lines on the different roads, and its performance was assessed using data from several road image databases under various illumination circumstances.</span>

Artificial Intelligence based Lane Detection using Satellite Images

Lane detection is one of the most important task for tragedy or emergency response using satellite imagery structures. Most of the researchers adopted Machine Learning (ML) approaches to detect white lines on the roads namely lanes. These approaches are more complex and computational. In order to identify knowledge gaps, this study compares and analyses the various lane detection and tracking algorithms that have been used in research papers in the past. Additionally, it provides an overview of some of the datasets used in various research papers. The main challenge in detecting the lane using satellite images is the weather, which makes it difficult to achieve the expected objectives.

MT-Net: Fast video instance lane detection based on space time memory and template matching

Currently, only a few lane detection methods focus on the dynamic characteristics of a video. In continuous prediction, single-frame detection results produce different degrees of jitter, resulting in poor robustness. We propose a new fast video instance lane detection network, called MT-Net, based on space–time memory and template matching. Memory templates were used to establish feature associations between past and current frames from a local–global perspective to mitigate jitter from scene changes and other disturbances. Moreover, we also investigated the sources and spreading mechanism of memory errors. We designed new query frame and memory encoders to obtain higher-precision memory and query frame features. The experimental results showed that, compared with state-of-the-art models, the proposed model can reduce the number of parameters by 62.28% and the unnecessary jitter and unstable factors in muti-frame lane prediction results by 12.70%, and increases the muti-frame lane detection speed by 1.79. Our proposed methods has obvious advantages in maintaining multi-frame instance lane stability and reducing errors.

Multifocus object detector for vehicle tracking in smart cities using spatiotemporal attention map

In recent days, an unrivaled proliferation of autonomous driving becomes an active area of research in the field of smart city applications. Millions of autonomous cars emerge as ubiquitous in smart cities in the foreseeable future. Vehicle detection and tracking is one of the important cases in smart city applications. It clarifies that the efficient scene parsing methods will be a huge potential. There were several traditional methods employed for the detection of object for the purpose of vehicle detection and road segmentation. However, there were some drawbacks such as reduced rate of detection accuracy, improper road segmentations, and missing detections of occluded objects exist. To overcome the existing issues, we propose an effective multi focus object detector (MFOD) that retrieves spatiotemporal data and considers multiple cues of an object for detection and tracking. The proposed MFOD performs lane detection, vehicle detection, and tracking. To accomplish this task, modified Hough transform is proposed for lane detection and road segmentation. Residual attention unit (RAU) with shared convolutional neural network layers is deployed for vehicle detection and tracking. It makes use of motion model to update the network and creates visualization map to explore the visibility of occluded objects and spatial attention map for accurate prediction of object location. The proposed MFOD is also extended for scene parsing task. We performed extensive analysis of the proposed MFOD with standard evaluation metrics on two different datasets, such as KITTI for object detection and tracking task and cityscapes for scene parsing task. The experimental results demonstrate that the proposed MFOD achieves 3% to 4% improvement compared with the existing methods.

Lane Detection and Traffic Sign for Autonomous Cars

Lane Detection and Traffic Sign for Autonomous Cars

Non-residual unrestricted pruned ultra-faster line detection for edge devices

Line detection with deep learning is a popular visual task that focuses mostly on lane detection. It requires quicker inference speed and lower consumption, especially for high-speed edge device applications. Based on the UFAST, we propose the Non-Residual Unrestricted Pruned Ultra-faster (NRUPU) line detection via a novel model compression method including non-interference structural reconstruction (NISR), shallow channel priority reservation (SCPR) pruning and non-residual equivalent transformation (NRET). NISR is a structure reconstruction scheme allocating residual branches into each layer to solve the cross-layer channel interference in ResNet-18. SCPR pruning directly uses the factors of BN layers to build channel importance evaluation for backbone and designs channel selection method for head based on data distribution consistency, reducing the parameters of each layer independently. Then NRET losslessly converts the multi-branch model to a single-branch one containing only convolution, linear, and relu, which reduces implementation complexity on edge devices. These designs follow the theoretical foundations: the data distribution transformation trend and effect of gradient back-propagation on model learning ability. Compared with previous pruning methods, our method optimizes not only the parameters of the model but also the structure of the model. We train NRUPU in RTX2080Ti and deploy tests on edge devices NVIDIA Jetson Xavier NX (NJXN) and Atlas 200 DK (A2DK). Extensive experiments are conducted on the dataset TuSimple, CULane and our belt dataset with 11,894 data. Results show that NRUPU achieves over 96% speed increase and over 66% parameter reduction on all datasets within 0.7% accuracy loss. The FPS can reach 749, 665 and 783 on RTX2080Ti, 133, 117 and 143 on NJNX, 178, 161 and 183 on A2DK respectively. The code is released at https://anonymous.4open.science/r/NRUPU-29B0.

Preserving Privacy of Classified Authentic Satellite Lane Imagery Using Proxy Re-Encryption and UAV Technologies

Privacy preservation of image data has been a top priority for many applications. The rapid growth of technology has increased the possibility of creating fake images using social media as a platform. However, many people, including researchers, rely on image data for various purposes. In rural areas, lane images have a high level of importance, as this data can be used for analyzing various lane conditions. However, this data is also being forged. To overcome this and to improve the privacy of lane image data, a real-time solution is proposed in this work. The proposed methodology assumes lane images as input, which are further classified as fake or bona fide images with the help of Error Level Analysis (ELA) and artificial neural network (ANN) algorithms. The U-Net model ensures lane detection for bona fide lane images, which helps in the easy identification of lanes in rural areas. The final images obtained are secured by using the proxy re-encryption technique which uses RSA and ECC algorithms. This helps in ensuring the privacy of lane images. The cipher images are maintained using fog computing and processed with integrity. The proposed methodology is necessary for protecting genuine satellite lane images in rural areas, which are further used by forecasters, and researchers for making interpretations and predictions on data.