Lane departure warning systems have gained considerable research interest in the past decade for its promising usage in automotive, where lane detection and tracking is applied. However, it is a challenging task to improve the robustness of lane detection due to environmental factors, such as perspective effect, possible low visibility of lanes, and partial occlusions. To deal with these issues, we propose a reliable vision-based real-time lane markings detection and tracking system that can adapt to various environmental conditions. The lane detection is composed of three stages: pre-processing, Adaptive Region of Interest (AROI) setting, and lane marking detection and tracking. In the pre-processing stage, smoothing and edge detection operators are applied on input frames to automatically obtain binary images, then, lane markings segmentation are carried out. After that, An Adaptive Region of Interest is extracted to reduce the computational complexity. In the subsequent detection stages, Kalman filter is employed to track road boundaries detected in the AROI using Progressive Probabilistic Hough Transform (PPHT) in the next frame. Based on road boundaries and the vehicle's position, the proposed algorithm decides if the vehicle has drifted off the lane. For the performance evaluation of lane detection and tracking, real-life datasets for both urban roads and highways in various lighting conditions are used. Applying our method to Catltech dataset, the average correct detection rate is 93.82%. In addition, the proposed method outperforms that of the state-of-the-art methods in processing time (21.54ms/frame).

/pdf/a-lane-tracking-method-based-on-progressive-probabilistic-7fw6l38676.pdf

A Lane Tracking Method Based on Progressive Probabilistic Hough Transform

Understanding the complex urban infrastructure with centimeter-level accuracy is essential for many applications from autonomous driving to mapping, infrastructure monitoring, and urban management. Aerial images provide valuable information over a large area instantaneously; nevertheless, no current dataset captures the complexity of aerial scenes at the level of granularity required by real-world applications. To address this, we introduce SkyScapes, an aerial image dataset with highly-accurate, fine-grained annotations for pixel-level semantic labeling. SkyScapes provides annotations for 31 semantic categories ranging from large structures, such as buildings, roads and vegetation, to fine details, such as 12 (sub-)categories of lane markings. We have defined two main tasks on this dataset: dense semantic segmentation and multi-class lane-marking prediction. We carry out extensive experiments to evaluate state-of-the-art segmentation methods on SkyScapes. Existing methods struggle to deal with the wide range of classes, object sizes, scales, and fine details present. We therefore propose a novel multi-task model, which incorporates semantic edge detection and is better tuned for feature extraction from a wide range of scales. This model achieves notable improvements over the baselines in region outlines and level of detail on both tasks.

/pdf/skyscapes-fine-grained-semantic-understanding-of-aerial-4rpbpu0fbg.pdf

SkyScapes ­ Fine-Grained Semantic Understanding of Aerial Scenes

Single image dehazing based on learning of haze layers

Autonomous driving is experiencing rapid development. A lane-level map is essential for autonomous driving, and a lane-level road network is a fundamental part of a lane-level map. A large amount of research has been performed on lane-level road network generation based on various on-board systems. However, there is a lack of analysis and summaries with regards to previous work. This paper presents an overview of lane-level road network generation techniques for the lane-level maps of autonomous vehicles with on-board systems, including the representation and generation of lane-level road networks. First, sensors for lane-level road network data collection are discussed. Then, an overview of the lane-level road geometry extraction methods and mathematical modeling of a lane-level road network is presented. The methodologies, advantages, limitations, and summaries of the two parts are analyzed individually. Next, the classic logic formats of a lane-level road network are discussed. Finally, the survey summarizes the results of the review.

/pdf/lane-level-road-network-generation-techniques-for-lane-level-x90z6zt38x.pdf

Lane-level road network generation techniques for lane-level maps of autonomous vehicles: a survey

SkyScapes -- Fine-Grained Semantic Understanding of Aerial Scenes

Vision-based lane-detection methods provide low-cost density information about roads for autonomous vehicles. In this paper, we propose a robust and efficient method to expand the application of these methods to cover low-speed environments. First, the reliable region near the vehicle is initialized and a series of rectangular detection regions are dynamically constructed along the road. Then, an improved symmetrical local threshold edge extraction is introduced to extract the edge points of the lane markings based on accurate marking width limitations. In order to meet real-time requirements, a novel Bresenham line voting space is proposed to improve the process of line segment detection. Combined with straight lines, polylines, and curves, the proposed geometric fitting method has the ability to adapt to various road shapes. Finally, different status vectors and Kalman filter transfer matrices are used to track the key points of the linear and nonlinear parts of the lane. The proposed method was tested on a public database and our autonomous platform. The experimental results show that the method is robust and efficient and can meet the real-time requirements of autonomous vehicles.

Robust Lane-Detection Method for Low-Speed Environments.

High-definition (HD) maps have gained increasing attention in highly automated driving technology and show great significance for self-driving cars. An HD road network (HDRN) is one of the most important parts of an HD map. To date, there have been few studies focusing on road and road-segment extraction in the automatic generation of an HDRN. To improve the precision of an HDRN further and represent the topological relations between road segments and lanes better, in this paper, we propose an HDRN model (HDRNM) for a self-driving car. The HDRNM divides the HDRN into a road-segment network layer and a road-network layer. It includes road segments, attributes and geometric topological relations between lanes, as well as relations between road segments and lanes. We define the place in a road segment where the attribute changes as a linear event point. The road segment serves as a linear benchmark, and the linear event point from the road segment is mapped to its lanes via their relative positions to segment the lanes. Then, the HDRN is automatically generated from road centerlines collected by a mobile mapping vehicle through a multi-directional constraint principal component analysis method. Finally, an experiment proves the effectiveness of this HDRNM.

A High-Definition Road-Network Model for Self-Driving Vehicles

The data collected by floating cars is an important source for lane-level map production. Compared with other data sources, this method is a low-cost but challenging way to generate high-accuracy maps. In this paper, we propose a data correction algorithm for low-frequency floating car data. First, we preprocess the trajectory data by an adaptive density optimizing method to remove the noise points with large mistakes. Then, we match the trajectory data with OpenStreetMap (OSM) using an efficient hierarchical map matching algorithm. Lastly, we correct the floating car data by an OSM-based physical attraction model. Experiments are conducted exploiting the data collected by thousands of taxies over one week in Wuhan City, China. The results show that the accuracy of the data is improved and the proposed algorithm is demonstrated to be practical and effective.

A Data Correction Algorithm for Low-Frequency Floating Car Data.

As an important role in autonomous vehicles or advanced driving assistance systems, lane detection uses the onboard camera high up on the windshield to provide the vehicle’s lateral offset within its own lane in a real-time, low-cost way. In this paper, we propose an efficient, robust lane detection method based on histogram of oriented vanishing points. First, the lane features are extracted by symmetrical local threshold. Then, the lines are generated from oriented vanishing points. The lines crossing most features are selected and oriented vanishing points are updated by the overlap between features and selected lines. Last step will be repeated for getting stable oriented vanishing points. Therefore, the last selected lines are most likely to be lane lines. Finally, Validate and select the best lane lines. The proposed method has been tested on a public dataset. The experimental results show that the method can improve robustness under real-time automated driving.

Lane Detection Based on Histogram of Oriented Vanishing Points

Lane detection algorithm based on monocular camera is one of the most popular methods in recent years, which can meet the requirement of real-time and robust for autonomous vehicle. In this way, the position of lane markers can be transferred from perspective space to road space base on the planar road assumption. However, large numbers of road scenes, especially the up and down slope road environment, cannot meet this requirement.In this paper, we propose a multiple vanishing point detection method to reconstruct the road space in slope scenes. In order to improve the accuracy of vanishing point estimation, the road images are decomposed into near and far regions. We extract candidate lane markers in near region by using multiscale convolution kernel and Hough Transform at first. Then, the lane markers in far region can be detected based on the result of near region. At last, different vanishing points are extracted in near and far regions. With the help of a vanishing point based on camera model, we can project both of near and far regions into road space. The experiment is conducted on our self-driving car ‘TuLian’ in campus environment.

Jian Zhou

Papers

Robust Lane-Detection Method for Low-Speed Environments.

A High-Definition Road-Network Model for Self-Driving Vehicles

A Data Correction Algorithm for Low-Frequency Floating Car Data.

Lane Detection Based on Histogram of Oriented Vanishing Points

Lane Detection and Road Surface Reconstruction Based on Multiple Vanishing Point & Symposia