Unstructured Road Research Articles

Real-time path planning of autonomous vehicles for unstructured road navigation

This paper presents a path planning algorithm for autonomous vehicles to generate feasible and smooth maneuvers in unstructured environments. Our approach uses a graph-based search algorithm and a discrete kinematic vehicle model to find a primitive path that is non-holonomic, collision-free, and safe. The algorithm then improves the quality and smoothness of the identified path by making local shortcuts. This shortcut for smoothing the path is determined by connecting the internal state of the primitive path to the initial state based on the Pythagorean Hodograph (PH) cubic curve. The formulation of the PH cubic curves in the smoothing path provides arc-length parameterization of the curve in a closed form. We present examples and experimental results for the real time path planning in unstructured road from an implementation on an autonomous vehicle.

Construction Research on Multi-Threshold Segmentation Based on Improved Otsu Threshold Method

The aim of unstructured road detection is the recognition of road region and the tracking of road boundary. An improved Otsu threshold method available in double-threshold segmentation was proposed in this paper to resolve the multi-peaks problem in both complicated background and target. This method remedies the mis-segmentation of Otsu threshold method caused by huge diversity of between-class variances and refines the segmentation precision by matching the proposed Otsu edges with the weighted Canny edges. According to the irregular characteristics of the unstructured road and the requirement of the real-time motion planning for intelligent vehicle, improved Otsu threshold method was proposed. The experiment results in different road environments demonstrated the validity and real-time of the proposed method.

Research on a Novel Method for Road Edge Detection Based on Road Environment

Considering the difficulty of real-time, robustness for the edge detection in the unstructured road environment, a heuristic probabilistic Hough transform method for weighted Canny edges image was proposed in this paper. The experiment results in the unstructured road environment demonstrated the validity and real-time of the proposed method.

Applied Technology in Unstructured Road Detection with Road Environment Based on SIFT-HARRIS

This paper proposed a method of Optical flow detection on SIFT-Harris for monovision that aims to solve the problem of gray inconsistency in certain region on actual road. It adopts the optical flow for the region of interest so that we can judge whether the object is an obstacle or not. The layered structure for the scale invariant features and corner features is set up to detect the obstacles in time in road region and meets the requirement of real-time visual navigation for the intelligent vehicle.

Lane Detection and Tracking Using a Parallel-snake Approach

In this paper, we discuss the design of a parallel-snake model for lane detection and the use of a Kalman filter for tracking. The parallel-snake model is an extension of the open active contour model through the application of a parallel constraint to two open snakes. Compared with other models, this model can handle lanes with broken boundaries and reduce the convergence time with the aid of the parallel constraint and a double external energy force from two parallel snakes. To solve the problem in previous snake models, whereby the external force is lost on images with a low gradient, a balloon force is utilized to expand the double snakes from the center of the road to the lane boundaries. Because lane boundaries do not retain the parallel property, the captured images are transformed into a bird's-eye view to retrieve the parallel property of lane boundaries by planar homography. At least four corresponding points are determined and the EM-based vanishing point estimation algorithm is applied to these points to estimate the planar homography. Finally, we use a Kalman filter for parameter optimization in lane tracking considering the continuity of lane parameters between consecutive frames; i.e., to predict the parameters of subsequent frames from the previous frame and refine the estimated results to improve robustness. Experimental results show that the proposed method achieves good performance on lane datasets with shadows, variations in illumination, and broken boundaries. Furthermore, it can handle both structured and unstructured (country) roads well.

Simple road detection based on vanishing point

Vision-based road detection is one of the key techniques of autonomous driving, intelligent vehicles, and visual navigation. At present, methods based on vanishing point perform best with general roads. However, it is difficult for them to meet the needs of a real-time system due to high time consumption. This paper presents a fast detection method, namely simple road detection, which achieves high efficiency by employing sky segmentation and two new optimization schemes-sample convolution and fast voting. The optimizations are based on lookup tables, sample computing, and computing simplification. The interval sampling in sample convolution makes the proposed method flexible to meet various efficiency and accuracy demands by different sample-step values. Mean filter and vote orientation limitation are also proposed to help improve detection accuracy. Experiments have been conducted with a large number of road images under different environmental conditions, and the results demonstrate that our proposed method is efficient and effective in detecting both structured and unstructured roads.

Road boundary detection and tracking for structured and unstructured roads using a 2D lidar sensor

Road boundaries can give useful information for evaluating safe vehicle paths in intelligent vehicles. Much previous research has studied road boundary detection, using different types of sensors such as vision, radar, and lidar. Lidar sensors, in particular, show advantages for road boundary extraction including high resolution and wide field of view. However, none of the previous studies examined the problem of detecting road boundaries when roads could be either structured or unstructured. In this study, we developed a road boundary detection and tracking algorithm using lidar sensing for both structured and unstructured roads. The algorithm extracts road features as line segments in polar coordinates relative to the lidar sensor. The extracted road features are then tracked with respect to a vehicle’s local coordinates using a nearest neighbor filter. The proposed algorithm accurately detected the road boundaries regardless of the road type.

Road-model-based and graph-structure-based hierarchical path-planning approach for autonomous vehicles

This paper presents a path-planning strategy for autonomous vehicles which aims to provide safe and feasible manoeuvres in various driving environments. Our strategy uses a hierarchical architecture which consists of three components: a behaviour planner, a map and path selector and a local-path planner. The behaviour planner performs the rule-based decision process which determines the overall vehicle manoeuvres. The map and path selector preprocesses perception data and chooses a local-path-planning algorithm using the results of the behaviour planner. From this selection, the local-path planner generates a driveable and collision-free path. For reliable path generation under various driving conditions, the proposed local path planner employs two algorithms: a road-model-based path planning algorithm and a graph-structure-based path-planning algorithm. The former is used for structured road driving, such as lane keeping or changing, and the latter is used for unstructured road driving. The proposed hierarchical path-planning algorithm was implemented in the autonomous vehicle called A1, which was applied with an in-vehicle-network-based distributed system architecture. A1 won the 2012 Autonomous Vehicle Competition organized by the Hyundai Motor Group in Korea.

A Sensor-Fusion Drivable-Region and Lane-Detection System for Autonomous Vehicle Navigation in Challenging Road Scenarios

Autonomous vehicle navigation is challenging since various types of road scenarios in real urban environments have to be considered, particularly when only perception sensors are used, without position information. This paper presents a novel real-time optimal-drivable-region and lane detection system for autonomous driving based on the fusion of light detection and ranging (LIDAR) and vision data. Our system uses a multisensory scheme to cover the most drivable areas in front of a vehicle. We propose a feature-level fusion method for the LIDAR and vision data and an optimal selection strategy for detecting the best drivable region. Then, a conditional lane detection algorithm is selectively executed depending on the automatic classification of the optimal drivable region. Our system successfully handles both structured and unstructured roads. The results of several experiments are provided to demonstrate the reliability, effectiveness, and robustness of the system.

Road model prediction based unstructured road detection

Vision-based road detection is an important research topic in different areas of computer vision such as the autonomous navigation of mobile robots. In outdoor unstructured environments such as villages and deserts, the roads are usually not well-paved and have variant colors or texture distributions. Traditional region- or edge-based approaches, however, are effective only in specific environments, and most of them have weak adaptability to varying road types and appearances. In this paper we describe a novel top-down based hybrid algorithm which properly combines both region and edge cues from the images. The main difference between our proposed algorithm and previous ones is that, before road detection, an off-line scene classifier is efficiently learned by both low- and high-level image cues to predict the unstructured road model. This scene classification can be considered a decision process which guides the selection of the optimal solution from region- or edge-based approaches to detect the road. Moreover, a temporal smoothing mechanism is incorporated, which further makes both model prediction and region classification more stable. Experimental results demonstrate that compared with traditional region- and edge-based algorithms, our algorithm is more robust in detecting the road areas with diverse road types and varying appearances in unstructured conditions.

Unstructured road detection based on two-dimensional entropy and contour features

The scene of unstructured road is complex and easy to be influenced by many factors.In order to solve the detection difficulty,a road detection algorithm based on contour features and two-dimensional maximum entropy was proposed.Quadratic two-dimensional maximum entropy segmentation method combined with invariant color feature was used for road image segmentation.Afterwards,contour features were extracted from segmentation result by boundary tracking algorithm,and then the maximum contour was chosen.Finally,the improved mid-to-side algorithm was used to search road edge points,then road boundary was reconstructed through road model and road direction was judged.The experimental results show that the detection accuracy rate is improved about 25% in three kinds of unstructured scene compared with traditional algorithm.In addition,this method is robust against shadows and can recognize road direction efficiently.

Robust Unstructured Road Detection: The Importance of Contextual Information

Unstructured road detection is a key step in an unmanned guided vehicle (UGV) system for road following. However, current vision-based unstructured road detection algorithms are usually affected by continuously changing backgrounds, different road types (shape, colour), variable lighting conditions and weather conditions. Therefore, a confidence map of road distribution, one of contextual information cues, is theoretically analysed and experimentally generated to help detect unstructured roads. Two traditional algorithms, support vector machine (SVM) and k-nearest neighbour (KNN), are carried out to verify the helpfulness of the proposed confidence map. Following this, a novel algorithm, which combines SVM, KNN and the confidence map under a Bayesian framework, is proposed to improve the overall performance of the unstructured road detections. The proposed algorithm has been evaluated using different types of unstructured roads and the experimental results show its effectiveness.

Road Tracking Method Suitable for Both Unstructured and Structured Roads

This paper deals with a problem of road tracking and vehicle positioning based on sequential images captured by a vehicle mounted monocular colour camera. The paper presents a new region-based road tracking method, which is suitable for both structured and unstructured roads. The proposed method is based on our original road segmentation algorithm and estimates road model parameters from measurements obtained by analysis of segmented road region. Although the proposed method is tested over a limited range, evaluation on real image sequences shows promising results for various types of road.

Unstructured Road Spectrum α-stable Distribution Parameters Interval Estimation and Reconstruction Based on Moving Block Bootstrap Method

Symmetrical α-stable distribution is used to express the amplitude non-Gaussian characteristics of the unstructured road spectrum.In the in-situ road spectrum collection implementation,the route length limitation and road surface diversity may decrease the spectrum accuracy.The moving block bootstrap confidence interval estimation method is adopted to estimate the interval of the stable distribution parameters.According to both the stable distribution random series generation theory and the simulation capability of road simulation test bench,the reconstructed spectrum is composed by the amplitude truncated stable distribution random series.The validity and practicality of proposed methods are verified by reconstructing the spectrum of an off-highway vehicle riding through a test ground.An effect time domain road spectrum reconstruction method is provided for the unstructured road simulation and virtual reliability test.

A Texture-Based Local Soft Voting Method for Vanishing Point Detection from a Single Road Image

SUMMARY Estimating a proper location of vanishing point from a single road image without any prior known camera parameters is a challenging problem due to limited information from the input image. Most edge-based methods for vanishing point detection only work well for structured roads with clear painted lines or distinct boundaries, while they usually fail in unstructured roads lacking sharply defined, smoothly curving edges. In order to overcome this limitation, texture-based methods for vanishing point detection have been widely published. Authors of these methods often calculate the texture orientation at every pixel of the road image by using directional filter banks such as Gabor wavelet filter, and seek the vanishing point by a voting scheme. A local adaptive soft voting method for obtaining the vanishing point was proposed in a previous study. Although this method is more effective and faster than prior texture-based methods, the associated computational cost is still high due to a large number of scanning pixels. On the other hand, this method leads to an estimation error in some images, in which the radius of the proposed half-disk voting region is not large enough. The goal of this paper is to reduce the computational cost and improve the performance of the algorithm. Therefore, we propose a novel local soft voting method, in which the number of scanning pixels is much reduced, and a new vanishing point candidate region is introduced to improve the estimation accuracy. The proposed method has been implemented and tested on 1000 road images which contain large variations in color, texture, lighting condition and surrounding environment. The experimental results demonstrate that this new voting method is both efficient and effective in detecting the vanishing point from a single road image and requires much less computational cost when compared to the previous voting method.

Unstructured Road Edge Detection and Initial Positioning Approach based on Monocular Vision

This paper proposes two complementary road edge detection methods for unstructured roads. The methods can be used for visual navigation and intelligent control of mobile robots. One method is color-based, which is applicable to the circumstance that the road and off-road areas have obvious color difference; the other is based on threshold segmentation and can be applied even the road boundary is not clear. On the other hand, shadow has enormous impact on threshold segmentation method, but color-based method is not sensitive to it. These make the two methods complementary. Furthermore, on the basis of edge detection, inverse perspective projection transformation is carried out to calculate running state of the robots. Through experiments on mobile robot platform, verifications that the two proposed methods complement each other in different road environments well are made. The experiments also show that the methods achieve high accuracy in initial positioning and meet requirement of real-time.

Curve path detection of unstructured roads for the outdoor robot navigation

Path planning is a crucial problem in the application of mobile robot and autonomous vehicle. Recently most of methods only achieve reliable results in some particular structured environments. In this paper, we describe a new navigation path detection algorithm in an unstructured environment. Natural frames are analyzed in RGB vector space to research the feasibility of curve path detection of unstructured roads. Perceptual color clustering and morphological image processing have been used as pre-processing to obtain the segmented path. The pixels of the segmented image are analyzed from right to left line-by-line to find the middle points of the path. In order to obtain the optimal navigation path, the least-squares curve fitting method has been used in our research. At last a new method of obtaining the navigation parameters is given. The experimental result shows that our algorithm has high speed and remarkable precision. The navigation parameters in our algorithm can control the robot movement well.

Fast Vanishing-Point Detection in Unstructured Environments

Vision-based road detection in unstructured environments is a challenging problem as there are hardly any discernible and invariant features that can characterize the road or its boundaries in such environments. However, a salient and consistent feature of most roads or tracks regardless of type of the environments is that their edges, boundaries, and even ruts and tire tracks left by previous vehicles on the path appear to converge into a single point known as the vanishing point. Hence, estimating this vanishing point plays a pivotal role in the determination of the direction of the road. In this paper, we propose a novel methodology based on image texture analysis for the fast estimation of the vanishing point in challenging and unstructured roads. The key attributes of the methodology consist of the optimal local dominant orientation method that uses joint activities of only four Gabor filters to precisely estimate the local dominant orientation at each pixel location in the image plane, the weighting of each pixel based on its dominant orientation, and an adaptive distance-based voting scheme for the estimation of the vanishing point. A series of quantitative and qualitative analyses are presented using natural data sets from the Defense Advanced Research Projects Agency Grand Challenge projects to demonstrate the effectiveness and the accuracy of the proposed methodology.

Environment classification and hierarchical lane detection for structured and unstructured roads

This study presents a hierarchical lane detection system with the ability to deal with both structured and unstructured roads. The proposed system classifies the environment first before applying suitable algorithms for different types of roads. Instead of dealing with all situations with one complicated algorithm, this hierarchical architecture makes it possible to achieve high accuracy with relatively simple and efficient lane detection algorithms. For environment classification, pixels with lane-marking colours are extracted as feature points. Eigenvalue decomposition regularised discriminant analysis is utilised in model selection and maximum likelihood estimation of Gaussian parameters in high-dimensional feature space. For structured roads, the extracted feature points are reused for lane detection. Moving vehicles that have the same colours as the lane markings are eliminated from the feature points before the authors perform angles of inclination and turning points searching to locate the lane boundaries. For unstructured roads, mean-shift segmentation is applied to divide the scene into regions. Possible candidate pairs for road boundaries are elected from the region boundaries, and Bayes rule is used to choose the most probable candidate pairs as the lane boundaries. The experimental results have shown that the classification mechanism can effectively choose the correct lane detection algorithm according to the current environment setting, and the system is able to robustly find the lane boundaries on different types of roads in various weather conditions.

Integrating Thematic, Geometric, and Topological Information in the Generalization of Road Networks

A technique is presented for determining and quantifying the functional importance of road segments in a road network, according to a set of source/destination ["source and destination"?] points that reflect the user's context. This technique is an important element in a scheme for the automatic structuring, classification, and coding of unstructured road data — necessary steps in creating a database to support contextually sensitive generalization. The quantification technique employs graph-theoretic methods, and includes the integration of thematic, geometric, and topological information. In the generalization methods, two aspects of data integration are addressed