We present a robust and real time approach to lane marker detection in urban streets. It is based on generating a top view of the road, filtering using selective oriented Gaussian filters, using RANSAC line fitting to give initial guesses to a new and fast RANSAC algorithm for fitting Bezier Splines, which is then followed by a post-processing step. Our algorithm can detect all lanes in still images of the street in various conditions, while operating at a rate of 50 Hz and achieving comparable results to previous techniques.

Real time detection of lane markers in urban streets

Real time Detection of Lane Markers in Urban Streets

Given a single image of an arbitrary road, that may not be well-paved, or have clearly delineated edges, or some a priori known color or texture distribution, is it possible for a computer to find this road? This paper addresses this question by decomposing the road detection process into two steps: the estimation of the vanishing point associated with the main (straight) part of the road, followed by the segmentation of the corresponding road area based upon the detected vanishing point. The main technical contributions of the proposed approach are a novel adaptive soft voting scheme based upon a local voting region using high-confidence voters, whose texture orientations are computed using Gabor filters, and a new vanishing-point-constrained edge detection technique for detecting road boundaries. The proposed method has been implemented, and experiments with 1003 general road images demonstrate that it is effective at detecting road regions in challenging conditions.

/pdf/general-road-detection-from-a-single-image-1vxtfzpegg.pdf

General Road Detection From a Single Image

By using an onboard camera, it is possible to detect the free road surface ahead of the ego-vehicle. Road detection is of high relevance for autonomous driving, road departure warning, and supporting driver-assistance systems such as vehicle and pedestrian detection. The key for vision-based road detection is the ability to classify image pixels as belonging or not to the road surface. Identifying road pixels is a major challenge due to the intraclass variability caused by lighting conditions. A particularly difficult scenario appears when the road surface has both shadowed and nonshadowed areas. Accordingly, we propose a novel approach to vision-based road detection that is robust to shadows. The novelty of our approach relies on using a shadow-invariant feature space combined with a model-based classifier. The model is built online to improve the adaptability of the algorithm to the current lighting and the presence of other vehicles in the scene. The proposed algorithm works in still images and does not depend on either road shape or temporal restrictions. Quantitative and qualitative experiments on real-world road sequences with heavy traffic and shadows show that the method is robust to shadows and lighting variations. Moreover, the proposed method provides the highest performance when compared with hue-saturation-intensity (HSI)-based algorithms.

Road Detection Based on Illuminant Invariance

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.

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

Road detection is a key issue for autonomous driving in urban traffic. In this paper, after a brief overview of existing methods, we present a road area detection algorithm based on color images. This algorithm is composed of two modules: boundaries are first estimated based on the intensity image and road areas are subsequently detected based on the full color image. In the first module, an edge image of the scene is analyzed to obtain the candidates for the left and right road borders and to delimit the area that will subsequently be used to compute the mean and variance of the Gaussian distribution, assumed to be obeyed by the color components of road surfaces. The second module effectively extracts the road area and reinforces boundaries that the most appropriate fit the road-extraction result. The combination of these modules can overcome basic problems due to inaccuracies in edge detection based on the intensity image alone and due to the computational complexity of segmentation algorithms based on color images. Experimental results on real road scenes have substantiated the effectiveness of the proposed method.

Color based road detection in urban traffic scenes

The real-time detection of circle and ellipse from complex background is a very challenging problem. This paper presents an efficient and effective method introducing the connectivity constraint which dramatically enhances the performance of detection and accuracy of localization. Lacking in abstract denotation of features, most of the current techniques suffer from the huge feature point set. In contrast to presenting features as isolated points, we propose to regard features as contours, continuous lines of one-pixel width. The chain code algorithm is employed to organize feature points as disjoint feature contours. For each independent contour, the parameters of possible figures (circle/ellipse) are estimated based on the RANSAC (Random Sample Consensus) algorithm, thus reducing the scale of problem to several smaller subproblems. To avoid the influence of small arcs and to avoid the case that several targets overlap in the real application, the 'fitting factor' of each possible figure is introduced to evaluate the estimation of parameters. Our experiments successfully demonstrate its real-time performance, accuracy, and robustness.

A fast contour-based approach to circle and ellipse detection

Ellipse is one of the most common features that appears in images. Over years in research, real-timing and robustness have been two very challenging problems aspects of ellipse detection. Aiming to tackle them both, we propose an ellipse detection algorithm based on pseudo-random sample consensus (PRANSAC). In PRANSAC we improve a contour-based ellipse detection algorithm (CBED), which was presented in our previous work. In addition, the parallel thinning algorithm is employed to eliminate useless feature points, which increases the time efficiency of our detection algorithm. In order to further speed up, a 3-point ellipse fitting method is introduced. In terms of robustness, a "robust candidate sequence" is proposed to improve the robustness performance of our detection algorithm. Compared with the state-of-the-art ellipse detection algorithms, experimental results based on real application images show that significant improvements in time efficiency and performance robustness of the proposed algorithm have been achieved.

A fast and robust ellipse detection algorithm based on pseudo-random sample consensus

Obstacle detection is an essential capability for thesafe guidance of autonomous vehicles, especially in ur-ban environments. Most of the existing stereovisiontechniques for obstacle detection rely on the planarground assumption. However in urban environmentsthe real-time requirement and the range of distancesthat must be considered imply that the planar assump-tion is too restrictive. In order to enhance the reliabil-ity of the obstacle detection task, we do not considerthe urban roads as rigid planes, but a quasi-plane,whose normal vector has a predictable constraint. Un-der this °exible road model, we propose a fast, ro-bust method, which is also easy to implement on DSPsand microprocessors. In this paper, we ﬂrst model theideal ground plane in the disparity space and extractthe potential obstacle points with the quasi-plane con-straint estimated by a Random Sampling Consensus(RANSAC) algorithm o†ine. Then we introduce awatershed transformation to segment isolated obsta-cles. To avoid the di–culty of the computation inmetric space, the whole process is performed in the dis-parity image. Various experimental results as well asthe real time performance and comparison with resultsfrom the planar road model approach are presented,showing the advantages of this method.

Stereo-Vision Based Real time Obstacle Detection for Urban Environments

Deception dectection is one of the most difficult problems in affect recognition and expression research area. Recently, non-verbal methods of detecting deception have appeared to be promising. Thomas[1] presented a proof-of-concept study based on the blob analysis of some suspects' interviews and mock experiments video clips. In this paper, we present our recent research work in the direction of developing an automated deception detection system. We propose a blob motion pattern analysis approach to solve this problem.

/pdf/deception-detection-via-blob-motion-pattern-analysis-2phl6u175z.pdf

Hong Wang

Papers

Color based road detection in urban traffic scenes

A fast contour-based approach to circle and ellipse detection

A fast and robust ellipse detection algorithm based on pseudo-random sample consensus

Stereo-Vision Based Real time Obstacle Detection for Urban Environments

Deception Detection Via Blob Motion Pattern Analysis