A temporal filter approach for detection and reconstruction of curbs and road surfaces based on Conditional Random Fields

Abstract

A temporal filter approach for real-time detection and reconstruction of curbs and road surfaces from 3D point clouds is presented. Instead of local thresholding, as used in many other approaches, a 3D curb model is extracted from the point cloud. The 3D points are classified to different parts of the model (i.e. road and sidewalk) using a temporally integrated Conditional Random Field (CRF). The parameters of curb and road surface are then estimated from the respectively assigned points, providing a temporal connection via a Kalman filter.In this contribution, we employ dense stereo vision for data acquisition. Other sensors capturing point cloud data, e.g. lidar, would also be suitable.The system was tested on real-world scenarios, showing the advantages over a temporally unfiltered version, due to robustness, accuracy and computation time. Further, the lateral accuracy of the system is evaluated. The experiments show the system to yield highly accurate results, for curved and straightline curbs, up to distances of 20 meters from the camera.

A new performance measure and evaluation benchmark for road detection algorithms

“…This information can be extracted by comparing the corridor with the ego-lane ground truth and integrating all evaluation results (TP, FP) in the BEV space up to a certain distance 3 . This allows to calculate the precision, which drops if the FP number rises due to a corridor hypothesis leaving the ground truth.…”

“…The values in Table IV represent the fraction of corridors correctly matched to the ground truth ego-lane up to that distance, i.e., with less than 10% lateral mismatch over the complete distance range. 3 In order to cope with invalid BEV cells close to the vehicle due to the imprecise annotation of the road area and ego-lane bottom points at the border of the perspective/BEV space and distortions from the dynamic transformation, the integration starts at 9m only.…”

“…Early works focused on the overall road area as it is more easy to extract. For example, the physical property of the road being flat has been used in a variety of approaches [3], [4]. However, this requires the road area to be limited by sufficiently elevated structures as well as accurate depth information which for stereo cameras is only available in the close range.…”

A Hybrid Vision-Map Method for Urban Road Detection

“…On the other hand, it is not possible to achieve this rate with a pair of stereo cameras, which have a detection range of approximately 20 meters. The most common approach used to detect curbs, according to the literature, is the use of a Digital Elevation Map (DEM) to integrate the 3D measurements and a posterior analysis of height variation [16]. Some of them attempt to model the curb shape with cubic polynomials or a cubic spline [17]; however, the diverse type of shapes present in urban scenarios makes these methods fail in certain scenarios.…”

“…On one side, in [19] the minimum curb height detected is 5 cm with an error of 3 cm at 20 meters. On the other side, in [16] the lateral distance is evaluated up to 20 meters with an error of 20 cm. Our novel method based on curvature values is presented in [20], where the system is evaluated on point clouds from stereovision and 3D LIDAR.…”