Conference Paper

Reconstruction of a road by local image matches and global 3D optimization

Comput. Vision Lab., Maryland Univ., College Park, MD
DOI: 10.1109/ROBOT.1990.126186 Conference: Robotics and Automation, 1990. Proceedings., 1990 IEEE International Conference on
Source: IEEE Xplore


A method is presented for reconstructing a 3-D road from a single
image. It finds the images of opposite points of the road. Opposite
points are points which face each other on the opposite sides of the
road; the images of these points are called matching points. For points
chosen from one side of the road image, the algorithm finds all the
matching point candidates on the other side, based on local properties
of a road. However, these solutions do not necessarily satisfy the
global properties of a typical road. A dynamic programming algorithm is
applied to reject the candidates which do not fit the global road. A
benchmark using synthetic roads is described. It shows that the roads
reconstructed by the proposed method match the actual roads better than
those reconstructed by two other road reconstruction algorithms.
Experiments with 50 road images taken by the autonomous land vehicle
(ALV) showed that the method is robust with real-world data and that the
reconstructions are fairly consistent with road profiles obtained by
fusion between range images and video images

1 Follower
5 Reads
  • Source
    • "It is a two dimensional line following experiment where the line can be curved but stays always in a plane parallel to the image plane of the camera. Other works are related to 3D reconstruction of a profile: e.g., in [3], [4], the authors deal with the 3D reconstruction of road geometry for autonomous land vehicles. This is a profile following task limited to 2 DOF, with assumptions that are specific to this type of application (e.g., the distance of the camera with respect to the road is a known constant) that cannot be used in our problem. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents the visual servoing of a six degrees of freedom (6-DOF) manipulator for unknown three-dimensional profile following. The profile has an unknown curvature, but its cross section is known. The visual servoing keeps the transformation between a cross section of the profile and the camera constant with respect to 6 DOE The position of the profile with respect to only five degrees of freedom can be measured with the camera since the image does not provide position information along the profile. The kinematic model of the robot is used to reconstruct the displacement along the profile, i.e., the sixth degree of freedom, and allows to control the profile-following velocity. Experiments show good accuracy for positioning at a sampling rate of 50 Hz. Two control strategies are tested: proportional-integral control and generalized predictive control (GPC). The visual servoing exhibits better accuracy with the GPC in simulations and in real experiments on a 6-DOF manipulator due to the predictive property of the algorithm.
    IEEE Transactions on Robotics and Automation 08/2002; 18(4):511-520. DOI:10.1109/TRA.2002.802201
  • Source
    • "Nevertheless, starting from image roadsides location, several reconstruction technics are able to compute 3D parameters of the road. These methods could be very noise sensitive since they need differential minimisation [3], [10] or approximations [18], [14]. Furthermore, since these methods are more often decorrelated from the recognition scheme, errors due to this stage could be dif£cult to manage even if the reconstruction scheme is powerful (see for example [1]). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Vision based road trackers are about to be integrated in current vehicles mainly for security purposes in response to sleepiness problems for example. Nevertheless, such systems must be acceptable for drivers and must have a good reliability both in terms of roadsides recognition and of vehicle location estimation. Such a system must therefore be able to run in spite of difficult situations (due to occlusions, traffic, bad weather conditions, etc). Furthermore, the accuracy of the 3D vehicle estimation must be sufficient in order to feed subsequent warning systems. The system we have designed is able to recognize with reliability the lane sides in the current image and uses a 3D/4D modelling which provides both a good recognition as well as a very accurate 3D parameters estimation (vehicle location, steer angle, road curvatures, etc). The paper focuses mainly on this 3D original estimation stage and presents our recent developments (distance between vehicle and each road side for lane tracking application, analysis distances increasing, vertical road curvature estimation). The algorithm behaviour is then presented in simulated and real situations as well in order to prove the reliability of the approach.
    Intelligent Vehicle Symposium, 2002. IEEE; 07/2002
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Abstract: "Over the last half decade, vision based road following systems have progressed from programs which could travel tens of meters between failures to programs capable of driving many kilometers between failures. System performance is typically limited by the following factors: the reliability of the image segmentation techniques used; the accuracy of the system's estimate of road shape and location; the robustness of the system's shape estimation algorithms when faced with data contaminated by bad observations; and the ability of the system to detect and adapt to changes in road structure and appearance. The YARF road following system presents novel approaches to improving performance in each of these areas. YARF is able to simplify the image segmentation problem by incorporating information about feature appearance as well as feature geometry in the model of road structure. Estimation of the road shape parameters in a data-dependent coordinate system produces dramatic increases in the accuracy of road shape estimation. Use of a robust estimation technique allows YARF to correctly determine the road shape in situations where a least squares based technique would fail due to contaminating data points. Finally, YARF includes techniques for detecting changes in road appearance, verifying intersections or changes in lane structure predicted by a map of the road network, and extracting a model of the visible lane structure of a road from an image. YARF has been tested on a variety of road scenes using a mixture of open- and closed-loop test runs on the Navlab vehicles as well as data collected on videotape and simulations." "24 February 1993." Thesis (Ph. D.)--Carnegie Mellon University, 1993. Includes bibliographical references. Supported in part by the Defense Advanced Research Projects Agency, monitored by TACOM and TEC
Show more

Preview (2 Sources)

5 Reads
Available from