CLARK: a heterogeneous sensor fusion method for finding lanes and obstacles

Abstract This paper describes Combined Likelihood Adding Radar Knowledge (CLARK), a new method for detecting lanes and obstacles by fusing information from two forward-looking vehicle mounted sensors—vision and radar. CLARK has three stages: (1) obstacle detection using a novel template matching approach; (2) lane detection using a modified version of the Likelihood Of Image Shape algorithm; (3) simultaneous estimation of both obstacle and lane positions by locally maximizing a combined likelihood function. Experimental results illustrating the efficacy of these components are presented. CLARK detects the position of lanes and obstacles accurately, even under significantly noisy conditions.

[1]  Sridhar Lakshmanan,et al.  Lane Boundary Detection Using Deformable Templates: Effects of Image Subsampling on Detected Lane Edge , 1995, ACCV.

[2]  Charles E. Thorpe,et al.  Range sensor based outdoor vehicle Navigation, collision avoidance and parallel parking , 1995, Auton. Robots.

[3]  Han Wang,et al.  Recent Developments in Computer Vision , 1995, Lecture Notes in Computer Science.

[4]  Lamberto Raffaelli,et al.  Millimeter-wave automotive radars: the markets, technologies, and production costs , 1995, Other Conferences.

[5]  Klaus-Werner Jörg.  World modeling for an autonomous mobile robot using heterogenous sensor information , 1995, Robotics Auton. Syst..

[6]  Yoram Koren,et al.  Real-time obstacle avoidance for fact mobile robots , 1989, IEEE Trans. Syst. Man Cybern..

[7]  Todd Jochem,et al.  Rapidly Adapting Machine Vision for Automated Vehicle Steering , 1996, IEEE Expert.

[8]  Karl C. Kluge,et al.  Extracting road curvature and orientation from image edge points without perceptual grouping into features , 1994, Proceedings of the Intelligent Vehicles '94 Symposium.

[9]  Volker Graefe,et al.  Visual recognition of obstacles on roads , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[10]  G. Grimmett,et al.  Probability and random processes , 2002 .

[11]  S.A. Kassam,et al.  Robust techniques for signal processing: A survey , 1985, Proceedings of the IEEE.

[12]  Michael J. Goodman,et al.  DASCAR sensor suite and video data system , 1997, Other Conferences.

[13]  P. L. Wisely.  The design of wide angle head up displays for synthetic vision , 1995 .

[14]  Andrew Gerald Stove,et al.  Linear FMCW radar techniques , 1992 .

[15]  Bruce A. Draper,et al.  Color machine vision for autonomous vehicles , 1998 .

[16]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[17]  Richard J. Carter,et al.  Feasibility of a Portable Data Acquisition System for Driver Performance Testing , 1996 .

[18]  S. Tokoro.  Automotive application systems of a millimeter-wave radar , 1996, Proceedings of Conference on Intelligent Vehicles.

[19]  K. Saneyoshi.  3-D image recognition system by means of stereoscopy combined with ordinary image processing , 1994, Proceedings of the Intelligent Vehicles '94 Symposium.

[20]  L. H. Eriksson,et al.  A high performance automotive radar for automatic AICC , 1995, IEEE Aerospace and Electronic Systems Magazine.

[21]  Ernst D. Dickmanns,et al.  An integrated spatio-temporal approach to automatic visual guidance of autonomous vehicles , 1990, IEEE Trans. Syst. Man Cybern..

[22]  J. D. Woll.  VORAD collision warning radar , 1995, Proceedings International Radar Conference.

[23]  S. Nakayama,et al.  An image processing architecture and a motion control method for an autonomous vehicle , 1992, Proceedings of the Intelligent Vehicles `92 Symposium.

[24]  Sridhar Lakshmanan,et al.  A deformable-template approach to lane detection , 1995, Proceedings of the Intelligent Vehicles '95. Symposium.

[25]  Kenichi Yamada,et al.  Development of rear-end collision avoidance system , 1996, Proceedings of Conference on Intelligent Vehicles.

[26]  P. Ganci,et al.  A forward looking automotive radar sensor , 1995, Proceedings of the Intelligent Vehicles '95. Symposium.

[27]  Massimo Bertozzi,et al.  Real-time lane and obstacle detection on the GOLD system , 1996, Proceedings of Conference on Intelligent Vehicles.

[28]  D. Langer,et al.  Fusing radar and vision for detecting, classifying and avoiding roadway obstacles , 1996, Proceedings of Conference on Intelligent Vehicles.

[29]  Jing-Yu Yang,et al.  Obstacle detection and environment modeling based on multisensor fusion for robot navigation , 1996, Artif. Intell. Eng..

[30]  Andreas Kuehnle,et al.  Symmetry-based recognition of vehicle rears , 1991, Pattern Recognit. Lett..

[31]  Mei Chen,et al.  AURORA: a vision-based roadway departure warning system , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[32]  A.G. Ulsoy,et al.  CAPC: A Road-Departure Prevention System , 1996, IEEE Control Systems.

[33]  Thomas E. McEwan,et al.  Micropower impulse radar , 1997 .

[34]  Sridhar Lakshmanan,et al.  Building world models for mobile platforms using heterogeneous sensors fusion and temporal analysis , 1997, Proceedings of Conference on Intelligent Transportation Systems.

[35]  W. Ritter,et al.  Obstacle detection based on color blob flow , 1995, Proceedings of the Intelligent Vehicles '95. Symposium.

[36]  Christopher M. Kreucher,et al.  LANA: a lane extraction algorithm that uses frequency domain features , 1999, IEEE Trans. Robotics Autom..

[37]  Karl C. Kluge.  Performance evaluation of vision-based lane sensing: some preliminary tools, metrics, and results , 1997, Proceedings of Conference on Intelligent Transportation Systems.

[38]  N. Nakano,et al.  Lane recognition system for guiding of autonomous vehicle , 1992, Proceedings of the Intelligent Vehicles `92 Symposium.