A vision-based method for on-road truck height measurement in proactive prevention of collision with overpasses and tunnels

Abstract Over-height trucks are continuously striking low clearance overpasses and tunnels. This has led to significant damage, fatalities, and inconvenience to the public. Smart systems can automatically detect and warn oversize trucks, and have been introduced to provide the trucks with the opportunity to avoid a collision. However, high cost of implementing these systems remains a bottleneck for their wide adoption. This paper evaluates the feasibility of using computer vision to detect over-height trucks. In the proposed method, video streams are collected from a surveillance camera attached on the overpass/tunnel, and processed to measure truck heights. The height is measured using line detection and blob tracking which locate upper and lower points of a truck in pixel coordinates. The pixel coordinates are then translated into 3D world coordinates. Proof-of-concept experiment results signify the high performance of the proposed method and its potential in achieving cost-effective monitoring of over-height trucks in the transportation system. The limitations and considerations of the method for field implementation are also discussed.

[1]  Alan L. Yuille,et al.  Manhattan World: compass direction from a single image by Bayesian inference , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[2]  Carolina Burnier,et al.  Intelligent Transportation Systems Benefits, Costs, Deployment, and Lessons Learned Desk Reference: 2011 Update , 2011 .

[3]  Jacob Scharcanski,et al.  A Particle-Filtering Approach for Vehicular Tracking Adaptive to Occlusions , 2011, IEEE Transactions on Vehicular Technology.

[4]  Rama Chellappa,et al.  Robust Height Estimation of Moving Objects From Uncalibrated Videos , 2010, IEEE Transactions on Image Processing.

[5]  Gangbing Song,et al.  An overheight vehicle–bridge collision monitoring system using piezoelectric transducers , 2007 .

[6]  Lionel Prevost,et al.  A Cascade of Boosted Generative and Discriminative Classifiers for Vehicle Detection , 2008, EURASIP J. Adv. Signal Process..

[7]  F. C. Hadipriono,et al.  ANALYSIS OF RECENT BRIDGE FAILURES IN THE UNITED STATES , 2003 .

[8]  Dani Lischinski,et al.  The Shadow Meets the Mask: Pyramid‐Based Shadow Removal , 2008, Comput. Graph. Forum.

[9]  Stanley T. Birchfield,et al.  A Taxonomy and Analysis of Camera Calibration Methods for Traffic Monitoring Applications , 2010, IEEE Transactions on Intelligent Transportation Systems.

[10]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[12]  Ian D. Reid,et al.  Single View Metrology , 2000, International Journal of Computer Vision.

[13]  Mark S. Drew,et al.  Removing Shadows from Images , 2002, ECCV.

[14]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  Rafael Grompone von Gioi,et al.  LSD: A Fast Line Segment Detector with a False Detection Control , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  B. S. Manjunath,et al.  The multiRANSAC algorithm and its application to detect planar homographies , 2005, IEEE International Conference on Image Processing 2005.

[17]  ZuWhan Kim,et al.  Evaluation of feature-based vehicle trajectory extraction algorithms , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[18]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Joseph V. Sinfield.  Synthesis Study: Development of an Electronic Detection and Warning System to Prevent Overheight Vehicles from Impacting Overhead Bridges , 2010 .

[20]  Jake K. Aggarwal,et al.  Robust Vehicle Detection for Tracking in Highway Surveillance Videos Using Unsupervised Learning , 2009, 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance.

[21]  R L Gordon,et al.  Traffic Control Systems Handbook , 1996 .

[22]  Nigel J. B. McFarlane,et al.  Segmentation and tracking of piglets in images , 1995, Machine Vision and Applications.

[23]  Andrea Fusiello,et al.  Robust Multiple Structures Estimation with J-Linkage , 2008, ECCV.

[24]  P M Cawley.  EVALUATION OF OVERHEIGHT VEHICLE DETECTION/WARNING SYSTEMS , 2002 .

[25]  Derek Hoiem,et al.  Single-image shadow detection and removal using paired regions , 2011, CVPR 2011.

[26]  A K Agrawal.  Bridge vehicle impact assessment. , 2011 .

[27]  Qi Tian,et al.  Foreground object detection from videos containing complex background , 2003, MULTIMEDIA '03.

[28]  Seth J. Teller,et al.  Automatic recovery of relative camera rotations for urban scenes , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[29]  Alireza Behrad,et al.  Over-Height Vehicle Detection in Low Headroom Roads Using Digital Video Processing , 2008 .

[30]  Gang-Len Chang,et al.  Overheight Vehicle Collisions with Highway Bridges , 2004 .

[31]  Jean-Philippe Tardif,et al.  Non-iterative approach for fast and accurate vanishing point detection , 2009, 2009 IEEE 12th International Conference on Computer Vision.