An Energy Minimization Approach to Automatic Traffic Camera Calibration

We present a method for automatic calibration of traffic cameras. The problem is formulated as one of energy minimization in reduced road-parameter space, from which internal and external camera parameters are determined. Our approach combines bottom-up processing of a video to find a vanishing point, lines in the background, and a directed activity map, along with top-down processing to fit a road model to these detected features using Markov chain Monte Carlo (MCMC). Enhanced autocorrelation along the dashed lines is used in conjunction with a best-fit road model to find road-to-image parameters. To maximize both robustness to noise and flexibility (e.g., to handle cases in which the camera is looking straight down the road), a single-vanishing-point length-based approach (VWL, according to the taxonomy in the work of Kanhere and Birchfield) is used. On a large number of data sets exhibiting a wide variety of conditions (including distractions such as bridges and on/off-ramps), our approach performs well, achieving less than 10% error in measuring test lengths in all cases.

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

[2]  Daniel J. Dailey,et al.  An algorithm to estimate mean traffic speed using uncalibrated cameras , 2000, IEEE Trans. Intell. Transp. Syst..

[3]  Kai-Tai Song,et al.  Dynamic Calibration of Pan–Tilt–Zoom Cameras for Traffic Monitoring , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  N. H. C. Yung,et al.  Lane detection by orientation and length discrimination , 2000, IEEE Trans. Syst. Man Cybern. Part B.

[5]  Nelson H. C. Yung,et al.  New method for overcoming ill-conditioning in vanishing-point-based camera calibration , 2007 .

[6]  Daniel J. Dailey,et al.  Dynamic camera calibration of roadside traffic management cameras for vehicle speed estimation , 2003, IEEE Trans. Intell. Transp. Syst..

[7]  J. D. Crisman,et al.  An easy to install camera calibration for traffic monitoring , 1997, Proceedings of Conference on Intelligent Transportation Systems.

[8]  N. H. C. Yung,et al.  A Method for Vehicle Count in the Presence of Multiple-Vehicle Occlusions in Traffic Images , 2007, IEEE Transactions on Intelligent Transportation Systems.

[9]  Shi Peng-fei,et al.  Efficient method for camera calibration in traffic scenes , 2004 .

[10]  Osama Masoud,et al.  Detection and classification of vehicles , 2002, IEEE Trans. Intell. Transp. Syst..

[11]  Rong Dong,et al.  An Automatic Calibration Method for PTZ Camera in Expressway Monitoring System , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.

[12]  Tieniu Tan,et al.  Practical camera auto-calibration based on object appearance and motion for traffic scene visual surveillance , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  N.H.C. Yung,et al.  Vehicle shape approximation from motion for visual traffic surveillance , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[14]  法律.  Manual on Uniform Traffic Control Devices , 2010 .

[15]  Massimo Bertozzi,et al.  GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection , 1998, IEEE Trans. Image Process..

[16]  Daniel J. Dailey,et al.  Algorithms for Calibrating Roadside Traffic Cameras and Estimating Mean Vehicle Speed , 2004, 2007 IEEE Intelligent Transportation Systems Conference.

[17]  Wei-Hsin Chen,et al.  Dynamic CCD camera calibration for traffic monitoring and vehicle applications , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.

[18]  Martin Kampel,et al.  Camera auto-calibration using pedestrians and zebra-crossings , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

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

[20]  Roger Y. Tsai,et al.  A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses , 1987, IEEE J. Robotics Autom..

[21]  Briarcliff Manor.  Interactive Calibration of a PTZ Camera for Surveillance Applications , 2001 .

[22]  Wei Zhang,et al.  Tracking and Pairing Vehicle Headlight in Night Scenes , 2012, IEEE Transactions on Intelligent Transportation Systems.

[23]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Matthew Crosby,et al.  Association for the Advancement of Artificial Intelligence , 2014 .

[25]  Wayne A Sarasua,et al.  Real-Time Detection and Tracking of Vehicle Base Fronts for Measuring Traffic Counts and Speeds on Highways , 2007 .

[26]  Yunfeng Ai,et al.  On Automatic and Dynamic Camera Calibration based on Traffic Visual Surveillance , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[27]  D.J. Dailey,et al.  One-parameter camera calibration for traffic management cameras , 2004, Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749).

[28]  Z. Zivkovic.  Improved adaptive Gaussian mixture model for background subtraction , 2004, ICPR 2004.

[29]  Stanley T. Birchfield,et al.  Real-Time Incremental Segmentation and Tracking of Vehicles at Low Camera Angles Using Stable Features , 2008, IEEE Transactions on Intelligent Transportation Systems.

[30]  Wayne A Sarasua,et al.  Automatic Camera Calibration Using Pattern Detection for Vision-Based Speed Sensing , 2008 .

[31]  Matti Karjalainen,et al.  A computationally efficient multipitch analysis model , 2000, IEEE Trans. Speech Audio Process..

[32]  Grantham K. H. Pang,et al.  Camera calibration from road lane markings , 2003 .