Vision-Based Bicycle Detection Using Multiscale Block Local Binary Pattern

Bicycle traffic has heavy proportion among all travel modes in some developing countries, which is crucial for urban traffic control and management as well as facility design. This paper proposes a real-time multiple bicycle detection algorithm based on video. At first, an effective feature called multiscale block local binary pattern (MBLBP) is extracted for representing the moving object, which is a well-classified feature to distinguish between bicycles and nonbicycles; then, a cascaded bicycle classifier trained by AdaBoost algorithm is proposed, which has a good computation efficiency. Finally, the method is tested with video sequence captured from the real-world traffic scenario. The bicycles in the test scenario are successfully detected.

[1]  David A Noyce,et al.  Development of Bicycle and Pedestrian Detection and Classification Algorithm for Active-Infrared Overhead Vehicle Imaging Sensors , 2006 .

[2]  Hongyu Hu,et al.  Robust Detection and Tracking Algorithm of Multiple Objects in Complex Scenes , 2014 .

[3]  Kevin J. Krizec.  Estimating the Economic Benefits of Bicycling and Bicycle Facilities: an Interpretive Review and Proposed Methods , 2007 .

[4]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[5]  John H. Dukesherer,et al.  A hybrid Hough-Hausdorff method for recognizing bicycles in natural scenes , 2001, 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace (Cat.No.01CH37236).

[6]  Nikolaos Papanikolopoulos,et al.  A ROBUST VIDEO-BASED BICYCLE COUNTING SYSTEM , 1999 .

[7]  Guizhu Wang,et al.  Research on the Classifier for Bicycle Flow Detecting Device , 2002 .

[8]  Lie Guo,et al.  Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine , 2012, Expert Syst. Appl..

[9]  Birgitta Gatersleben,et al.  Contemplating Cycling to Work: Attitudes and Perceptions in Different Stages of Change , 2007 .

[10]  Tianjun Feng,et al.  Research on bicycle conversion factors , 2008 .

[11]  Wuhong Wang,et al.  Incident Tree Model and Incident Tree Analysis Method for Quantified Risk Assessment: An In-depth Accident Study in Traffic Operation , 2010 .

[12]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[13]  R Leschinski.  EVALUATION OF INDUCTIVE LOOPS FOR BICYCLE DETECTION , 1994 .

[14]  Zhihui Li,et al.  Fast Pedestrian Recognition Based on Multisensor Fusion , 2012 .

[15]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Stefano Messelodi,et al.  Vision-based bicycle/motorcycle classification , 2007, Pattern Recognit. Lett..

[17]  Paul A. Viola,et al.  Robust Real-time Object Detection , 2001 .

[18]  James V. Krogmeier,et al.  Design Considerations for Detecting Bicycles with Inductive Loop Detectors , 2006 .

[19]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..