A research of pavement potholes detection based on three-dimensional projection transformation

In order to detect the three-dimensional cross-section of pavement pothole more effectively, this paper proposes a method which employs optical imaging principle of three-dimensional projection transformation to obtain pictorial information of pothole's cross-section in pothole detection. Multiple digital image processing technologies, including: image preprocessing, binarization, thinning, three-dimensional reconstruction, error analysis and compensation are conducted in the series of image analysis and processing. Experimental results indicate that the method is markedly superior to traditional methods in many aspects. For its simple detection principle, low cost and high efficiency, the method suggests great practical and promoting value.

[1]  J. Maxwell A Treatise on Electricity and Magnetism , 1873, Nature.

[2]  Xinyu Cheng,et al.  The simple camera calibration approach based on a triangle and depth estimation from monocular vision , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Xiaohui Hu,et al.  Development on surface defect holes inspection based on image recognition , 2010, 2010 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.

[4]  Mi Gang The latest technology of intelligent detection of highway pavement at home and abroad , 2009 .

[5]  Wensheng Wu,et al.  Design and Application of 3D Laser Profile Data Acquisition System , 2011 .

[6]  M. Avila,et al.  Detection of defects in road surface by a vision system , 2008, MELECON 2008 - The 14th IEEE Mediterranean Electrotechnical Conference.

[7]  Wei Li,et al.  Automatic pavement cracks detection system based on Visual Studio C++ 6.0 , 2010, 2010 Sixth International Conference on Natural Computation.

[8]  Sha Aimin,et al.  Study of image-based pavement cracking measurement techniques , 2009, 2009 9th International Conference on Electronic Measurement & Instruments.