Image Mosaic Intelligent Vehicle Around View Monitoring System Based on Ring Fusion Method

In order to solve the problem that the edge correction effect of fish-eye image is poor, we proposed a radial de-distortion method. The mapping relationship between the distortion point and the aberration point in the image coordinate system is established by the division model based on the radial distortion. We also setup ideal pattern to extract the target position of correction. Aiming at the problem of low degree of automation and low accuracy in the process of mosaic, the integrated corner detection method is used to automatically extract the coordinate position of the corner points in the calibration pattern. Aiming at the problem that the brightness of each region is inconsistent and the transition effect is not good, the ring fusion method is designed to fuse the image. The experimental results show that the proposed algorithm has the average pixel error of 1.792, the accuracy and efficiency of corner extraction is 100%, which effectively improve the automation degree of the algorithm.

[1]  S. M. Santhanam,et al.  Lens distortion correction and geometrical alignment for Around View Monitoring system , 2014, The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014).

[2]  Benjamin Bustos,et al.  Harris 3D: a robust extension of the Harris operator for interest point detection on 3D meshes , 2011, The Visual Computer.

[3]  Yoshiko Kojima,et al.  A Multimodal ADAS System for Unmarked Urban Scenarios Based on Road Context Understanding , 2015, IEEE Transactions on Intelligent Transportation Systems.

[4]  Jake K. Aggarwal,et al.  Intrinsic parameter calibration procedure for a (high-distortion) fish-eye lens camera with distortion model and accuracy estimation , 1996, Pattern Recognit..

[5]  Gao Hong-b.  Research of Intelligent Vehicle Variable Granularity Evaluation Based on Cloud Model , 2016 .

[6]  Le-Nan Wu,et al.  An adaptive threshold for the Canny Operator of edge detection , 2010, 2010 International Conference on Image Analysis and Signal Processing.

[7]  A. Agarwala,et al.  Optimizing content-preserving projections for wide-angle images , 2009, SIGGRAPH 2009.

[8]  Hongbin Zha,et al.  Radial distortion correction from a single image of a planar calibration pattern using convex optimization , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[9]  Sing Bing Kang,et al.  Parameter-Free Radial Distortion Correction with Center of Distortion Estimation , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Xinyu Zhang,et al.  A study on key technologies of unmanned driving , 2016, CAAI Trans. Intell. Technol..

[11]  Yingen Xiong,et al.  Mobile panoramic imaging system , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[12]  Dancheng Li,et al.  3D Point Sets Matching Method Based on Moravec Vertical Interest Operator , 2012 .

[13]  Zetao Jiang,et al.  Stitching method for distorted image based on SIFT feature matching , 2012, 2012 8th International Conference on Computing and Networking Technology (INC, ICCIS and ICMIC).

[14]  Ching-Lung Su,et al.  3D AVM system for automotive applications , 2015, 2015 10th International Conference on Information, Communications and Signal Processing (ICICS).

[15]  Yu Liu,et al.  Automatic chessboard corner detection method , 2016, IET Image Process..

[16]  Augusto Sarti,et al.  Piecewise distortion correction for fisheye lenses , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[17]  Roland Siegwart,et al.  Automatic detection of checkerboards on blurred and distorted images , 2008 .