An algorithm based on photo consistency for image feature point matching

Matching image feature point by the SURF (Speed-up Robust Features) algorithm needs to loop through all feature points on the image to be matched, which will take a long computation time. In order to solve this problem, it is proved based on the photo consistency that the Hessian matrix determinants between the matched feature points are equal in theory. Experimental results show that because of the influences of light and other elements, the ratio of the Hessian matrix determinant of 95 percent of the correct SURF feature point's pairs is between 0.7 and 1.5. Based on the relation of the Hessian matrix determinants between the matched feature points, a fast image feature point matching algorithm is proposed, which improves the recognition rate of feature points, and it makes over twice faster than the SURF algorithm.

[1]  Wolfram Burgard,et al.  A benchmark for the evaluation of RGB-D SLAM systems , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Arturo Gil,et al.  Occupancy grid based graph-SLAM using the distance transform, SURF features and SGD , 2015, Eng. Appl. Artif. Intell..

[3]  Tian Guo.  QR Code Based Semantic Map Building in Domestic Semi-Unknown Environment , 2010 .

[4]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Ye You.  The Research of SLAM Monocular Vision Based on The Improved SURF Feather , 2014, 2014 International Conference on Computational Intelligence and Communication Networks.

[6]  Yanling Liu,et al.  Research on Image Based on Improved SURF Feature Matching , 2014, 2014 Seventh International Symposium on Computational Intelligence and Design.

[7]  Jie Li,et al.  Face Recognition Based on Improved SURF , 2013, 2013 Third International Conference on Intelligent System Design and Engineering Applications.

[8]  Naoya Takeishi,et al.  Evaluation of Interest-region Detectors and Descriptors for Automatic Landmark Tracking on Asteroids , 2015 .

[9]  Dong Zhe,et al.  Image matching method based on improved SURF algorithm , 2015, 2015 IEEE International Conference on Computer and Communications (ICCC).

[10]  Seungwon Oh,et al.  Dynamic EKF-based SLAM for autonomous mobile convergence platforms , 2014, Multimedia Tools and Applications.

[11]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[12]  M. Bleyer.  Does Color Really Help in Dense Stereo Matching ? , 2010 .

[13]  Zhang Huijuan,et al.  Fast image matching based-on improved SURF algorithm , 2011, 2011 International Conference on Electronics, Communications and Control (ICECC).

[14]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .