New Technique for distance estimation using SIFT for mobile robots

This paper addresses a novel method to estimate distance for autonomous systems, using single monocular camera. The method in essence employs scale parameters obtained from SIFT (Scale Invariant Feature Transform) algorithm and a corresponding zooming factor as inputs to train a neural network which results in the determination of physical distance.

[1]  Åke Björck,et al.  Numerical methods for least square problems , 1996 .

[2]  J. Navarro-Pedreño.  Numerical Methods for Least Squares Problems , 1996 .

[3]  Ray A. Jarvis,et al.  A Perspective on Range Finding Techniques for Computer Vision , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Ming-Chao Chiang,et al.  Local blur estimation and super-resolution , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[6]  Frédéric Guichard,et al.  Uniqueness of blur measure , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[7]  V Aslantas,et al.  Depth from automatic defocusing. , 2007, Optics express.

[8]  François Michaud,et al.  Iterative Design of Advanced Mobile Robots , 2009, J. Comput. Inf. Technol..

[9]  Danica Kragic,et al.  Object Search and Localization for an Indoor Mobile Robot , 2009, J. Comput. Inf. Technol..

[10]  F. Guichard,et al.  UNIQUENESS OF BLUR MEASURES , 2004 .

[11]  Ashutosh Saxena,et al.  High speed obstacle avoidance using monocular vision and reinforcement learning , 2005, ICML.

[12]  M. S. Güzel,et al.  Autonomous Vehicle Navigation Using Vision and Mapless Strategies: A Survey , 2013 .