Scale-invariant representation of light field images for object recognition and tracking

We propose a scale-invariant feature descriptor for representation of light-field images. The proposed descriptor can significantly improve tasks such as object recognition and tracking on images taken with recently popularized light field cameras. We test our proposed representation using various light field images of different types, both synthetic and real. Our experiments showvery promising results in terms of retaining invariance under various scaling transformations.

[1]  Shree K. Nayar,et al.  PiCam , 2013, ACM Trans. Graph..

[2]  Pier Luigi Dragotti,et al.  Segmentation of Epipolar-Plane Image Volumes with Occlusion and Disocclusion Competition , 2006, 2006 IEEE Workshop on Multimedia Signal Processing.

[3]  Andrea Vedaldi,et al.  Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[4]  Ramesh Raskar,et al.  Near-invariant blur for depth and 2D motion via time-varying light field analysis , 2013, TOGS.

[5]  Ivana Tosic,et al.  Dictionary Learning for Incoherent Sampling with application to plenoptic imaging , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[7]  Edward H. Adelson,et al.  Single Lens Stereo with a Plenoptic Camera , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

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

[9]  Josef Kittler,et al.  A survey of the hough transform , 1988, Comput. Vis. Graph. Image Process..

[10]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[11]  Yael Pritch,et al.  Scene reconstruction from high spatio-angular resolution light fields , 2013, ACM Trans. Graph..

[12]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[13]  Minh N. Do,et al.  Ieee Transactions on Image Processing on the Bandwidth of the Plenoptic Function , 2022 .

[14]  Gordon Wetzstein,et al.  Compressive light field photography using overcomplete dictionaries and optimized projections , 2013, ACM Trans. Graph..

[15]  J. Berent,et al.  Plenoptic Manifolds , 2007, IEEE Signal Processing Magazine.

[16]  Andrew P. Papli.  Rotation-Invariant Categorization of Colour Images using the Radon Transform , 2012 .

[17]  Zhan Yu,et al.  Lytro camera technology: theory, algorithms, performance analysis , 2013, Electronic Imaging.

[18]  Robert C. Bolles,et al.  Epipolar-plane image analysis: An approach to determining structure from motion , 1987, International Journal of Computer Vision.

[19]  Tom E. Bishop,et al.  The Light Field Camera: Extended Depth of Field, Aliasing, and Superresolution , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Kiran B. Raja,et al.  A novel image fusion scheme for robust multiple face recognition with light-field camera , 2013, Proceedings of the 16th International Conference on Information Fusion.

[21]  Sven Wanner,et al.  Globally Consistent Multi-label Assignment on the Ray Space of 4D Light Fields , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Laurent Wendling,et al.  A new shape descriptor defined on the Radon transform , 2006, Comput. Vis. Image Underst..

[23]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[24]  S. Helgason.  The Radon Transform , 1980 .

[25]  Tomasz Arodz.  Invariant Object Recognition Using Radon-based Transform , 2005, Comput. Artif. Intell..

[26]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).