The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.05 - May (2010 vol.32)
pp: 815-830
Engin Tola , Ecole Polytechnic Fédérale de Lausanne (EPFL), Lausanne
Vincent Lepetit , Ecole Polytechnic Fédérale de Lausanne (EPFL), Lausanne
Pascal Fua , Ecole Polytechnic Fédérale de Lausanne (EPFL), Lausanne
ABSTRACT
In this paper, we introduce a local image descriptor, DAISY, which is very efficient to compute densely. We also present an EM-based algorithm to compute dense depth and occlusion maps from wide-baseline image pairs using this descriptor. This yields much better results in wide-baseline situations than the pixel and correlation-based algorithms that are commonly used in narrow-baseline stereo. Also, using a descriptor makes our algorithm robust against many photometric and geometric transformations. Our descriptor is inspired from earlier ones such as SIFT and GLOH but can be computed much faster for our purposes. Unlike SURF, which can also be computed efficiently at every pixel, it does not introduce artifacts that degrade the matching performance when used densely. It is important to note that our approach is the first algorithm that attempts to estimate dense depth maps from wide-baseline image pairs, and we show that it is a good one at that with many experiments for depth estimation accuracy, occlusion detection, and comparing it against other descriptors on laser-scanned ground truth scenes. We also tested our approach on a variety of indoor and outdoor scenes with different photometric and geometric transformations and our experiments support our claim to being robust against these.
INDEX TERMS
Image processing and computer vision, dense depth map estimation, local descriptors.
CITATION
Engin Tola, Vincent Lepetit, Pascal Fua, "DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.32, no. 5, pp. 815-830, May 2010, doi:10.1109/TPAMI.2009.77
REFERENCES
[1] L. Alvarez, R. Deriche, J. Weickert, and J., Sanchez, "Dense Disparity Map Estimation Respecting Image Discontinuities: A PDE and Scale-Space Based Approach," J. Visual Comm. and Image Representation, vol. 13, nos. 1/2, pp. 3-21, Mar. 2002.
[2] N. Ayache and F. Lustman, "Fast and Reliable Passive Trinocular Stereovision," Proc. Int'l Conf. Computer Vision, June 1987.
[3] H.H. Baker and T.O. Binford, "Depth from Edge and Intensity Based Stereo," Proc. Int'l Joint Conf. Artificial Intelligence, vol. 2, pp. 631-636, Aug. 1981.
[4] H. Bay, T. Tuytelaars, and L. Van Gool, "SURF: Speeded Up Robust Features," Proc. European Conf. Computer Vision, 2006.
[5] A.C. Berg and J. Malik, "Geometric Blur for Template Matching," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 607-614, 2001.
[6] S. Birchfield and C. Tomasi, "A Pixel Dissimilarity Measure that is Insensitive to Image Sampling," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 4, pp. 401-406, Apr. 1998.
[7] A. Bosch, A. Zisserman, and X. Munoz, "Scene Classification via pLSA," Proc. European Conf. Computer Vision, 2006.
[8] Y. Boykov, O. Veksler, and R. Zabih, "Fast Approximate Energy Minimization via Graph Cuts," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1222-1239, Nov. 2001.
[9] M.Z. Brown, D. Burschka, and G.D. Hager, "Advances in Computational Stereo," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 8, pp. 993-1008, Aug. 2003.
[10] F. Devernay and O.D. Faugeras, "Computing Differential Properties of 3D Shapes from Stereoscopic Images without 3D Models," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 208-213, June 1994.
[11] O.D. Faugeras and R. Keriven, "Complete Dense Stereovision Using Level Set Methods," Proc. European Conf. Computer Vision, June 1998.
[12] L. Fei-Fei and P. Perona, "A Bayesian Hierarchical Model for Learning Natural Scene Categories," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005.
[13] D. Geiger, B. Ladendorf, and A. Yuille, "Occlusions and Binocular Stereo," Int'l J. Computer Vision, vol. 14, pp. 211-226, 1995.
[14] S.S. Intille and A.F. Bobick, "Disparity-Space Images and Large Occlusion Stereo," Proc. European Conf. Computer Vision, pp. 179-186, May 1994.
[15] T. Kanade and M. Okutomi, "A Stereo Matching Algorithm with an Adaptative Window: Theory and Experiment," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 9, pp. 920-932, Sept. 1994.
[16] V. Kolmogorov and R. Zabih, "Multi-Camera Scene Reconstruction via Graph Cuts," Proc. European Conf. Computer Vision, May 2002.
[17] K.N. Kutulakos and S.M. Seitz, "A Theory of Shape by Space Carving," Int'l J. Computer Vision, vol. 38, no. 3, pp. 197-216, July 2000.
[18] S. Lazebnik, C. Schmid, and J. Ponce, "Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2006.
[19] D.G. Lowe, "Distinctive Image Features from Scale Invariant Keypoints," Int'l J. Computer Vision, vol. 20, no. 2, pp. 91-110, 2004.
[20] G. Medioni, C.K. Tang, and M.S. Lee, "Tensor Voting: Theory and Applications," Proc. Reconnaissance des Formes et Intelligence in Artificielle, 2000.
[21] K. Mikolajczyk and C. Schmid, "A Performance Evaluation of Local Descriptors," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 10, pp. 1615-1630, Oct. 2005.
[22] F. Porikli, "Integral Histogram: A Fast Way to Extract Histograms in Cartesian Spaces," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 829-836, 2005.
[23] L.H. Quam, "Hierarchical Warp Stereo," Readings in Computer Vision: Issues, Problems, Principles, and Paradigms, pp. 80-86, Morgan Kaufmann, 1987.
[24] S. Roy and I.J. Cox, "A Maximum-Flow Formulation of the N-Camera Stereo Correspondence Problem," Proc. Int'l Conf. Computer Vision, pp. 492-499, 1998.
[25] D. Scharstein and R. Szeliski, "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms," Int'l J. Computer Vision, vol. 47, nos. 1-3, pp. 7-42, Apr.-June 2002.
[26] C. Strecha, R. Fransens, and L. Van Gool, "Combined Depth and Outlier Estimation in Multi-View Stereo," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2006.
[27] C. Strecha, T. Tuytelaars, and L. Van Gool, "Dense Matching of Multiple Wide Baseline Views," Proc. Int'l Conf. Computer Vision, 2003.
[28] C. Strecha, W. von Hansen, L. Van Gool, P. Fua, and U. Thoennessen, "On Benchmarking Camera Calibration and Multi-View Stereo for High Resolution Imagery," Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2008.
[29] C. Strecha, Multi-View Evaluation, http://cvlab.epfl.chdata, 2008.
[30] E. Tola, Daisy Code, http://cvlab.epfl.chsoftware, 2008.
[31] T. Tuytelaars and L. Van Gool, "Wide Baseline Stereo Matching Based on Local, Affinely Invariant Regions," Proc. British Machine Vision Conf., pp. 412-422, 2000.
[32] S.A. Winder and M. Brown, "Learning Local Image Descriptors," Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2007.
[33] J. Yao and W.-K. Cham, "3D Modeling and Rendering from Multiple Wide Baseline Images," Signal Processing: Image Comm., vol. 21, pp. 506-518, 2006.
9 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool