PRIMITIVE VISUAL RELATION FEATURE DESCRIPTOR APPLIED TO STEREO VISION
DOI:
https://doi.org/10.47839/ijc.17.3.1037Keywords:
Image Local Descriptor, Dense Depth Map, Visual Primitives, Vision Stereo, PCA, GPU.Abstract
In this study, we present a novel local image descriptor, which is very efficient to compute densely, with semantic information based on visual primitives and relations between them, namely, coplanarity, cocolority, distance and angle. The designed feature descriptor covers both geometric and appearance information. The proposed descriptor has demonstrated its ability to compute dense depth maps from image pairs with a good performance evaluated by the Bad Matched Pixel criterion. Since novel descriptor is very high dimensional, we show that a compact descriptor can be sustitable. An analysis of size reduction was performed in order to reduce the computational complexity with no lose of quality by using different algorithms like max-min or PCA. This novel descriptor has a better results than state-of-the-art methods in stereo vision task. Also, an implementation in GPU hardware is presented performing time reduction using a NVIDIA R GeForce R GT640 graphic card and Matlab over a PC with Windows 10.References
D. Scharstein, R. Szeliski, “A taxonomy and evaluation of dense two-frame stereo correspondence algorithms,” International Journal of Computer Vision, Vol. 47, Issue 1, pp. 7-42, 2002.
S. Zhu, R. Gao, Z. Li, “Stereo matching algorithm with guided filter and modified dynamic programming,” Multimedia Tools and Applications, Vol, 76, Issue 1, pp. 199-216, 2017.
O.D. Faugeras and R. Keriven, “Complete dense stereovision using level set methods,” Proceedings of the European Conf. on Computer Vision, June 1998.
V. Kolmogorov, R. Zabih, “Multi-camera scene reconstruction via graph cuts,” Proceedings of the European Conf. Computer vision, Springer, Berlin, Heidelberg, pp. 82-96, 2002.
L. Alvarez et al., “Dense disparity map estimation respecting image discontinuities: A PDE and scale-space based approach,” Journal of Visual Communication and Image Representation, Vol. 13, Issue1, pp. 3-21, 2002.
C. Strecha, R. Fransens, L. Van Gool, “Combined depth and outlier estimation in multi-view stereo,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, Vol. 2.
X. Wang, J. Keller, P. Gader, “Using spatial relationships as features in object recognition,” Annual Meeting of the North American, pp. 160-165, 1997.
O. Henricson, “Interfering homogeneous regions from rich image attributes,” Automatic Extraction of Man-Made objects from Aerial and Space Images, Centro Stefano Franscini Ascona, pp. 13-22, 1991.
J. D. Winter, J. Wagemans, “Contour-based object identification and segmentation: stimuli, norms and data, and software tools,” Behav. Res. Methods Instrum. Comput., Vol 36, Issue 4, pp.604-624, 2004.
V. Gonzalez-Huiltron, V. Ponomaryov, “Robust approach for disparity map estimation based on multilevel decomposition,” IEEE Latin America Transactions, Vol. 14, Issue 6, pp. 2968-2973, 2016.
V. Gonzalez-Huiltron, V. I. Ponomaryov, E. Ramos-Diaz, S. Sadovnychiy, “Parallel Framework for Dense Disparity Map Estimation Using Hamming Distance,” Signal, Image Video Process., vol. 12, no 2, pp. 231-238, 2016.
S. Lee et al., “Robust stereo matching using adaptive random walk with restart algorithm,” Image and Vision Computing, Vol. 37, pp. 1-11, 2015.
S. Birchfield, C. Tomasi, “A pixel dissimilarity measure that is insensitive to image sampling,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 20, Issue 4, pp401-406, 1998.
X. Yong et al., “Descriptor evaluation and feature regression for multimodal image analysis,” Machine Vision and Applications, Vol. 26, Issue 7, pp. 975-990, 2015.
E. Tola, V. Lepetit, P. Fua, “Daisy: An efficient dense descriptor applied to wide-baseline stereo,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol 32, Issue 5, pp. 815-830, 2010.
I. Kokkinos, A. Yuille, “Scale invariance without scale selection,” UCLA: Department of Statistics. [Online]. https://escholarship.org/uc/item/9m811940, 2008.
N. Pugeault, F. Wörgötter, N. Krüger, “Visual primitives: local, condensed, semantically rich visual descriptors and their applications in robotics,” International Journal of Humanoid Robotics, Vol. 7, No. pp. 379-405, 2010.
M. Felsberg, G. Sommer, “The monogenic signal,” IEEE Trans. Signal Processing, Vol. 49, Issue 12, pp. 3136-3144, 2001.
D. Scharstein, R. Szeliski, and H. Hirschmller, Middlebury Stereo Vision Page. [Online]. Available: vision.middlebury.edu/stereo/, 2016.
E. Iranmehr, S. Kasaei, “An efficient FPGA implementation of DAISY descriptor based on pipeline and multicycle architectures,” Int. Journal of Mechatronics, Vol. 8, Issue 27, pp. 3745-3752, 2018.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
