Abstract
We describe a method for resolving ambiguities in low-level disparity calculations in a stereo-vision scheme by using a recurrent mechanism that we call signal-symbol loop. Due to the local nature of low-level processing it is not always possible to estimate the correct disparity values produced at this level. Symbolic abstraction of the signal produces robust, high confidence, multimodal image features which can be used to interpret the scene more accurately and therefore disambiguate low-level interpretations by biasing the correct disparity. The fusion process is capable of producing more accurate dense disparity maps than the low- and symbolic-level algorithms can produce independently. Therefore we describe an efficient fusion scheme that allows symbolic- and low-level cues to complement each other, resulting in a more accurate and dense disparity representation of the scene.
Similar content being viewed by others
References
Darabiha A., MacLean W., Rose J.: Reconfigurable hardware implementation of a phase-correlation stereoalgorithm. Mach. Vis. Appl. 17(2), 116–132 (2006)
Díaz, J.: Multimodal bio-inspired vision system. High performance motion and stereo processing architecture. PhD thesis, University of Granada, Spain (2006)
Díaz J., Ros E., Carillo R., Prieto A.: Real-time system for high-image-resolution disparity. IEEE Trans. Image Process. 16, 280–285 (2006)
Felsberg M., Kalkan S., Krüger N.: Continuous characterization of image structures of different dimensionality. Image Vis. Comput. 27(6), 628–636 (2009)
Fitzgibbon, A.W., Zisserman, A.: Multibody Structure and Motion: 3-D Reconstruction of Independently Moving Objects. Lecture Notes in Computer Science, vol. 1842, pp. 891–906 (2000)
Fleet D., Jepson A.: Phase-based disparity measurement. Comput. Vis. Graph. Image Process. 53(2), 198–210 (1991)
Fleet D., Jepson A.: Stability of phase information. IEEE Trans. Pattern Anal. Mach. Intell. 15(12), 1253–1268 (1993)
Gautama T., Hulle M.V.: A phase-based approach to the estimation of the optical flow field using spatial filtering. IEEE Trans Neural Netw. 13, 1127–1136 (2002)
Hubel D., Wiesel T.: Anatomical demonstration of columns in the monkey striate cortex. Nature 221, 747–750 (1969)
Kalkan, S., Yan, S., Krüger, V., Wörgötter, F., Krüger, N.: A signal-symbol loop mechanism for enhanced edge extraction. In: International Conference on Computer Vision Theory and Applications VISAPP’08, pp. 214–221 (2008)
Krüger, N.: Three dilemmas of signal- and symbol-based representations in computer vision. In: Proceedings of the Workshop Brain, Vision and Artificial Intelligence, vol. 3704, pp. 167–176 (2005)
Krüger N., Lappe M., Wörgötter F.: Biologically motivated multi-modal processing of visual primitives. Interdiscip. J. Artif. Intell. Simul. Behav. 1(5), 417–427 (2004)
Lee M., Medioni G., Mordohai P.: Inference of segmented overlapping surfaces from binocular stereo. IEEE Trans. Pattern Anal. Mach. Intell. 24, 824–837 (2002)
Medioni G., Lee M., Tang C.: A Computational Framework for Segmentation and Grouping. Elsevier, Amsterdam (2000)
Mordohai P., Medioni G.: Stereo using monocular cues within the tensor voting framework. IEEE Trans. Pattern Anal. Mach. Intell. 28, 968–982 (2006)
Pugeault N.: Early Cognitive Vision: Feedback Mechanisms for the Disambiguation of Early Visual Representation. Vdm Verlag Dr. Müller, Germany (2008)
Pugeault, N., Wörgötter, F., Krüger, N.: Multi-modal scene reconstruction using perceptual grouping constraints. In: Proceedings of the 5th IEEE Computer Society Workshop on Perceptual Organization in Computer Vision, New York City, 22 June 2006 (in conjunction with IEEE CVPR 2006)
Pugeault, N., Wörgötter, F., Krüger, N.: Multi-modal scene reconstruction using preceptual grouping constraints. In: Proceedings of the 5th IEEE Computer Society Workshop on Perceptual Organization in Computer Vision, pp. 195–195 (2006)
Qian G., Chellappa R., Zheng Q.: Bayesian algorithms for simultaneous structure from motion estimation of multiple independently moving objects. IEEE Trans. Image Process. 14, 94–109 (2005)
Ralli J., Díaz J., Ros E.: A method for sparse disparity densification using voting mask propagation. J. Vis. Commun. Image Represent. 21(1), 67–74 (2010)
Ralli, J., Díaz, J., Ros, E.: Spatial and temporal constraints in variational correspondence methods. IEEE Trans. Image Process. (2010, submitted)
Rares, A., Reinders, M., Hendriks, E.: Image interpretation systems. Tech. rep., mCCWS project Technical Report (MCCWS 2.1.1.3.C) (1999)
Sabatini, S., Gastaldi, G., Solari, F., Pauwels, K., van Hulle, M., Diaz, J., Ros, E., Pugeault, N., Krüger, N.: Compact (and accurate) early vision processing in the harmonic space. In: VISAPP (1), vol. 1, pp. 213–220 (2007)
Sabatini, S., Gastaldi, G., Solari, F., Pauwels, K., Van Hulle, M., Diaz, J., Ros, E., Pugeault, N., Krüger, N.: A compact harmonic code for early vision based on anisotropic frequency channels. Comput. Vis. Image Underst. (2010, accepted)
Scharstein D., Szeliski R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vis. 47(1–3), 7–42 (2002)
Solari F., Sabatini S., Bisio G.: Fast technique for phase-based disparity estimation with no explicit calculation of phase. Electron. Lett. 37(23), 1382–1383 (2001)
Tang Y.L., Kasturi R.: Tracking moving objects during low altitude flight. Mach. Vis. Appl. 9, 20–31 (1996)
Weems, C.C.: Architectural requirements of image understanding with respect to parallel processing. In: Proceedings of the IEEE, vol. 79, no. (4), pp. 537–547 (1991)
Author information
Authors and Affiliations
Corresponding author
Electronic Supplementary Material
The Below is the Electronic Supplementary Material.
ESM 1 (AVI 28253 kb)
Rights and permissions
About this article
Cite this article
Ralli, J., Díaz, J., Kalkan, S. et al. Disparity disambiguation by fusion of signal- and symbolic-level information. Machine Vision and Applications 23, 65–77 (2012). https://doi.org/10.1007/s00138-010-0266-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-010-0266-z