nach oben

International Journal of Computer Vision

Erschienen in:

01.01.2014

Accurate Junction Detection and Characterization in Natural Images

verfasst von: Gui-Song Xia, Julie Delon, Yann Gousseau

Erschienen in: International Journal of Computer Vision | Ausgabe 1/2014

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Accurate junction detection and characterization are of primary importance for several aspects of scene analysis, including depth recovery and motion analysis. In this work, we introduce a generic junction analysis scheme. The first asset of the proposed procedure is an automatic criterion for the detection of junctions, permitting to deal with textured parts in which no detection is expected. Second, the method yields a characterization of L-, Y- and X- junctions, including a precise computation of their type, localization and scale. Contrary to classical approaches, scale characterization does not rely on the linear scale-space. First, an a contrario approach is used to compute the meaningfulness of a junction. This approach relies on a statistical modeling of suitably normalized gray level gradients. Then, exclusion principles between junctions permit their precise characterization. We give implementation details for this procedure and evaluate its efficiency through various experiments.

Vorheriger Artikel A Comprehensive Survey to Face Hallucination

Nächster Artikel Detecting parametric objects in large scenes by Monte Carlo sampling

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Nur mit Berechtigung zugänglich

In this paper, we use the following discrete scheme to compute the gradient: for a pixel \(\mathbf{q }=(x,y), I_x(\mathbf{q }) = \frac{1}{2} (I(x+1,y) - I(x-1,y))\) and \(I_y(\mathbf{q }) = \frac{1}{2} (I(x,y+1) - I(x,y-1))\).

For a circle of radius \(r\) centered at pixel (0,0), \(\lfloor 2\pi r \rfloor \) is a good approximation of the number of pixels \((x,y)\) on the circle, in the sense that \(\hbox {round}(\sqrt{x^2+y^2}) = r\).

The code of LSD can be downloaded from the IPOL website: http://www.ipol.im/pub/algo/gjmr_line_segment_detector/.

This boils down to replace the distribution of the strength at a pixel with \(\mu = \dfrac{1}{2} \delta _0 + \frac{2}{\pi }\frac{1}{\sqrt{2 - z^2}} 1\!\!1_{z\ge 0}.\mathcal{L }\) in Eq. (11). The resulting junction detection algorithm is similar to Algorithm 7.

We use the codes kindly provided by the authors: http://vision.caltech.edu/~mmaire/software/gpb_src.tar.gz and http://www.ipb.uni-bonn.de/sfop/

This natural images database is available at http://perso.telecom-paristech.fr/~gousseau/db/imageDB.zip

The Berkeley dataset can be downloaded from www.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/.

\(F\) is defined as the highest value of the quantity \(2\frac{Precision \cdot Recall}{Precision+Recall}\) along the curve.

Adelson, E. H. (2000). Lightness perception and lightness illusions. In M. Gazzaniga (Ed.), The new cognitive neurosciences (2nd ed., pp. 339–351).

Alvarez, L., & Morales, F. (1997). Affine morphological multiscale analysis of corners and multiple junctions. International Journal of Computer Vision, 25(2), 95–107.CrossRef

Bergevin, R., & Bubel, A. (2004). Detection and characterization of junctions in a 2d image. Computer Vision and Image Understanding, 93(3), 288–309, ISSN 1077–3142.

Beymer, D. J. (1991). Finding junctions using the image gradient. In Proceedings of Computer Vision and Pattern Recognition (pp. 720–721).

Bolles, R. C., & Cain, R. A. (1982). Recognizing and locating partially visible objects: The local-feature-focus method. International Journal of Robotics Research, 1(3), 57–82.CrossRef

Cao, F. (2003). Good continuations in digital image level lines. In Proceedings of International Conference on Computer Vision (pp. 440–446).

Caselles, V., Coll, B., Morel, J.-M. (1996). Junction detection and filtering: A morphological approach. In Proceedings of International Conference on Image Processing (pp. 493–496).

Cazorla, M. A., & Escolano, F. (2003). Two Bayesian methods for junction classification. IEEE Transactions on Image Processing, 12(3), 317–327.CrossRefMathSciNet

Cazorla, M. A., Escolano, F., Gallardo, D., & Rizo, R. (2002). Junction detection and grouping with probabilistic edge models and Bayesian A*. Pattern Recognition, 35(9), 1869–1881.CrossRefMATH

Deriche, R., & Blaszka, T. (1993). Recovering and characterizing image features using an efficient model based approach. In Proceedings of Computer Vision and Pattern Recognition (pp. 530–535).

Deriche, R., & Giraudon, G. (1993). A computational approach for corner and vertex detection. International Journal of Computer Vision, 10(2), 101–124.CrossRef

Deschenes, F., & Djemel, Ziou. (2004). Detection of lines, line junctions and line terminations. International Journal of Remote Sensing, 25(3), 511–535.CrossRef

Desolneux, A., Moisan, L., & Morel, J.-M. (2000). Meaningful alignments. International Journal of Computer Vision, 40(1), 7–23.CrossRefMATH

Desolneux, A., Moisan, L., & Morel, J.-M. (2008). From Gestalt theory to image analysis: A probabilistic approach. Berlin: Springer.CrossRef

Dickscheid, T., Schindler, F., & Förstner, W. (2011). Coding images with local features. International Journal of Computer Vision, 94(2), 154–174.CrossRefMATH

Dimiccoli, M., & Salembier, P. (2009). Exploiting t-junctions for depth segregation in single images. In Proceedings of ICASSP (pp. 1229–1232).

Förstner, W. (1986). A feature based correspondence algorithm for image matching. In ISP Commission III.

Förstner, W. (1994). A framework for low level feature extraction. In Proceedings of European Conference on Computer Vision ECCV 1994 (Vol. II, pp. 383–394).

Förstner, W., Dickscheid, T., Schindler, F. (2009). Detecting interpretable and accurate scale-invariant keypoints. In ICCV (pp. 2256–2263).

Freeman, W. T. (1992). Steerable filters and local analysis of image structure. PhD thesis, MIT, Cambridge, MA, USA.

Fuchs, C., & Förstner, W. (1995). Polymorphic grouping for image segmentation. In Proceedings of International Conference on Computer Vision (pp. 175–182).

Geiger, D., Kumaran, K., & Parida, L. (1996). Visual organization for figure/ground separation. In Proceedings of Computer Vision and Pattern Recognition (pp. 155–161).

Golubchyck, R., & Lindenbaum, M. (2006). Improving the saliency algorithm by cue optimization. Technical Report MSC-2006-07, Technion.

Guo, C.-E., Zhu, S.-C., Wu, Y.-N. (2007). Primal sketch: Integrating structure and texture. Computer Vision and Image Understanding, 106(1):5–19. Special issue on Generative Model Based Vision.

Guzmán, A. (1968). Decomposition of a visual scene into three-dimensional bodies. In Proceedings of Fall Joint Computer Conference (part I, pp. 291–304).

Hannah, M. J. (1974). Computer matching of areas in stereo images. PhD thesis, Stanford University.

Harris, C., & Stephens, M. (1988). A combined corner and edge detection. In Proceedings of The Fourth Alvey Vision Conference (pp. 147–151).

Ishikawa, H., & Geiger D. (1998). Segmentation by grouping junctions. In Proceedings of Computer Vision and Pattern Recognition (pp. 125–132).

Kanizsa, G. (1979). Organization in vision: Essays on gestalt perception. New York: Praeger.

Kenney, C. S., Zuliani, M., Manjunath, B. S. (2005). An axiomatic approach to corner detection. In Proceedings of Computer Vision and Pattern Recognition (pp. 191–197).

Kitchen, L., & Rosenfeld, A. (1982). Non-maximum suppression of gradient magnitudes makes them easier to threshold. Pattern Recognition Letters, 1(2), 93–94.CrossRef

Kovesi, P. (2003). Phase congruency detects corners and edges. In Proceedings of DICTA (pp. 309–318).

Leichter, I., & Lindenbaum, M. (2009). Boundary ownership by lifting to 2.1d. In IEEE 12th International Conference on Computer Vision 2000 (pp. 9–16). 29 Nov to 2 Oct 2009. doi:10.1109/ICCV.2009.5459208.

Lin, L., Peng, S., Porway, J., Zhu, S.-C., & Wang, Y. (2007). An empirical study of object category recognition: sequential testing with generalized samples. In Proceedings of International Conference on Computer Vision.

Lindeberg, T. (1994). Junction detection with automatic selection of detection scales and localization scales. In Proceedings of International Conference on Image Processing (pp. 924–928).

Lindeberg, T. (1998). Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2), 79–116.CrossRef

Lindeberg, T., & Li, M.-X. (1997). Segmentation and classification of edges using minimum description length approximation and complementary junction cues. Computer Vision and Image Understanding, 67(1), 88–98.CrossRef

Liu, G., Xia, G.-S., Huang, X., Yang, W., Zhang, L. (2013). A perception-inspired building index for automatic built-up area detection in high-resolution satellite images. In Proceedings of International Geoscience and Remote Sensing Symposium (pp. 1–4).

Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91–110.CrossRef

Luo, B., Aujol, J.-F., Gousseau, Y., Ladjal, S., & Maître, H. (2007). Resolution-independent characteristic scale dedicated to satellite images. IEEE Transactions on Image Processing, 16(10), 2503–2514.CrossRefMathSciNet

Maire, M., Arbelaez, P., Fowlkes, C., Malik, J. (2008). Using contours to detect and localize junctions in natural images. In Proceedings of Computer Vision and Pattern Recognition (pp. 1–8).

Marr, D. (1982). Vision. A computational investigation into the human representation and processing of visual information. San Francisco: W.H. Freeman and Company.

McDermott, J. (2004). Psychophysics with junctions in real images. Perception, 33, 1101–1127.CrossRef

Metelli, F. (1974). The perception of transparency. Scientific American, 4(230), 90–98.CrossRef

Mikolajczyk, K., & Schmid, C. (2004). Scale and affine invariant interest point detectors. International Journal of Computer Vision, 60, 63–86.CrossRef

Mohammad, A., & Lu, G. (2008). An improved curvature scale-space corner detector and a robust corner matching approach for transformed image identification. IEEE Transactions on Image Processing, 17(12), 2425–2441.CrossRefMathSciNet

Moisan, L., & Stival, B. (2004). A probabilistic criterion to detect rigid point matches between two images and estimate the fundamental matrix. International Journal of Computer Vision, 57, 201–218.CrossRef

Mokhtarian, F., & Suomela, R. (1998). Robust image corner detection through curvature scale space. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 1376–1381.CrossRef

Moravec, H. P. (1977). Towards automatic visual obstacle avoidance. In Proceedings of IJCAI (pp. 584).

Musé, P., Sur, F., Cao, F., Gousseau, Y., & Morel, J.-M. (2006). An a contrario decision method for shape element recognition. International Journal of Computer Vision, 69(3), 295–315.CrossRef

Neubeck, A., & Van Gool, L. (2006). Efficient non-maximum suppression. In Proceedings of International Conference on Pattern Recognition (pp. 850–855).

Parida, L., Geiger, D., & Hummel, R. A. (1998). Junctions: Detection, classification, and reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(7), 687–698.CrossRef

Perona, P. (1992). Steerable-scalable kernels for edge detection and junction analysis. Image and Vision Computing, 10(10), 663–672.CrossRef

Rabin, J., Delon, J., & Gousseau, Y. (2009). A statistical approach to the matching of local features. SIAM Journal on Imaging Sciences, 2(3), 931–958.CrossRefMATHMathSciNet

Rattarangsi, A., & Chin, R. T. (1992). Scale-based detection of corners of planar curves. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14, 430–449.CrossRef

Ren, X., Fowlkes, C. C., Malik, J. (2006). Figure/ground assignment in natural images. In Proceedings of European Conference on Computer Vision (Vol. 2, pp. 614–627).

Rohr, K. (1992). Recognizing corners by fitting parametric models. International Journal of Computer Vision, 9(3), 213–230.CrossRef

Rosenfeld, A., & Johnston, E. (1973). Angle detection on digital curves. IEEE Transactions on Computers, 22(9), 875–878.

Rosenthaler, L., Heitger, F., Kübler, O., von der Heydt, R. (1992). Detection of general edges and keypoints. In Proceedings of the Second European Conference on Computer Vision, ECCV 1992 (pp. 78–86). ISBN 3-540-55426-2.

Rosten, E., Porter, R., & Drummond, T. (2010). Faster and better: A machine learning approach to corner detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(1), 105–119.CrossRef

Rubin, N. (2001). The role of junctions in surface completion and contour matching. Perception, 3(30), 339–366.CrossRef

Ruderman, D. L., & Bialek, W. (1994). Statistics of natural images: Scaling in the woods. Physical Review Letters, 73(6), 814–817.CrossRef

Ruzon, M. A., & Tomasi, C. (2001). Edge, junction, and corner detection using color distributions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(11), 1281–1295.CrossRef

Schmid, C., Mohr, R., & Bauckhage, C. (2000). Evaluation of interest point detectors. International Journal of Computer Vision, 37(2), 151–172.CrossRefMATH

Shi, J., & Tomasi, C. (1994). Good features to track. In Proceedings of Computer Vision and Pattern Recognition (pp. 593–600).

Sinzinger, E. D. (2008). A model-based approach to junction detection using radial energy. Pattern Recognition, 41(2), 494–505.CrossRefMATH

Smith, S. M., & Brady, J. M. (1995). SUSAN: A new approach to low level image processing. Proceedings of International Journal of Computer Vision, 23, 45–78.CrossRef

Teh, C. H., & Chin, R. T. (1989). On the detection of dominant points on digital curves. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(8), 859–872.CrossRef

Trajkovic, M., & Hedley, M. (1998). Fast corner detection. Image and Vision Computing, 16(2), 75–87.CrossRef

Grompone von Gioi, R., Jakubowicz, J., Morel, J.-M., & Randall, G. (2010). LSD: A fast line segment detector with a false detection control. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, 722–732.CrossRef

Wallach, H. (1935). Ueber visuell whargenommene bewegungrichtung. Psychologische Forschung, 20, 325–380.

Wang, H., & Brady, M. (1995). Real-time corner detection algorithm for motion estimation. Image and Vision Computing, 13(9), 695–703.CrossRef

Wu, T.F., Xia, G.-S., Zhu, S.-C. (2007). Compositional boosting for computing hierarchical image structures. In Proceedings of Computer Vision and Pattern Recognition (pp. 1–8).

Xia, G.-S., Delon, J., & Gousseau, Y. (2012). An accurate and contrast invariant junction detector. In Proceedings of International Conference on Pattern Recognition.

Titel: Accurate Junction Detection and Characterization in Natural Images
verfasst von: Gui-Song Xia
Julie Delon
Yann Gousseau
Publikationsdatum: 01.01.2014
Verlag: Springer US
Erschienen in: International Journal of Computer Vision / Ausgabe 1/2014
Print ISSN: 0920-5691
Elektronische ISSN: 1573-1405
DOI: https://doi.org/10.1007/s11263-013-0640-1

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Weitere Artikel der Ausgabe 1/2014

A Comprehensive Survey to Face Hallucination

Erratum to: Learning Vocabularies over a Fine Quantization

Detecting parametric objects in large scenes by Monte Carlo sampling

Spline-Based Hybrid Image Registration using Landmark and Intensity Information based on Matrix-Valued Non-radial Basis Functions

Appreciation to IJCV Reviewers

Sampling Minimal Subsets with Large Spans for Robust Estimation