access icon openaccess Straight line matching method based on line pairs and feature points

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 20/10/2014, Accepted 06/12/2015, Revised 18/11/2015, Published 08/03/2016

Straight line matching is a fundamental task in many applications such as scene matching, stereo vision and sequence images analysis. As individual line segments cannot completely present the information of image and methods based on them are difficult to achieve high matching accuracy, the authors propose a straight line matching algorithm based on line pairs and feature points. Extracted lines are clustered into line feature sets according to their spatial proximity and geometric structures. The structural relationship between line pairs, which are selected from the line feature sets, is described by feature vector consisting of length ratio, angle and average gradient. Coarse matching of line segments is achieved by using feature vector as similarity measurement. To eliminate the mismatches in the matched straight lines, the constraints of feature points are employed. The experimental results demonstrate that the authors’ algorithm can successfully match image lines with high accuracy under various image transformations, including scale, illumination changes and viewpoint variations.

Inspec keywords: transforms; stereo image processing; image matching; lighting; feature extraction; computational geometry

Other keywords: feature vector; average gradient; line feature sets; similarity measurement; stereo vision; line pairs; geometric structures; feature points; scene matching; straight line matching method; viewpoint variations; structural relationship; sequence images analysis; spatial proximity; length ratio; image transformations; illumination changes

Subjects: Integral transforms; Computer vision and image processing techniques; Computational geometry; Integral transforms; Image recognition

References

    1. 1)
      • 9. Wang, K., Shi, T., Liao, G., et al: ‘Image registration using a point-line duality based line matching method’, J. Vis. Commun. Image Represent., 2013, 24, (5), pp. 615–626.
    2. 2)
      • 7. Fu, D., Wang, C.: ‘A new algorism of matching line segments’, J. Natl. Univ. Def. Technol., 2008, 30, (1), pp. 115–119.
    3. 3)
      • 4. Wang, Z., Wu, F., Hu, Z.: ‘MSLD: a robust descriptor for line matching’, Pattern Recognit., 2009, 42, (5), pp. 941–953.
    4. 4)
      • 6. Schmid, C., Zisserman, A.: ‘The geometry and matching of lines and curves over multiple views’, Int. J. Comput. Vis., 2000, 40, (3), pp. 199–233.
    5. 5)
      • 12. Ok, A.O., Wegner, J.D., Heipke, C., et al: ‘Matching of straight line segments from aerial stereo images of urban areas’, ISPRS J. Photogramm. Remote Sens., 2012, 74, pp. 133–152.
    6. 6)
      • 15. Zhang, Y., Yang, H., Liu, X.: ‘A line matching method based on local and global appearance’. IEEE Proc. of 2011 4th Int. Conf. on Image and Signal Processing (CISP), Shanghai, October 2011, pp. 1381–1385.
    7. 7)
      • 17. Boldt, M., Weiss, R., Riseman, E.: ‘Token-based extraction of straight lines’, IEEE Trans. Syst. Man Cybern., 1989, 19, (7), pp. 1581–1594.
    8. 8)
      • 8. Mosaddegh, S., Fofi, D., Vasseur, P.: ‘Short baseline line matching for central imaging systems’, Pattern Recognit. Lett., 2012, 33, pp. 2292–2301.
    9. 9)
      • 18. Burns, J.B., Hanson, A.R., Riseman, E. M.: ‘Extracting straight lines’, IEEE Trans. Pattern Anal. Mach. Intell., 1986, 18, (4), pp. 425–455.
    10. 10)
      • 13. Elaksher, A.F.: ‘Automatic line matching across multiple views based on geometric and radiometric properties’, Appl. Geomatics, 2011, 3, (1), pp. 23–33.
    11. 11)
      • 16. Nevatia, R., Babu, K.: ‘Linear feature extraction and description’, Comput. Graph. Image Process., 1980, 13, (3), pp. 257–269.
    12. 12)
      • 14. Kim, H., Lee, S.: ‘A novel line matching method based on intersection context’. Proc. of 2010 IEEE Int. Conf. on Robotics and Automation (ICRA), Anchorage, AK, May 2010, pp. 1014–1021.
    13. 13)
      • 11. Lourakis, M.I.A., Halkidis, S.T., Orphanoudakis, S.C., et al: ‘Matching disparate views of planar surfaces using projective invariants’, Image Vis. Comput., 2000, 18, pp. 673–683.
    14. 14)
      • 3. Wang, Z., Wu, F.: ‘Mean-standard deviation descriptor and line matching’, Pattern Recognition and Artificial Intelligence, 2009, 22, (1), pp. 32–39.
    15. 15)
      • 2. Gan, J., Wang, X., Zhao, J., et al: ‘Fast matching algorithm for images matching based edge light characteristic’, Comput. Eng. Appl., 2010, 46, (11), pp. 193–195.
    16. 16)
      • 1. Li, T., Liu, X.: ‘A robust approach for extracting and matching straight line’, Comput. Simul., 2008, 25, (9), pp. 171–173.
    17. 17)
      • 21. Fan, B., Wu, F., Hu, Z.: ‘Line matching leveraged by point correspondences’. Proc. of IEEE Int. Conf. on Computer Vision and Pattern Recognition, San Francisco, CA, June 2010, pp. 390–397.
    18. 18)
      • 20. Lowe, D.G.: ‘Distinctive image features from scale-invariant key points’, Int. J. Comput. Vis., 2004, 60, (2), pp. 91–110.
    19. 19)
      • 19. Wang, L., Neumann, U., You, S.: ‘Wide-baseline image matching using line signatures’. Proc. of IEEE 12th Int. Conf. on Computer Vision, Kyoto, September 2009, pp. 1311–1318.
    20. 20)
      • 10. Wen, G.: ‘A global algorithm for straight line stereo matching based on feature grouping’, J. Softw., 2006, 17, (12), pp. 2471–2484.
    21. 21)
      • 5. Wang, J., Wen, G., Li, D.: ‘Complex correspondences in straight line stereo matching’, Geospatial Inf. Sci., 2010, 13, (2), pp. 103–110.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2014.0372
Loading

Related content

content/journals/10.1049/iet-cvi.2014.0372
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading