access icon free Moving shadow detection based on stationary wavelet transform and Zernike moments

© The Institution of Engineering and Technology
Received 18/05/2017, Accepted 24/03/2018, Revised 05/03/2018, Published 26/03/2018

The presence of shadows degrades the performance of many computer vision and video surveillance applications, as objects can be incorrectly classified. The article proposes a method for detecting moving shadows using stationary wavelet transform (SWT) and Zernike moments (ZM) based on an automatic threshold determined by the wavelet coefficients. The multi-resolution and shift invariance properties of the SWT make it suitable for change detection and feature extraction. To reduce the redundant wavelet coefficients, ZM are applied. The novelty of the proposed method is the determination of the variant statistical threshold – ‘skewness’, without the requirement of any supervised learning or manual calibration. The experimental results prove that the proposed threshold performs well to show a better variation between the objects and shadows in various environments.

Inspec keywords: image resolution; wavelet transforms; feature extraction; learning (artificial intelligence); statistical analysis; object detection

Other keywords: supervised learning; redundant wavelet coefficient; SWT; moving shadow detection; calibration; shift invariance property; Zernike moment; change detection; statistical threshold; computer vision; ZM; feature extraction; stationary wavelet transform; video surveillance application

Subjects: Integral transforms; Knowledge engineering techniques; Integral transforms; Image recognition; Computer vision and image processing techniques; Other topics in statistics; Other topics in statistics

References

    1. 1)
      • 16. Tsai, V.J.D.: ‘A comparative study on shadow compensation of color aerial images in invariant color models’, IEEE Trans. Geosci. Remote Sens., 2006, 44, pp. 1661–1671.
    2. 2)
      • 29. Zhenjiang, M.: ‘Zernike moment based image shape analysis and its application’, Pattern Recognit. Lett., 2000, 21, (2), pp. 169–177.
    3. 3)
      • 22. Teague, M: ‘Image analysis via the general theory of moments’, J. Opt. Soc. Am., 1980, 70, (8), pp. 920–930.
    4. 4)
      • 15. Sun, B., Li, S.: ‘Moving cast shadow detection of vehicle using combined color models’. IEEE Proc. of the Chinese Conf. on Pattern Recognition, Chongqing, China, 21–23 October 2010, pp. 1–5.
    5. 5)
      • 24. Celebi, E. M., Aslandogan, Y. A: ‘A comparative study of three moment based shape descriptors’. Proceeding of Int. Conf. on Information Technology: Coding and Computing (ITCC), Las Vegas, NV, USA, 2005, vol. I, pp. 788–793.
    6. 6)
      • 10. Zhang, L., He, X.: ‘Fake shadow detection based on SIFT features matching’. Proc. of the WASE Int. Conf. on Information Engineering, Beidaihe, China, August 2010, pp. 216–220.
    7. 7)
      • 26. Bin, Y., Xiong, P.J: ‘Invariance analysis of improved Zernike moments’, J. Opt. A, Pure Appl. Opt., 2002, 4, (6), pp. 606–614.
    8. 8)
      • 18. Finlayson, G.D., Fredembach, C., Drew, M.S.: ‘Detecting illumination in images’. IEEE 11th Int. Conf. on Computer Vision (ICCV), Rio de Janeiro, Brazil, 2007, pp. 1–8.
    9. 9)
      • 12. Zhu, J., Samuel, K.G.G., Masood, S.Z., et al: ‘Learning to recognize shadows in monochromatic natural images’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, San Francisco, CA, USA, June 2010, pp. 223–230.
    10. 10)
      • 20. Khare, M., Srivastava, R.K., Khare, A.: ‘Moving shadow detection and removal – a wavelet transform based approach’, IET Comput. Vis., 2014, 8, (6), pp. 701–717.
    11. 11)
      • 31. Golchin, M., Khalid, F., Abdullah, L.N., et al: ‘Shadow detection using color and edge information’, J. Comput. Sci., 2013, 9, (11), pp. 1575–1588.
    12. 12)
      • 9. Sanin, A., Sanderson, C., Lovell, B.C.: ‘Improved shadow removal for robust person tracking in surveillance scenario’. Proc. Int. Conf. on Pattern Recognition (ICPR), Istanbul, Turkey, 2010, pp. 141–144.
    13. 13)
      • 25. Chong, C.W., Raveendran, P., Mukundan, R: ‘Translation invariance of Zernike moments’, Pattern Recognit., 2003, 36, (8), pp. 1765–1773.
    14. 14)
      • 6. Cavallaro, A., Salvador, E., Ebrahimi, T.: ‘Shadow aware object-based video processing’, Proc. IET Int. Conf. Vis., Image Signal Process., 2005, 152, (4), pp. 398–406.
    15. 15)
      • 23. Hwang, S.K., Kim, W.Y: ‘A novel approach to the fast computation of Zernike moments’, Pattern Recognit., 2006, 39, (11), pp. 2065–2076.
    16. 16)
      • 2. Prati, A., Cucchiara, R., Mikic, I., et al: ‘Analysis and detection of shadows in video streams: a comparative evaluation’. Proc. IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR), Kauai, HI, USA, 2001, vol. 2, pp. 571–576.
    17. 17)
      • 19. Shi, W., Li, J.: ‘Shadow detection in color aerial images based on HSI space andcolor attenuation relationship’, EURASIP J. Adv. Signal Process., 2012, 141, pp. 1–13.
    18. 18)
      • 13. Panicker, J.V., Wilscy, M.: ‘Detection of moving cast shadows using edge information’. Proc. of the 2nd Int. Conf. on Computer and Automation Engineering, Singapore, February 2010, pp. 817–821.
    19. 19)
      • 14. Cogun, F., Cetin, A.E.: ‘Moving shadow detection in video using cepstrum’, Int. J. Adv. Robot. Syst., 2013, 10, 18, pp. 1–5.
    20. 20)
      • 4. Chen, C.T., Su, C.Y., Kao, W.C.: ‘An enhanced segmentation on vision-based shadow removal for vehicle detection’. Proc. Int. Conf. on Green Circuit and Systems, Shanghai, China, 2010, pp. 679–682.
    21. 21)
      • 30. Sharan, L., Adelson, E.H., Motoyoshi, I., et al: ‘Non-oriented filters are better than oriented filters for skewness detection’, Perception, 2007, 36, (6a), pp. 206–209.
    22. 22)
      • 3. Guan, Y.P.: ‘Spatio-temporal motion-based foreground segmentation and shadow suppression’, IET Comput. Vis., 2010, 4, (1), pp. 50–60.
    23. 23)
      • 11. Kumar, S., Kaur, A.: ‘Algorithm for shadow detection in real-colour images’, Int. J. Comput. Sci Eng., 2010, 2, pp. 2444–2446.
    24. 24)
      • 27. Papakostas, G.A., Boutalis, Y.S., Karras, D.A., et al: ‘A new class of Zernike moments for computer vision applications’, Inf. Sci., 2007, 177, (13), pp. 2802–2819.
    25. 25)
      • 28. Farzem, M., Shirani, S.: ‘A robust multimedia watermarking technique using Zernike transform’. Proc. of Fourth IEEE Workshop on Multimedia Signal Processing, Vancouver, Canada, 2001, pp. 529–534.
    26. 26)
      • 8. Cucchiara, R., Grana, C., Piccardi, M., et al: ‘Detecting moving objects, ghosts and shadows in video streams’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, (10), pp. 1337–1342.
    27. 27)
      • 21. Zhang, Y., Wang, S., Huo, Y., et al: ‘Feature extraction of brain MRI by stationary wavelet transform and its application’, J. Biol. Syst., 2010, 18, (spec 01), pp. 115–132.
    28. 28)
      • 5. Najdawi, N.A., Bez, H.E., Singhai, J., et al: ‘A survey of cast shadow detection algorithms’, Pattern Recognit. Lett., 2012, 33, pp. 752–764.
    29. 29)
      • 7. Salvador, E., Cavallaro, A., Ebrahimi, T.: ‘Cast shadow segmentation using invariant color features. Comput. Vis. Image Underst., 2004, 95, (2), pp. 238–259.
    30. 30)
      • 1. Sanin, A., Sanderson, C., Lovell, B.C.: ‘Shadow detection: a survey and comparative evaluation of recent methods’, Pattern Recognit., 2012, 45, (4), pp. 1684–1695.
    31. 31)
      • 17. Chung, K.-L., Lin, Y.-R., Huang, Y.-H.: ‘Efficient shadow detection of color aerial images based on successive thresholding scheme’, IEEE Trans. Geosci. Remote Sens., 2009, 47, pp. 671–682.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2017.0273
Loading

Related content

content/journals/10.1049/iet-cvi.2017.0273
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading