An adaptive wavelet shrinkage based accumulative frame differencing model for motion segmentation

Motion segmentation in real-world scenes is a fundamental component in computer vision.  There exists a variety of motion recognition algorithms, each with varying degrees of accuracy and computational complexity.  The most widely used techniques, in the case of static cameras, are those based on frame difference.  Those methods have a significant weakness when it comes to detect slow moving objects.  Therefore, we introduce in this paper a novel approach that aims to improve motion segmentation by proposing an accumulative wavelet based frame differencing technique.  Moreover, in the proposed approach we exploit a combination of several techniques to efficiently enhance the quality of motion segmentation results.  The approach's performance on real-world video sequences shows that comparing frames using the 2D wavelet transform increases motion segmentation quality.

  1. Cheng V., Kehtarnavaz N.   A smart camera application: DSP-based people detection and tracking.  Journal of Electronic Imaging.  9 (3), 336–346 (2000).
  2. Inaguma T., Saji H., Nakatani H.  Hand motion tracking based on a constraint of three-dimensional continuity.  Journal of Electronic Imaging.  14 (1), 013021 (2005).
  3. Makris D., Ellis T.  Path detection in video surveillance.  Image and Vision Computing.  20 (12), 895–903 (2002).
  4. Makris D., Ellis T.  Learning semantic scene models from observing activity in visual surveillance.  IEEE Transactions on Systems, Man, and Cybernetics. Part B (Cybernetics).  35 (3), 397–408 (2005).
  5. Paragios N., Chen Y., Faugeras O.  Handbook of Mathematical Models in Computer Vision. Springer New York, NY (2006).
  6. Baghaie A., D'Souza R., Yu Z.  Dense Descriptors for Optical Flow Estimation: A Comparative Study.  Journal of Imaging.  3 (1), 12 (2017).
  7. Kushwaha A., Khare A., Prakash O., Khare M.  Dense optical flow based background subtraction technique for object segmentation in moving camera environment.  IET Image Processing.  14 (14), 3393–3404 (2020).
  8. Cucchiara R., Grana C., Piccardi M., Prati A.  Detecting moving objects, ghosts and shadows in video streams.  IEEE Transactions on Pattern Analysis and Machine Intelligence.  25 (10), 1337–1342 (2003).
  9. Warnell G., Chellappa R.  Compressive Sensing in Visual Tracking. IntechOpen (2012).
  10. Song Y., Noh S., Yu J., Park C., Lee B.  Background subtraction based on Gaussian mixture models using color and depth information.  2014 International Conference On Control, Automation and Information Sciences (ICCAIS 2014). 132–135 (2015).
  11. Elgammal A., Duraiswami R., Harwood D., Davis L.  Background and foreground modeling using nonparametric kernel density estimation for visual surveillance.  Proceedings of the IEEE.  90 (7), 1151–1163 (2002).
  12. Hoogendoorn E., Crosby K. C., Leyton-Puig D., Breedijk R. M. P., Jalink K., Gadella T. W. J., Postma M.  The fidelity of stochastic single-molecule super-resolution reconstructions critically depends upon robust background estimation.  Scientific Reports.  4, 3854 (2014).
  13. Mohaoui S., Raghay S., Hakim A.  Bi-dictionary learning model for medical image reconstruction from undersampled data.  IET Image Processing.  14 (10), 2130–2139 (2020).
  14. Ophir B., Lustig M., Elad M.  Multi-Scale Dictionary Learning Using Wavelets.  IEEE Journal of Selected Topics in Signal Processing.  5 (5), 1014–1024 (2011).
  15. Kim K., Chalidabhongse T. H., Harwood D., Davis L.  Background modeling and subtraction by codebook construction.  2004 International Conference on Image Processing, 2004. ICIP'04.  5, 3061–3064 (2004).
  16. Stauffer C., Grimson W. E. L.  Adaptive background mixture models for real-time tracking.  Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).  2, 246–252 (2007).
  17. Elgammal A., Duriswami R., Harwood D., Davis L. S.  Background and foreground modelling using nonparametric kernel density estimation for visual surveil.  Proceedings of the IEEE.  90 (7), 1151–1163 (2002).
  18. Zhao C., Wang X., Cham W.-K.  Background Subtraction via Robust Dictionary Learning.  EURASIP Journal on Image and Video Processing.  2011, 972961 (2011).
  19. Azmat S., Wills L., Wills S.  Parallelizing Multimodal Background Modeling on a Low-Power Integrated GPU.  Journal of Signal Processing Systems.  88, 43–53 (2017).
  20. Grossmann A., Morlet J.  Decomposition of Hardy Functions into Square Integrable Wavelets of Constant Shape.  SIAM Journal on Mathematical Analysis.  15 (4), 723–736 (1984).
  21. Carmona R., Hwang W.-L., Torrésani B.  Practical Time-Frequency Analysis.  9, 441–464 (1998).
  22. Chui C.  Wavelet analysis and its application.  Wavelets.  2, 725 (1992).
  23. Mallat S.  A Wavelet Tour of Signal Processing. The Sparse Way. Academic Press, Inc. (2008).
  24. Carpine R., Ientile S., Vacca N., Boscato G., Rospars C., Cecchi A., Argoul P.  Modal identification in the case of complex modes – Use of the wavelet analysis applied to the after-shock responses of a masonry wall during shear compression tests.  Mechanical Systems and Signal Processing.  160, 107753 (2021).
  25. Davies D., Palmer P., Mirmehdi M.  Detection and Tracking of Very Small Low Contrast Objects.  In M. Nixon and J. Carter (editors),  Proceedings of the British Machine Conference, 60.1–60.10 (1998).
  26. Graps A.  An introduction to wavelets.  IEEE Computational Science and Engineering.  2 (2), 50–61 (1995).
  27. Khare M., Srivastava R., Khare A.  Moving object segmentation in Daubechies complex wavelet domain.  Signal, Image and Video Processing.  9, 635–650 (2015).
  28. Al-Berry M. N., Salem M. A.-M., Ebied H. M., Tolba M. F., Hussein A. S.  Wavelet-enhanced detection of small/slow object movement in complex scenes.  2016 11th International Conference on Computer Engineering & Systems (ICCES). 172–180 (2016).
  29. Jalal A. S., Singh V.  A framework for background modelling and shadow suppression for moving object detection in complex wavelet domain.  Multimedia Tools And Applications.  73, 779–801 (2014).
  30. Sunkara J.  Selection of Wavelet Basis Function for Image Compression – A Review.  Electronic Letters on Computer Vision and Image Analysis.  18 (1), 1–20 (2019).
  31. Mallat S. G.  A theory of multiresolution signal decomposition: the wavelet representation.  IEEE Transactions on Pattern Analysis and Machine Intelligence.  11 (7), 674–693 (1989).
  32. Akansu A., Haddad R.  Multiresolution Signal Decomposition. Transforms, Subbands, and Wavelets.  Academic Press (2001).
  33. Mallat S. A Wavelet Tour of Signal Processing. The Sparse Way. Academic Press (2009).
  34. Bobulski J.  Wavelet Transform in Face Recognition. Springer, Boston, MA (2006).
  35. Bnou K., Raghay S., Hakim A.  A wavelet denoising approach based on unsupervised learning model.  EURASIP Journal On Advances In Signal Processing.  2020, 36 (2020).
  36. Chi M., Han X., Xu Y., Wang Y., Shu F., Zhou W., Wu Y.  An Improved Background-Correction Algorithm for Raman Spectroscopy Based on the Wavelet Transform.  Applied Spectroscopy.  73 (1), 78–87 (2018).
  37. Donoho D. L., Johnstone I. M.  Adapting to Unknown Smoothness via Wavelet Shrinkage.  Journal of the American Statistical Association.  90 (432), 1200–1224 (1995).
  38. Sezgin M., Sankur B.  Survey over image thresholding techniques and quantitative performance evaluation.  Journal of Electronic Imaging.  13 (1), 146–168 (2004).
  39. Ferryman J., Shahrokni A.  PETS2009: Dataset and challenge.  2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance. 1–6 (2009).