A method for dynamic segmentation of a pair of sequental video-frames
Vaganov S.E.

 

Ivanovo State University, Ivanovo, Russia

 PDF

Abstract:
An algorithm of dynamic segmentation of sequential frame pairs was proposed. A comparative analysis of segmentation quality when finding shifts and affine inter-frame transformations for the segments was conducted. In addition, we compared the performance of the proposed method with some static segmentation approaches.

Keywords:
segmentation, image, video, affine transformation, optical flow.

Citation:
Vaganov SE. A method for dynamic segmentation of a pair of sequential video-frames. Computer Optics 2019; 43(1): 83-89. DOI: 10.18287/2412-6179-2019-43-1-83-89.

References:

  1. Ghazvinian Zanjani F, van Gerven M. Improving semantic video segmentation by dynamic scene integration. The Netherlands Conference on Computer Vision 2016.
  2. Tsai Y-H, Yang M-H, Black MJ. Video segmentation via object flow. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016: 3899-3908. DOI: 10.1109/CVPR.2016.423.
  3. Kumar MP, Torr PHS, Zisserman A. Learning layered motion segmentations of video. International Journal of Computer Vision 2008; 76(3): 301-319. DOI: 10.1007/s11263-007-0064-x.
  4. Sevilla-Lara L, Sun D, Jampani V, Black MJ. Optical flow with semantic segmentation and localized layers. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016: 3889-3898. DOI: 10.1109/CVPR.2016.422.
  5. Zappella L, Llado X, Salvi J. New trends in motion segmentation. In Book: Yin P-Y, ed. Pattern Recognition. Ch 3. Rijeka, Croatia: IntechOpen; 2009: 31-46. DOI: 10.5772/7551.
  6. Optical flow evaluation results. Source: <http://vision.middlebury.edu/flow/eval/results/results-i1.php>.
  7. Lucas BD, Kanade T. An iterative image registration technique with an application to stereo vision. Proceedings of the 1981 DARPA Image Understanding Workshop 1981: 121-130.
  8. Baker S, Matthews I. Lucas-Kanade 20 years on: A unifying framework. International Journal of Computer Vision 2004; 56(3): 221-255. DOI: 10.1023/B:VISI.0000011205.11775.fd.
  9. Hashin SI. The estimation of quality of segmentation of the map [In Russian]. Ivanovo Sate University bulletin, Series “Natural, Social Sciences” 2010: 2; 112-117.
  10. Szeliski R. Computer vision: Algorithms and applications. London: Springer; 2011. ISBN: 978-1-84882-934-3.
  11. Vaganov SE, Hashin SI. A comparison of the effectiveness of different versions of Lucas–Kanade method [In Russian]. Ivanovo Sate University Bulletin, Series “Natural, Social Sciences” 2017: 2: 63-70.
  12. Farnebäck G. Two-frame motion estimation based on polynomial expansion. In Book: Bigun J, Gustavsson T, eds. Image analysis. SCIA: Scandinavian conference on image analysis. Berlin, Heidelberg: Springer; 2003: 363-370. DOI: 10.1007/3-540-45103-X_50.
  13. Khashin SI. Affine version of Lucas–Kanade algorithm [In Russian]. Proceedings of Mathematical Method of Pattern Recognition 2011: 459-462.
  14. Test bmp-file pairs [In Russian]. Source: <http://math.ivanovo.ac.ru/dalgebra/Khashin/bmp_ex2/>.
  15. Kruchinin AE, Hashin SI. The image segmentation by building continuous borders [In Russian]. Ivanovo Sate University Bulletin 2007; 3: 80-83.
  16. Khashin SI. Dynamic segmentation of frames sequences [In Russian]. Machine Learning and Data Analysis 2013; 6(1): 787-795.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846)332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20