Use of salient region detecting methods after telemetric image segmentation for object group identification

Cover Page

Cite item

Full Text

Abstract

In this paper we describe how to accelerate object group identification and tracking in real time. It is in need to remove non informational part of image backward and to detect highly salient objects. The salient objects are detected by mean-shift segmentation in image pixel feature high dimensional space and by determining the segmented image salience map. The frequency-tuned salient region detection method is in use, which produces segmented image full resolution saliency map displaying salient object boundaries. The method preserves the object boundaries by retaining main frequency content from the segmented image and exploits features of color and luminance. Since salient object detection is not a pure low-level process, next a unified model is in use to incorporate the image low-level features with higher-level knowledge. In the model, a special image matrix in the feature space is decomposed as a low-rank matrix representing background plus sparse matrix indicating the salient regions. To ensure the model validity, a linear transform of the image feature space has to be learned. Next, the higher-level knowledge is fused to compose a prior map, and is treated as a prior term in the objective function. The approach efficiency is demonstrated on sample image with salient objects.

About the authors

B. G. Kukharenko

Blagonravov Mechanical Engineering Research Institute of the RAS

Author for correspondence.
Email: kukharenkobg@gmail.com

Leading Research Scientist

Russian Federation, Moscow

M. O. Solntseva-Chalei

Moscow Institute of Physics and Technology (SU)

Email: solnceva.chalei@gmail.com

Post-Graduate Student

Russian Federation, Moscow

References

  1. Kukharenko B. G., Solntseva-Chalei M. O. Ispolzovanie metodov sokraschenia fona pri segmentirovanii telemetricheskih izobragenyi dlya identifikacii grupp objectov, Informacionnye tehnologii, 2014, no. 2, pp. 3—8.
  2. Borji A., Sihite D. N., Itti L. Salient object detection: A benchmark, Computer Vision — ECCV 2012. Lecture Notes in Computer Science, vol. 7573, Berlin, Heidelberg: Springer, 2012. P. 414—429.
  3. Ren T., Liu Y., Ju R., Wu G. How important is location information in saliency detection of natural images, Multimedia Tools and Applications, 2015, vol. 74, issu 20, pp. 1—22.
  4. Lang C., Liu G., Yu J., Yan S. Saliency detection by multitask sparsity pursuit, IEEE Transactions on Image Processing, 2012, vol. 21, no. 3, pp. 1327—1338.
  5. Goferman S., Zelnik-Manor L., Tal A. Context-aware saliency detection, IEEE Transactions on Pattern Analysis and Machine Intelligence , 2012, vol. 34, no. 10, pp. 1915—1926.
  6. Cheng M. M., Mitra N. J., Huang X., Hu S. M. Salientshape: Group saliency in image collections, The Visual Computer, Springer, 2014, vol. 30, issue 4, pp. 443—453.
  7. Ren T., Qui Z., Yu T., Liu Y., Bei J. Soft-assigned bag of features for object tracking, Multimedia Systems, 2014, vol. 21, no. 2, pp. 189—205.
  8. Cheng M. M., Mitra N. J., Huang X., Hu S. M. RepFinder: Finding approximately repeated scene elements for image editing, ACM Transactions on Graphics (TOG), Proceedings of ACMSIGGRAPH — 2010, 2010, vol. 29, no. 4, article No. 83.
  9. Gao Y., Wang M., Zha Z. G., Shen J., Li X., Wu X. Visual-textual joint relevance learning for tag-based social image search, IEEE Transactions on Image Processing, 2013, vol. 22, no. 1, pp. 363—376.
  10. Borji A., Itti L. State-of-the-art in visual attention modeling, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, vol. 35, no. 1, pp. 185—207.
  11. Cheng M., Mitra N. J., Huang X., Torr P. H.S., Hu S. Global contrast based salient region detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, vol. 37, issue 3, pp. 569—582.
  12. Qiu Y., Sun X., She M. F. Saliency detection using hierarchical manifold learning, Neurocomputing, 2015, vol. 168, pp. 538—549.
  13. Jiang P., Vasconcelos N., Peng J. Generic promotion of diffusion-based salient object detection, Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 217—225.
  14. Yang J., Yang M. H. Top-down visual saliency via joint CRF and dictionary learning, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’2012), IEEE, 2012, pp. 2296—2303.
  15. Liu T., Yuan Z., Sun J., Wang J., Zheng N., Tang X., Shum H. Y. Learning to detect a salient object, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, vol. 33, issue 2, pp. 353—367.
  16. Borji A., Itti L. State-of-the-art in visual attention modeling, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, vol. 35, issue 1, pp. 185—207.
  17. Shen X., Wu Y. A unified approach to salient object detection via low rank matrix recovery, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’2012), IEEE, 2012, pp. 853—860.
  18. Yang C., Zhang L., Lu H., Ruan X., Yang M. H. Saliency detection via graph-based manifold ranking, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’2013), IEEE, 2013, pp. 3166—3173.
  19. Chang K. Y., Liu T. L., Chen H. T., Lai S. H. Fusing generic objectness and visual saliency for salient object detection, Proceedings of the IEEE International Conference on Computer Vision (ICCV’2011), IEEE, 2011, pp. 914—921.
  20. Feng J., Wie Y., Tao L., Zhang C., Sun J. Salient object detection by composition, Proceedings of the IEEE International Conference on Computer Vision (ICCV’2011), IEEE, 2011, pp. 1028—1035.
  21. Lu Y., Zhang W., Lu H., Xue X. Salient object detection using concavity context, Proceedings of the IEEE International Conference on Computer Vision (ICCV’2011), IEEE, 2011, pp. 233—240.
  22. Achanta R., Estrada F., Wils P., Susstrunk S. Frequency-tuned salient region detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’2009), IEEE, 2009, pp. 1597—1604.
  23. Hou X., Zhang L. Saliency detection: A spectral residual approach, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'07), IEEE, 2007, pp. 1—8.
  24. Itti L., Koch C. A saliency-based search mechanism for overt and covert shifts of visual attention, Vision Research, 2000, vol. 40, no. 10, pp. 1489—1506.
  25. Achanta R., Estrada F., Wils P., Susstrunk S. Salient region detection and segmentation, Proceedings of the International Conference on Computer Vision Systems (ICVS '08). Springer Lecture Notes in Computer Science, V. 5008. Berlin, Heidelberg: Springer. 2008. P. 66—75.
  26. Marr D. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information, San Francisco, CA: W. H. Freeman and Company, 1982.
  27. Lowe D. G. Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 2004, vol. 60, no. 2, pp. 91—110.
  28. Harel J., Koch C., Perona P. Graph-based visual saliency / Scholkopf B., Platt J. C., Hoffman T., Advances in Neural Information Processing Systems, vol. 19, Cambridge, MA: The MIT Press, 2006, pp. 545—552.
  29. Itti L., Koch C., Niebur E. A model of saliency-based visual attention for rapid scene analysis, IEEE Transactions on Pattern Analysis & Machine Intelligence, 1998, issue 11, pp. 1254—1259.
  30. Comaniciu D., Meer P. Mean shift: A robust approach toward feature space analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, vol. 24, issue 5, pp. 603—619.
  31. Wright J., Ganesh A., Rao S., Peng Y., Ma Y. Robust principal component analysis: Exact recovery of corrupted low-rank matrices via convex optimization, Bengio Y., Schuurmans D., Lafferty J. D., eds., Advances in Neural Information Processing Systems, vol. 22, Cambridge, MA: The MIT Press, 2009, pp. 2080—2088.
  32. Chambers G. Oxford's WWII Harvard Airplanes, URL: http://www.whattravelwriterssay.com/oxfordcounty4feb09gene.html

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) 2016 Informacionnye Tehnologii


СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: серия ПИ № 77 - 15565 от 02 июня 2003 г.