1 / 24

Leveraging Stereopsis for Saliency Analysis

Leveraging Stereopsis for Saliency Analysis. Yuzhen Niu † Yujie Geng † Xueqing Li ‡ Feng Liu † † Department of Computer Science Portland State University Shandong University Portland, OR, 97207 USA ‡ School of Computer Science and Technology Jinan , Shandong, 250101 China. Outline.

havyn
Download Presentation

Leveraging Stereopsis for Saliency Analysis

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Leveraging Stereopsis for Saliency Analysis YuzhenNiu†YujieGeng†Xueqing Li‡Feng Liu† †Department of Computer Science Portland State University Shandong University Portland, OR, 97207 USA ‡School of Computer Science and Technology Jinan, Shandong, 250101 China

  2. Outline • Introduction • Stereo Saliency • Experiments • Conclusion

  3. Introduction • The performance of saliency analysis methods depends on feature contrast. • When an object does not exhibit distinct visual features, it becomes challenging for saliency detection. • Stereopsis provides an additional depth cue and plays an important role in the human vision system.

  4. Introduction

  5. Introduction • Two approach • Computes stereo saliency based on the global disparity contrast in the input image. • Leverages domain knowledge in stereoscopic photography.

  6. Stereo Saliency • Stereo saliency analysis works on disparity map. • We apply the SIFT flow method to disparity estimation for its robustness.

  7. Stereo Saliency • Stereo Saliency from Disparity Contrast • Extend a recent color contrast-based saliency detection method[3] for disparity contrast analysis. [3] M. Cheng, G. Zhang, N. J. Mitra, X. Huang, and S. Hu. Global contrast based salient region detection. In IEEE CVPR, pages 409–416, 2011.

  8. Stereo Saliency • Stereo Saliency from Disparity Contrast w(p, q): the spatial distance between p and q dv(p, q): the disparity difference between pixel p and q

  9. Stereo Saliency

  10. Stereo Saliency • Domain Knowledge Assisted Saliency Analysis • Unique features of stereoscopic photography give useful cues for saliency analysis. • Two rules to compute the stereo saliency. • Objects with small disparity magnitudes (e.g. in the comfort zone) tend to be salient. • Objects popping out from the screen tend to be salient.

  11. Stereo Saliency

  12. Stereo Saliency • Follow Rule 1 • Assign big saliency values to regions with small disparity magnitudes.

  13. Stereo Saliency • Follow Rule 2 • Objects with negative disparities are perceived popping out from the screen.

  14. Stereo Saliency • Combine Rule 1 and 2 • When an image only has negative disparities. • Rule 2 > Rule 1 • When an image has both negative and positive disparities. • Rule 1 > Rule 2

  15. Stereo Saliency • Combine Rule 1 and 2

  16. Stereo Saliency • Modulate the original saliency map with local contrast-based saliency analysis • Disparities change little in each row in some of the background areas.

  17. Stereo Saliency

  18. Stereo Saliency • Stereo Saliency Map

  19. Experiments • Stereoscopic Image Database • Three users are asked to enclose the most salient object in each image with a rectangle. • Ask a user to manually segment the salient object(s) in each of the images.

  20. Experiments • Performance Evaluation

  21. Experiments

  22. Experiments • Automatic Salient Object Segmentation

  23. Experiments • Limitations • The performance of our methods depend on the quality of disparity maps. • Stereoscopic photography rules may conflict with each other for some images. • Stereo saliency is useful only if a salient object stays at a different depth than its surroundings.

  24. Conclusion • Developed two methods for stereo saliency detection. • Stereo saliency is a useful complement to existing visual saliency analysis.

More Related