Stereo GrabCut: Interactive and Consistent Object Extraction for Stereo Images

This paper presents an interactive object extraction approach for stereo images. The extraction task on stereo images has two significant differences compared to that on monoscopic images. First, the segmentation for both images should be consistent. Second, stereo images have implicit depth information, which supplies an important cue for object extraction. In this paper, we generate consistent segmentation by putting the correspondence relationship in a graph cut framework. Besides, we leverage depth information, which is obtained by stereo matching, to give a pre-estimation of foreground and background. The pre-estimation is then used to generate accurate color models to perform a graph cut based segmentation. To simplify the user interaction, we supply an interface similar to GrabCut, which only needs the user to drag a compact rectangle in most cases. The experiments show our approach works fast and produces more satisfactory results than state-of-the-art.

[1]  Shi-Min Hu,et al.  Global contrast based salient region detection , 2011, CVPR 2011.

[2]  Radim Sára,et al.  A Weak Structure Model for Regular Pattern Recognition Applied to Facade Images , 2010, ACCV.

[3]  Andrew Blake,et al.  Bi-layer segmentation of binocular stereo video , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[5]  Xueqing Li,et al.  Leveraging stereopsis for saliency analysis , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Woontack Woo,et al.  Silhouette Segmentation in Multiple Views , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Andreas Geiger,et al.  Efficient Large-Scale Stereo Matching , 2010, ACCV.

[9]  Michael Harville,et al.  Foreground segmentation using adaptive mixture models in color and depth , 2001, Proceedings IEEE Workshop on Detection and Recognition of Events in Video.

[10]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[11]  Hanqing Lu,et al.  Saliency Cuts: An automatic approach to object segmentation , 2008, 2008 19th International Conference on Pattern Recognition.

[12]  A. Aydin Alatan,et al.  User assisted stereo image segmentation , 2012, 2012 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON).

[13]  Matthias Zwicker,et al.  Stereoscopic 3D copy & paste , 2010, ACM Trans. Graph..

[14]  William A. Barrett,et al.  Intelligent scissors for image composition , 1995, SIGGRAPH.

[15]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[16]  Harry Shum,et al.  Lazy snapping , 2004, ACM Trans. Graph..

[17]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[18]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[19]  Scott Cohen,et al.  StereoCut: Consistent interactive object selection in stereo image pairs , 2011, 2011 International Conference on Computer Vision.

[20]  VekslerOlga,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001 .

[21]  Hyeran Byun,et al.  Robust Object Segmentation Using Graph Cut with Object and Background Seed Estimation , 2006, 18th International Conference on Pattern Recognition (ICPR'06).