Object Extraction with Excessive Disparities in 3D Stereoscopic Images

Abstract

Abstract-In this paper, we propose the method to extract objects with excessive disparities in 3D stereoscopic images using cost function considering the intensity and the depth information. The traditional region segmentation method such as CLRG (Centroid Linkage Region Growing) used in the general 2D images is processed only based on intensity information. 3D stereoscopic images have the additional information that is depth. In the proposed method, first the excessive disparity candidate regions are decided using the pre-defined threshold in the disparity-map. Next the extracted excessive disparity candidate regions are labeled to object regions and the other regions are labeled to background regions. The regions labeled as object are set as region that will be segmented in 3D stereoscopic left image. The proposed segmentation method considering the intensity and the depth is applied to these regions in 3D stereoscopic left image. Finally to eliminate small regions, the morphological filter is used.

Extraction of Region with Excessive Disparities Using Block Based Disparity Calculation

“…In Kim's method [13], the method to extract objects with excessive disparities in 3D stereoscopic images using cost function considering the pixel intensities and the depth information, disparities. This method can extract the exact object with excessive disparities in pre-defined ROI (region Sang Hyun Kim, Jeong Yeop Kim, and Gil Ja So Extraction of Region with Excessive Disparities Using Block Based Disparity Calculation of interest).…”