2D to 3D Conversion using Key Frame Extraction

Abstract

Background/Objectives: Extracting 3D information from two dimensional images is tedious process and challenging task. In this paper, a novel 2D to 3D conversion model is presented to convert monoscopic 2D images into 3D stereoscopic images. Method/Satistical Analysis: The depth information about key frames is extracted from the 2D images. Then both foreground and background objects are extracted using background subtraction algorithm. From the generated region of interest both forward and backward motion pixels are extracted in the form of vectors. Gabor filter is applied to decompose high pass luminance and chrominance. Each pixels decomposed with gabor filter is estimated with its own sub band to model the depth information. Findings: Depth map associated with each sub band and its oriented pixels are mapped with the depth information of 2D images and this makes a realistic view of 2D images in 3D stereoscopic view. Application/ Improvements: The proposed model is experimentally tested on both right and left view and the results shows that the presented model is better than the traditional model.