''6whuhrvfrslff,pdjhh3dluve\\'hswk0ds*hqhudwlrq Odfdvfld#xqlsdlww $evwudfww ,pdjhsuhsurfhvvlqj

Actually to generate a 3D view starting from a single view image different tools are required. These are not fully automatic application and require expensive computational resources. This paper presents a single framework aimed to obtain the stereoscopic view avoiding the user interaction and reducing the computation complexity. Moreover the depth map generation step is able to work directly onto a Bayer pattern image (CFA) further reducing band, memory and complexity requirements. Alternatively a sub sampled image can be used. This proposed technique is based on a novel algorithm [1] able to generate a depth map from a single image. The strength of method [3] is then used to reconstruct the left and right view. The two steps are pipelined so obtaining a single automatic 3D generation procedure. In order to obtain the depth map, an image preprocessing is required. It is composed of the following steps: 1) Image classification ; 2) Vanishing lines and vanishing point extraction. The stereoscopic pair image is then generated by calculating the parallax value ([8], [9], [10], [12]) of each object in the image extracting information only from the grey level depth map. The final left and right eye images give to the user a 3D perspective entertainment. The highlighted process is fully automatic and well suited for real-time application. Effectiveness of the proposed processing pipeline has been validated by an exhaustive set of experiments. This paper is organized as follows: Section 2 resumes the used image classification method describing also the techniques to extract the vanishing lines and the vanishing point. Section 3 explains how the depth map is generated. In section 4 an overview of the Stereoscopic pair image generation is given. Experimental results are reported in Section 5. Section 6 closes the paper tracking directions for future works.