Header menu link for other important links
Development of Semi-Automatic Methodology for Extraction of Depth for 2D-to-3D Conversion
Published in Association for Computing Machinery
Volume: Part F128357
Pages: 373 - 378
Recently, stereoscopic image/video conversion has been most demanding as it has a great stereo video experience. This paper presents the development of the methodology for generation of the depth map used for stereoscopic view. Normally, Stereoscopic conversion involves two steps: generation of depth map and generation of two left and right view using estimated depth. This paper focus for the generation of the depth map as a second step is well known. The estimation of the depth map is a difficult task. This paper uses a fusion of monocular cues as motion, Aerial Perspective cue(AP), Linear Perspective cue(LP), and Defocus cue to estimate the depth. The experimental results show that generation of the depth map is very close to the real depth map. Thus, the algorithm can apply for 2D-to-3D conversion in 3D displays. This algorithm tested in different conditions such as the sequence of camera motion and multiple objects, static cameras, and background as stationary, a highly dynamic foreground and with less motion as background, and motion is in behind the foreground. © 2017 ACM.
About the journal
JournalData powered by TypesetProceedings of the 9th International Conference on Machine Learning and Computing
PublisherData powered by TypesetAssociation for Computing Machinery
Open AccessNo