Estimating Scene-Oriented Pseudo Depth With Pictorial Depth Cues

Lee, Jae-Ho; Yoo, Seungwoo; Kim, Changick; Bhaskaran, Vasudev

doi:10.1109/tbc.2013.2240131

Cited by 6 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the first step, the proposed method determines if the given image is an OV scene or an NOV scene depending on existence of dominant foreground objects. For this process, it uses the characteristics of analysis result of the block-wised window discrete Fourier transform (BWDFT) [7]. The operations of the proposed method are described below in more detail.…”

Section: Proposed Depth Map Generation Methodsmentioning

confidence: 99%

“…The scene type of the given image is determined by investigating the characteristics of the amplitude spectral signature [7]. In case of the OV scene, owing to the foreground object, its spectrum is not biased because the spectrum is not dominant in vertical and horizontal direction.…”

Section: A Scene Classificationmentioning

confidence: 99%

“…In contrast, the spectrum of NOV is biased toward the vertical and horizontal directions (e.g., buildings with high frequency textures). Motivated by this characteristics of the spectral signature, we use the result of the block-wise windowed discrete Fourier transform (DFT) [7] as a scene feature. As a classifier, we employ the Support Vector Machine (SVM) which is a supervised learning model.…”

Section: A Scene Classificationmentioning

confidence: 99%

“…In the case of a scenery image, it is difficult to obtain a good segmentation result, and, thus, a segmentation-based depth estimation method generally provides inaccurate depth map. To cope with this problem, [7] proposed to use scene classification which classifies a given image into the objectview (OV) scene and the non-object-view (NOV) scene. Then, it selectively applied segmentation techniques depending on the scene type.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Foreground-based depth map generation for 2D-to-3D conversion

Lee

Cho

Bae

et al. 2015

2015 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

This paper proposes a foreground-based approach to generating a depth map which will be used for 2D-to-3D conversion. For a given input image, the proposed approach determines if the image is an object-view (OV) scene or a nonobject-view (NOV) scene, depending on the existence of foreground objects which are clearly distinguishable from the background. If the input image is an OV scene, the proposed approach extracts a foreground using block-wise background modeling and performs segmentation using adaptive background region selection and color modeling. Then, it performs segmentwise depth merging and cross bilateral filtering (CBF) to generate a final depth map. On the other hand, for the NOV scene, the proposed approach uses a conventional color-based depth map generation method [9] which has simple operations but provides a 3D depth map of good quality. Human beings are usually more sensitive to depth map quality, and 3D images, for OV scenes than for NOV scenes. With the proposed approach, it is possible to improve the quality of a depth map for OV scenes than using the conventional methods only. The performance of the proposed approach was evaluated through the subjective evaluation after 2D-to-3D conversion using a 3D display, and the proposed one provided the best depth quality and visual comfort among the benchmark methods.

show abstract

Section: Proposed Depth Map Generation Methodsmentioning

confidence: 99%

Section: A Scene Classificationmentioning

confidence: 99%

Section: A Scene Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations