Fast Dense Stereo Matching Using Adaptive Window in Hierarchical Framework

Yoon, Sangun; Min, Dongbo; Sohn, Kwanghoon

doi:10.1007/11919629_33

Cited by 6 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The actual images usually include noise in occluded and textureless regions in the initial disparity estimation result [7]. Especially, the main reason for image degradation is the influence of salt-pepper noise, that is, positive and negative pulse noise.…”

Section: Disparity Estimation To Create Adaptive Disparitymapmentioning

confidence: 99%

A Real-Time Virtual Re-Convergence Hardware Platform

Kim

Ham³

et al. 2012

JSTS:Journal of Semiconductor Technology and Science

View full text Add to dashboard Cite

Abstract-In this paper, we propose a real-time virtual re-convergence hardware platform especially to reduce the visual fatigue caused by stereoscopy. Our unique idea to reduce visual fatigue is to utilize the virtual re-convergence based on the optimized disparity-map that contains more depth information in the negative disparity area than in the positive area. Our virtual re-convergence hardware platform, which consists of image rectification, disparity estimation, depth post-processing, and virtual view control, is realized in real time with 60 fps on a single Xilinx Virtex-5 FPGA chip.

show abstract

Section: Disparity Estimation To Create Adaptive Disparitymapmentioning

confidence: 99%

A Real-Time Virtual Re-Convergence Hardware Platform

Kim

Ham³

et al. 2012

JSTS:Journal of Semiconductor Technology and Science

View full text Add to dashboard Cite

show abstract

“…The actual images usually include noise in occluded and textureless regions in the initial disparity estimation result [9]. Thus, we also devise a filter that computes to smooth the disparity value with the neighborhood disparities.…”

Section: Disparity Estimation To Create Optimized Disparitymapmentioning

confidence: 99%

Optimizing a Virtual Re-Convergence System to Reduce Visual Fatigue in Stereoscopic Camera

Kim

Cho

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, we propose an optimized virtual reconvergence system especially to reduce the visual fatigue caused by binocular stereoscopy. Our unique idea to reduce visual fatigue is to utilize the virtual re-convergence based on the optimized disparity-map that contains more depth information in the negative disparity area than in the positive area. Therefore, our system facilitates a unique search-range scheme, especially for negative disparity exploration. In addition, we used a dedicated method, using a so-called Global-Shift Value (GSV), which are the total shift values of each image in stereoscopy to converge a main object that can mostly affect visual fatigue. The experimental result, which is a subjective assessment by participants, shows that the proposed method makes stereoscopy significantly comfortable and attractive to view than existing methods.

show abstract

“…According to the scene representation, various stereo matching approaches can be classified as pixel-based and region-based. The pixel-based representation is the most universal one and can be applied to any scene, while the region-based stereo algorithms [38]- [47] have inherent ability of occlusion handling around region boundaries and the better performance in ambiguity discrimination. The second criterion is from the view of the optimization techniques used in disparity estimation.…”

Section: Depth Reconstructionmentioning

confidence: 99%

“…For computational efficiency, Gong [46] proposes an adaptive cost aggregation scheme using edge detection instead of color segmentation for real-time implementation with graphic hardware. Yoon et al [47] use boundary information to compute accurate windows for each pixel, and solve the iterative problem in a hierarchical framework, known as the scale-variant iterative scheme.…”

Section: Region-based Stereomentioning

confidence: 99%

Multi-view Video Based Object Segmentation - A Tutorial

Cui

Zhang²,

Ngan³

et al. 2008

ECTI-EEC

View full text Add to dashboard Cite

Video based object segmentation (VBOS) is an important step in many computer vision and multimedia tasks such as video editing and compositing. In recent years, multi-view VBOS systems have become more and more popular because the stereo clues from multiview data can be efficiently incorporated to improve the segmentation results and eliminate the required initial user input. In this paper, we give a review on recent development of multi-view VBOS systems and the related techniques including data acquisition, camera calibration, depth reconstruction, object segmentation and tracking. Furthermore, we introduce our multiple objects segmentation system from multiview video sequence to illustrate the practical implementation of multi-view VBOS system for 3D video rendering applications.

show abstract

Fast Dense Stereo Matching Using Adaptive Window in Hierarchical Framework

Cited by 6 publications

References 11 publications

A Real-Time Virtual Re-Convergence Hardware Platform

A Real-Time Virtual Re-Convergence Hardware Platform

Optimizing a Virtual Re-Convergence System to Reduce Visual Fatigue in Stereoscopic Camera

Multi-view Video Based Object Segmentation - A Tutorial

Contact Info

Product

Resources

About