Full-Image Guided Filtering for Fast Stereo Matching

Yang, Qingqing; Li, Dongxiao; Wang, Lianghao; Zhang, Ming

doi:10.1109/lsp.2013.2241759

Cited by 31 publications

(42 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, three cost aggregation methods are evaluated with various Middlebury data sets: aggregation with proposed method based on eightconnected weight propagation (denoted as WP-8), aggregation with the method based on four-connected weight propagation (denoted as WP-4) [22], aggregation with the method based on MST [22].…”

Section: Resultsmentioning

confidence: 99%

“…The parameter for WP-8 is kept constant for all four benchmark stereo pairs: G = 0.11. For WP-4 [22] method, their parameters follow the settings of corresponding paper. Source code of MST [16] method is available on the author's main page.…”

Section: Resultsmentioning

confidence: 99%

“…The best path would be the one that has the minimum weight propagation, but the computational complexity will be too high to have an efficient implementation. In [22], the authors proposed to compute , ; , ( )…”

Section: Amentioning

confidence: 99%

“…Recently, Yang [22] proposed a full-image guided filtering based on four-connected weight propagation. The author proposed to compute weight propagation using a fourconnected grid based on the guide image.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Improved Filtering for Fast Stereo Matching

Huang¹,

Cui²,

Zhang³

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

This paper presents a novel full-image guided filtering based on eight-connected weight propagation for dense stereo matching. The proposed method has three main features: first, the proposed eight-connected weight propagation is more approximate compared to previous approach; second, the pixels employed into the filtering are all the pixels without constrained by one fixed window; last but not least, computational complexity of each pixel at each disparity level is O(1), and the implementation of the filter can efficiently parallelized on hardware platform. Performance evaluation on Middlebury data sets shows that the proposed method is one of the best local algorithms in terms of both accuracy and speed.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Amentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Improved Filtering for Fast Stereo Matching

Huang¹,

Cui²,

Zhang³

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…샘플링기법을 이용하여 속도를 개선하는 연구 [9] , 양방 향 모델을 적용한 가이드 이미지 필터 [10] 등이 제안되 었다. full-image guided filter [10] 는 저질감 영역에서의 경계 보존을 만족하며, 가중치를 분산해서 연산함으로 [10] . full-image guided filter의 필터링을 과정을 설명하면 다음과 같다.…”

unclassified

Efficient VLSI Architecture of Full-Image Guided Filter Based on Two-Pass Model

Lee¹,

Park²

2016

The Journal of Korean Institute of Communications and Informati

View full text Add to dashboard Cite

Key Words : realtime system, guide filter, VLSI architecture, image filter, two-pass model ABSTRACT Full-image guided filter reflects all pixels of image in filtering by using weight propagation and two-pass model, whereas the existing guide filter is processed based on the kernel window. Therefore the computational complexity can be improved while maintaining characteristics of guide filter, such as edge-preserving, smoothing, and so on. In this paper, we propose an efficient VLSI architecture for the full-image guided filter by analyzing the data dependency, the data frequency and the PSNR analysis of the image in order to achieve enough speed for various applications such as stereo vision, real-time systems, etc. In addition, the proposed efficient scheduling enables the realtime process by minimizing the idle period in weight computation. The proposed VLSI architecture shows 214MHz of maximum operating frequency (image size: 384*288, 965 fps) and 76K of gates (internal memory excluded).

show abstract