2015 Seventh International Conference on Ubiquitous and Future Networks 2015
DOI: 10.1109/icufn.2015.7182542
|View full text |Cite
|
Sign up to set email alerts
|

A census-based stereo matching algorithm with multiple sparse windows

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2017
2017
2021
2021

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 10 publications
0
3
0
Order By: Relevance
“…We used an eight-bit, gray-level 752 × 480 image and a 15 × 15 window for the stereo matching and an 11 × 11 window for the post-processing. We chose these window sizes because of their high degree of matching accuracy [ 22 ]. Figure 4 shows the fully pipelined hardware architecture of the stereo matching processor, and Table 2 summarizes the features of the stereo matching processors.…”
Section: Stereo Matching Processormentioning
confidence: 99%
“…We used an eight-bit, gray-level 752 × 480 image and a 15 × 15 window for the stereo matching and an 11 × 11 window for the post-processing. We chose these window sizes because of their high degree of matching accuracy [ 22 ]. Figure 4 shows the fully pipelined hardware architecture of the stereo matching processor, and Table 2 summarizes the features of the stereo matching processors.…”
Section: Stereo Matching Processormentioning
confidence: 99%
“…The MSW method aggregates the matching costs of the adjacent sparse windows (SWs) to calculate one matching cost. By applying it to ACT in the calculation of the RMCs of the pixels in the support window, the proposed algorithm becomes robust to noise and generates a slight blurring effect because it aggregates the calculated matching costs of the SWs, whose center pixels are different from each other [13]. In addition, it improves the reliability of the matching cost by using the TAD between the center pixels of a pair of left and right SWs.…”
Section: Proposed Stereo Matching Algorithmmentioning
confidence: 99%
“…This paper, therefore, proposes an improved stereo matching algorithm [12] based on the existing ACT and analyzes its results. To achieve better matching accuracy and robustness to noise, the proposed algorithm adopts the truncated absolute difference (TAD) [8,9] and the multiple sparse windows (MSWs) method [13]. Section 2 of the paper introduces the existing ACT, Section 3 explains the proposed stereo matching algorithm, Section 4 evaluates the experimental results, and Section 5 concludes it.…”
Section: Introductionmentioning
confidence: 99%