High-Quality Real-Time Stereo Using Adaptive Cost Aggregation and Dynamic Programming

We present a stereo algorithm that achieves high quality results while maintaining real-time performance. The key idea is simple: we introduce an adaptive aggregation step in a dynamic-programming (DP) stereo framework. The per-pixel matching cost is aggregated in the vertical direction only. Compar...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:3DPVT 2006 : Third International Symposium on 3D Data Processing, Visualization, and Transmission : June 14-16, 2006, University of North Carolina, Chapel Hill, USA s. 798 - 805
Hlavní autoři: Liang Wang, Miao Liao, Minglun Gong, Ruigang Yang, Nister, D.
Médium: Konferenční příspěvek
Jazyk:angličtina
japonština
Vydáno: IEEE 01.06.2006
Témata:
Computer graphics
Computer vision
Costs
Dynamic programming
Hardware
Model driven engineering
Parallel processing
Performance gain
Stereo vision
ISBN:0769528252, 9780769528250
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We present a stereo algorithm that achieves high quality results while maintaining real-time performance. The key idea is simple: we introduce an adaptive aggregation step in a dynamic-programming (DP) stereo framework. The per-pixel matching cost is aggregated in the vertical direction only. Compared to traditional DP, our approach reduces the typical "streaking" artifacts without the penalty of blurry object boundaries. Evaluation using the benchmark Middlebury stereo database shows that our approach is among the best (ranked first in the new evaluation system) for DP-based approaches. The performance gain mainly comes from a computationally expensive weighting scheme based on color and distance proximity. We utilize the vector processing capability and parallelism in commodity graphics hardware to speed up this process over two orders of magnitude. Over 50 million disparity evaluations per second (MDE/s)1 are achieved in our current implementation.
ISBN:0769528252
9780769528250
DOI:10.1109/3DPVT.2006.75