Classification and evaluation of cost aggregation methods for stereo correspondence

Tombari, Federico; Mattoccia, Stefano; Stefano, Luigi Di; Addimanda, E.

doi:10.1109/cvpr.2008.4587677

Cited by 180 publications

(148 citation statements)

References 31 publications

Supporting

Mentioning

147

Contrasting

Unclassified

Order By: Relevance

“…Consequently, the resulting reconstructed wave surface is a collection of 3-D scattered points, and proper interpolation enforces spatial and temporal continuity (Benetazzo, 2006). The key issue in such methods is the optimal selection of both the Aggregation Support Window (ASW) and Search Area (SA) for pixel matching with respect to the 2-D image coordinates [y] T (Tombari et al, 2008). Since the camera parameters are known, epipolar geometry reduces the 2-D search to a sequence of 1-D searches along epipolar lines (or a band to account for uncertainties).…”

Section: ¡Mage Processing and Expected Errorsmentioning

confidence: 99%

Offshore stereo measurements of gravity waves

Benetazzo

Fedele

Gallego

et al. 2012

Coastal Engineering

111

104

View full text Add to dashboard Cite

Stereo video techniques are effective for estimating the space-time wave dynamics over an area of the ocean. Indeed, a stereo camera view allows retrieval of both spatial and temporal data whose statistical content is richer than that of time series data retrieved from point wave probes. To prove this, we consider an application of the Wave Acquisition Stereo System (WASS) for the analysis of offshore video measurements of gravity waves in the Northern Adriatic Sea. In particular, we deployed WASS at the oceanographic platform Acqua Alta, off the Venice coast, Italy. Three experimental studies were performed, and the overlapping field of view of the acquired stereo images covered an area of approximately 1100 m 2 . Analysis of the WASS measurements show that the sea surface can be accurately estimated in space and time together, yielding associated directional spectra and wave statistics that agree well with theoretical models. From the observed wavenumber-frequency spectrum one can also predict the vertical profile of the current flow underneath the wave surface. Finally, future improvements of WASS and applications are discussed.

show abstract

Section: ¡Mage Processing and Expected Errorsmentioning

confidence: 99%

Offshore stereo measurements of gravity waves

Benetazzo

Fedele

Gallego

et al. 2012

Coastal Engineering

111

104

View full text Add to dashboard Cite

show abstract

“…Violations of the single surface assumption typically lead to poor disparity boundary localization due to surface overextension. To overcome this issue, different researchers have proposed the use of variable cost aggregation within the photo-consistency function [3,14]. Among these approaches, adaptive weighing of each pixel contribution enables texture driven pixel segregation within a single image block [7,15].…”

Section: Background and Related Workmentioning

confidence: 99%

Adaptive Scale Selection for Hierarchical Stereo

Jen¹,

Dunn²,

Fite-Georgel³

et al. 2011

Procedings of the British Machine Vision Conference 2011

View full text Add to dashboard Cite

Hierarchical stereo provides an efficient coarse-to-fine mechanism for disparity map estimation. However, common drawbacks of such an approach include the loss of high frequency structures not observable at coarse scale levels, as well as the unrecoverable propagation of erroneous disparity estimates through the scale space. This paper presents an adaptive scale selection mechanism to determine a suitable resolution level from which to begin the hierarchical depth estimation process for each pixel. The proposed scale selection mechanism allows us to robustly implement variable cost aggregation in order to reduce the variability of the photo-consistency measure across scale space. We also incorporate a weighted shiftable window mechanism to enable error correction during coarse-to-fine depth refinement. Experiments illustrate the effectiveness of our approach in terms of disparity accuracy, while attaining a computational efficiency compromise between full resolution and hierarchical disparity map estimation.

show abstract

“…Although local algorithms [20,17] based on the adaptive weights approach [28] yielded excellent results [28,14,9], according to [17,16], most of the top-performing stereo algorithms rely on global approaches (e.g., [10,24,26,25,27,2,22,19]). Given a rectified stereo pair, these latter methods solve the correspondence problem in terms of a pixellabeling assignment of disparities, determining the disparity field D that minimizes…”

Section: Related Workmentioning

confidence: 99%

“…In local algorithms the focus is on cost aggregation [20] and disparity optimization is typically a simple Winner Takes All (WTA) strategy. These algorithms have a simple and regular computational structure that allows, in some cases, for fast/real-time implementations on standard PCs and their limited memory footprint renders these approaches suited to devices with constrained resources (e.g.…”

Section: Introductionmentioning

confidence: 99%