A Fast Line Segment Based Dense Stereo Algorithm Using Tree Dynamic Programming

Abstract

Many traditional stereo correspondence methods emphasized on utilizing epipolar constraint and ignored the information embedded in inter-epipolar lines. Actually some researchers have already proposed several grid-based algorithms for fully utilizing information embodied in both intra-and inter-epipolar lines. Though their performances are greatly improved, they are very time-consuming. The new graph-cut and believe-propagation methods have made the grid-based algorithms more efficient, but time-consuming still remains a hard problem for many applications. Recently, a tree dynamic programming algorithm is proposed. Though the computation speed is much higher than that of grid-based methods, the performance is degraded apparently. We think that the problem stems from the pixel-based tree construction. Many edges in the original grid are forced to be cut out, and much information embedded in these edges is thus lost. In this paper, a novel line segment based stereo correspondence algorithm using tree dynamic programming (LSTDP) is presented. Each epipolar line of the reference image is segmented into segments first, and a tree is then constructed with these line segments as its vertexes. The tree dynamic programming is adopted to compute the correspondence of each line segment. By using line segments as the vertexes instead of pixels, the connection between neighboring pixels within the same region can be reserved as completely as possible. Experimental results show that our algorithm can obtain comparable performance with state-of-the-art algorithms but is much more time-efficient.

Proximal splitting methods for depth estimation

“…We have also tested the approach recently proposed by Miled et al ("DDE-L2") which uses a cost function based on the ℓ 2 -norm and the same constraints. At this stage, it is worth pointing out that it was shown in [5] that the quality of the results provided by the latter approach is comparable with state-ofthe-art methods, such as those based on graph cuts and dynamic programming [11]. Fig.…”

Bioinformatics Inspired Algorithm for Stereo Correspondence

“…scanline, a new class of DP algorithms, which can be applied efficiently to tree structures, has been recently proposed (Veksler, 2005) and (Deng & Lin 2006). Results show they are significantly more accurate than scanline based methods with only a marginal increase of computational cost.…”

Fast locally consistent dense stereo on multicore

“…In [21], DP-based optimization is performed on a tree structure made of the most important edges. This approach was improved by replacing edges with segments: [11] deploys the Mean Shift algorithm [3], while [4] deploys a fast line segmentation algorithm. This latter class of approaches is quite fast: [21] and [4] runs in a fraction of a second, while [11] runs in a few seconds on standard PCs.…”

“…Moreover, their huge memory footprint typically renders these algorithms inappropriate for devices with constrained resources. Nevertheless, a subclass of global algorithms that enforce the smoothness term in 1D, such as Dynamic Programming (DP) [17,23,21] and Scanline Optimization (SO) [17,8], allow the efficient realization of reasonably accurate results [17,8,23,21,4]. Moreover, some of these methods have a limited memory footprint suited to devices with constrained resources (e.g., [6]) and their computational structure may allow the exploitation of thread-level parallelism.…”