Advances in Computational Stereo

By Myron Z. Brown, Darius Burschka, Gregory Hager. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003

1,315 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e02edd5fc99c5900e71f9133ecb403b93cccdff0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Quality Assessment of Stereoscopic Images (2008, background): “Several signal processing operations [9, 10] have been specifically designed for stereoscopic images.”
Visual simultaneous localization and mapping: a survey (2012, neutral): “3 of Brown et al. (2003).”
Real-time structured light profilometry: a review (2016, methodology): “Stereo vision profilometry 49 techniques [8,9] simulate the stereoscopic setup of human vision by employing a second camera 50 placed at an angle with the original camera.”
Evaluation of Stereo Matching Costs on Images with Radiometric Differences (2009, neutral): “Recent stereo surveys [32], [33] and the Middlebury online evaluation [34] compare state-of-the-art stereo methods on test data with complex geometries and varied texture.”
State of the art in high density image matching (2014, methodology): “The reader is instead referred to surveys and comparisons of matching algorithms presented in Makarovic (1992), Scharstein and Szeliski (2002), Brown et al. (2003), Seitz et al. (2006), Hirschm € uller and Scharstein (2009) and Gruen (2012).”
The leaf angle distribution of natural plant populations: assessing the canopy with a novel software tool (2015, methodology): “We implemented a block matching method, which makes use of the properties of the surrounding pixels and which uses a couple of statistical measures [40,41], e.g. the correlation C of grey values, where corresponding pixels are given by the maximum correlation C max of blocks [42].”
Semi-global Stereo Matching with Surface Orientation Priors (2017, background): “Stereo matching is one of the oldest and most-thoroughly studied problems in computer vision [40, 10].”
Fast 3D Scanning with Automatic Motion Compensation (2007, result): “In contrast to the above methods, multi-camera systems work with normal ambient light and reconstruct the 3D geometry using triangulation between cameras [15, 4].”
Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision? (2013, neutral): “, [16]).”
Motion Detail Preserving Optical Flow Estimation (2012, neutral): “Thus, we detect occlusion using the mapping uniqueness criterion [8], expressed as”
A fast local descriptor for dense matching (2008, background): “Though dense shot-baseline stereo matching is well understood [ 7 , 22], its wide baseline counterpart is, by contrast, much more challenging due to large perspective distortions and increased occluded areas.”
Optical techniques for 3D surface reconstruction in computer-assisted laparoscopic surgery (2013, background): “For a detailed perspective on the state-of-the art in computational stereo techniques outside surgery, the reader is referred to two comprehensive reviews of the field up to 2003 (Scharstein and Szeliski, 2002; Brown et al., 2003).”
Evaluation of Cost Functions for Stereo Matching (2007, background): “More complicated similarity measures are possible, including mutual information [7, 9, 11] and approximative Recent stereo surveys [5, 17] and the Middlebury online evaluation [14] compare state-of-the-art stereo methods on test data with complex geometries and varied texture.”
3-D Depth Reconstruction from a Single Still Image (2007, background): “(14)One can also envisage obtaining a better estimate of σg as a function of a match metric used during stereo correspondence [62], such as normalized sum of squared differences; or learning σg as a function of disparity/texture based features.”
A Review of Computer Vision Techniques for the Analysis of Urban Traffic (2011, neutral): “In contrast, we define a “bottom–up” approach as an approach that first detects and classifies parts of an object (see Fig.”
Equivalence of digital image correlation criteria for pattern matching. (2010, methodology): “In literature, various criteria, including crosscorrelation (CC) criterion, sum of absolute difference (SAD), sum of squared difference (SSD), and parametric sum of squared difference (PSSD) have been designed and used [4,6,9–17].”