Matching Widely Separated Views Based on Affine Invariant Regions

By Tinne Tuytelaars, Luc Van Gool. International Journal of Computer Vision, 2004

748 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/021bdc52f560900052a30b2feefca83f7a797904

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

Local Intensity Order Pattern for feature description (2011, methodology): “For example, Harris corner [10] and DoG(Difference of Gaussian) [13] for interest point detection, and Harris-affine [15], Hessian-affine [17], MSER(Maximally Stable Extremal Region) [14], IBR(Intensity-Based Region) and EBR(EdgeBased Region) [24] for affine covariant region detection.”
Description of interest regions with local binary patterns (2009, background): “Local features have performed very well in many computer vision applications, such as image retrieval [1], wide baseline matching [2], object recognition [3], texture recognition [4], and robot localization [5].”
Robust Point Matching via Vector Field Consensus (2014, methodology): “[52], and the match correctness is determined by manually refining the results of RANSAC.”
Efficient Non-Maximum Suppression (2006, background): “A good recent example is the extraction of interest points [3, 4, 2].”
An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency (2013, methodology): “Though there is some work on detecting and tracking scale invariant lines [20,21], the proposed multi-scale line extraction approach simply apply the EDLine [22] detector to a scale-space pyramid consisting a set of octave images, because it is more efficient to detect features in the scale space [2”
Groups of Adjacent Contour Segments for Object Detection (2008, background): “Hence, they can be reused effor tl ssly in a variety of recognition and image matching frameworks as a replacement or addition t o i terest points (such as [1], [6], [12], [18], [31]).”
A Comparison of Affine Region Detectors (2005, neutral): “More details about this method can be found in [47, 48].”
A performance evaluation of local descriptors (2005, background): “Local photometric descriptors computed for interest regions have proved to be very successful in applications such as wide baseline matching [37, 42], object recognition [10, 25], texture”
Modeling the World from Internet Photo Collections (2008, background): “However, for true wide baseline matching, i.e., the automatic matching of images taken from widely different views (Baumberg 2000; Schaffalitzky and Zisserman 2002; Strecha et al. 2003; Tuytelaars and Van Gool 2004; Matas et al. 2004), (weakly) affine-invariant feature descriptors must be used.”
Image Based Localization in Urban Environments (2006, background): “There are several representatives of local image features [9, 10, 11, 12] which have been shown to be robust with respect to changes in scale and/or affine transformations.”
Automated Construction of Robotic Manipulation Programs (2010, background): “A second approach is based on analyzing the structure of solutions sets of polynomial systems [Wampler and Morgan (1991)], but suffers from numerical ill-conditioning.”
Object Recognition in the Geometric Era: A Retrospective (2006, methodology): “The successful application of this idea by Cordelia Schmid and Roger Mohr [72] inspired an intensive search for other intensity and aﬃne projection invariant features [46, 70, 79, 38, 50].”