Distinctive Image Features from Scale-Invariant Keypoints
01 Jan 2011-
TL;DR: The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images that can then be used to reliably match objects in diering images.
Abstract: The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images. These features can then be used to reliably match objects in diering images. The algorithm was rst proposed by Lowe [12] and further developed to increase performance resulting in the classic paper [13] that served as foundation for SIFT which has played an important role in robotic and machine vision in the past decade.
Citations
More filters
08 Jul 2009
TL;DR: The Bag of Words pipeline forms the basis to compare various fast alternatives for all of its components, and a fast algorithm to densely sample SIFT and SURF is proposed, and several variants of these descriptors are compared.
Abstract: We start from the state-of-the-art Bag of Words pipeline that in the 2008 benchmarks of TRECvid and PASCAL yielded the best performance scores. We have contributed to that pipeline, which now forms the basis to compare various fast alternatives for all of its components: (i) For descriptor extraction we propose a fast algorithm to densely sample SIFT and SURF, and we compare several variants of these descriptors. (ii) For descriptor projection we compare a k-means visual vocabulary with a Random Forest. As a preprojection step we experiment with PCA on the descriptors to decrease projection time. (iii) For classification we use Support Vector Machines and compare the x2 kernel with the RBF kernel. Our results lead to a 10-fold speed increase without any loss of accuracy and to a 30-fold speed increase with 17% loss of accuracy, where the latter system does real-time classification at 26 images per second.
102 citations
Cites background from "Distinctive Image Features from Sca..."
...Mikolajczyk and Schmid [13] did a comparison of different descriptors and found SIFT [9] or SIFT-like descriptors to be the best for matching under different invariances....
[...]
TL;DR: Comparison of the models obtained using the presented method with those obtained using a precise laser scanner shows that multiview 3D reconstruction yields models that present a root mean square error/average linear dimensions between 0.11 and 0.68%.
102 citations
Cites methods from "Distinctive Image Features from Sca..."
...This process is carried out using the scale invariant feature transform (SIFT) algorithm (Lowe, 2004)....
[...]
...The procedure applied in this work comprises the following steps: (i) the scale invariant feature transform (SIFT) algorithm (Lowe, 2004) is used for key-point extraction; (ii) the...
[...]
...The procedure applied in this work comprises the following steps: (i) the scale invariant feature transform (SIFT) algorithm (Lowe, 2004) is used for key-point extraction; (ii) the open-source SfM software package Bundler (Snavely et al., 2006, 2007) generates a sparse 3D point cloud with…...
[...]
TL;DR: A generalized platform for constructing local shape descriptors that subsumes a large class of existing methods, and that allows for tuning to the geometry of specific models is presented.
102 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...Since this is computationally costly, a simple approximation could be used that only requires comparing the maximum value (I1) with the second largest value (I2) [21,14]....
[...]
...Local descriptors have been widely used for point matching both in 2-D intensity images [21,22] and in 3-D range data (i....
[...]
TL;DR: The main conclusions of this study are: all analyzed methods perform very well under the conditions in which they were evaluated, except for the case of GJD that has low performance in outdoor setups; the best tradeoff between high recognition rate and fast processing speed is obtained by WLD-based methods; and in experiments where the test images are acquired in an outdoor setup and the gallery images are acquiring in an indoor setup, the performance of all evaluated methods is very low.
102 citations
References
More filters
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Abstract: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.
46,906 citations
20 Sep 1999
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Abstract: An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low residual least squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
16,989 citations
01 Jan 1988
TL;DR: The problem the authors are addressing in Alvey Project MMI149 is that of using computer vision to understand the unconstrained 3D world, in which the viewed scenes will in general contain too wide a diversity of objects for topdown recognition techniques to work.
Abstract: The problem we are addressing in Alvey Project MMI149 is that of using computer vision to understand the unconstrained 3D world, in which the viewed scenes will in general contain too wide a diversity of objects for topdown recognition techniques to work. For example, we desire to obtain an understanding of natural scenes, containing roads, buildings, trees, bushes, etc., as typified by the two frames from a sequence illustrated in Figure 1. The solution to this problem that we are pursuing is to use a computer vision system based upon motion analysis of a monocular image sequence from a mobile camera. By extraction and tracking of image features, representations of the 3D analogues of these features can be constructed.
13,993 citations
TL;DR: It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.
Abstract: In this paper, we compare the performance of descriptors computed for local interest regions, as, for example, extracted by the Harris-Affine detector [Mikolajczyk, K and Schmid, C, 2004]. Many different descriptors have been proposed in the literature. It is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations. We compare shape context [Belongie, S, et al., April 2002], steerable filters [Freeman, W and Adelson, E, Setp. 1991], PCA-SIFT [Ke, Y and Sukthankar, R, 2004], differential invariants [Koenderink, J and van Doorn, A, 1987], spin images [Lazebnik, S, et al., 2003], SIFT [Lowe, D. G., 1999], complex filters [Schaffalitzky, F and Zisserman, A, 2002], moment invariants [Van Gool, L, et al., 1996], and cross-correlation for different types of interest regions. We also propose an extension of the SIFT descriptor and show that it outperforms the original method. Furthermore, we observe that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best. Moments and steerable filters show the best performance among the low dimensional descriptors.
7,057 citations
TL;DR: The high utility of MSERs, multiple measurement regions and the robust metric is demonstrated in wide-baseline experiments on image pairs from both indoor and outdoor scenes.
3,422 citations