Distinctive Image Features from Scale-Invariant Keypoints
01 Nov 2004-International Journal of Computer Vision (Kluwer Academic Publishers)-Vol. 60, Iss: 2, pp 91-110
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.
Citations
More filters
TL;DR: Implementation of the RED software package for automated collection and processing of rotation electron diffraction data is described.
Abstract: Implementation of a computer program package for automated collection and processing of rotation electron diffraction (RED) data is described. The software package contains two computer programs: RED data collection and RED data processing. The RED data collection program controls the transmission electron microscope and the camera. Electron beam tilts at a fine step (0.05–0.20°) are combined with goniometer tilts at a coarse step (2.0–3.0°) around a common tilt axis, which allows a fine relative tilt to be achieved between the electron beam and the crystal in a large tilt range. An electron diffraction (ED) frame is collected at each combination of beam tilt and goniometer tilt. The RED data processing program processes three-dimensional ED data generated by the RED data collection program or by other approaches. It includes shift correction of the ED frames, peak hunting for diffraction spots in individual ED frames and identification of these diffraction spots as reflections in three dimensions. Unit-cell parameters are determined from the positions of reflections in three-dimensional reciprocal space. All reflections are indexed, and finally a list with hkl indices and intensities is output. The data processing program also includes a visualizer to view and analyse three-dimensional reciprocal lattices reconstructed from the ED frames. Details of the implementation are described. Data collection and data processing with the software RED are demonstrated using a calcined zeolite sample, silicalite-1. The structure of the calcined silicalite-1, with 72 unique atoms, could be solved from the RED data by routine direct methods.
253 citations
Cites background from "Distinctive Image Features from Sca..."
...This is a common blob detection problem in the field of computer vision (Lowe, 2004)....
[...]
01 Dec 2013
TL;DR: A very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions for fast and exact AAM fitting is described.
Abstract: We describe a very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions. Our formulation results in two optimization problems for fast and exact AAM fitting, and one new algorithm which has the important advantage of being applicable to 3D. We show that the dominant cost for both forward and inverse algorithms is a few times mN which is the cost of projecting an image onto the appearance subspace. This makes both algorithms not only computationally realizable but also very attractive speed-wise for most current systems. Because exact AAM fitting is no longer computationally prohibitive, we trained AAMs in-the-wild with the goal of investigating whether AAMs benefit from such a training process. Our results show that although we did not use sophisticated shape priors, robust features or robust norms for improving performance, AAMs perform notably well and in some cases comparably with current state-of-the-art methods. We provide Matlab source code for training, fitting and reproducing the results presented in this paper at http://ibug.doc.ic.ac.uk/resources.
253 citations
TL;DR: The proposed technique for jointly quantizing continuous features and the posterior distributions of their class labels based on minimizing empirical information loss such that the quantizer index of a given feature vector approximates a sufficient statistic for its class label is proposed.
Abstract: This paper proposes a technique for jointly quantizing continuous features and the posterior distributions of their class labels based on minimizing empirical information loss such that the quantizer index of a given feature vector approximates a sufficient statistic for its class label. Informally, the quantized representation retains as much information as possible for classifying the feature vector correctly. We derive an alternating minimization procedure for simultaneously learning codebooks in the Euclidean feature space and in the simplex of posterior class distributions. The resulting quantizer can be used to encode unlabeled points outside the training set and to predict their posterior class distributions, and has an elegant interpretation in terms of lossless source coding. The proposed method is validated on synthetic and real data sets and is applied to two diverse problems: learning discriminative visual vocabularies for bag-of-features image classification and image segmentation.
253 citations
16 Jun 2019
TL;DR: This paper introduces a segmentation-driven 6D pose estimation framework where each visible part of the objects contributes a local pose prediction in the form of 2D keypoint locations and uses a predicted measure of confidence to combine these pose candidates into a robust set of 3D-to-2D correspondences.
Abstract: The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm. In both cases, the object is treated as a global entity, and a single pose estimate is computed. As a consequence, the resulting techniques can be vulnerable to large occlusions. In this paper, we introduce a segmentation-driven 6D pose estimation framework where each visible part of the objects contributes a local pose prediction in the form of 2D keypoint locations. We then use a predicted measure of confidence to combine these pose candidates into a robust set of 3D-to-2D correspondences, from which a reliable pose estimate can be obtained. We outperform the state-of-the-art on the challenging Occluded-LINEMOD and YCB-Video datasets, which is evidence that our approach deals well with multiple poorly-textured objects occluding each other. Furthermore, it relies on a simple enough architecture to achieve real-time performance.
253 citations
Proceedings Article•
07 Dec 2009TL;DR: It is shown that bag-of-words representations commonly used in conjunction with linear classifiers can be viewed as special match kernels, which count 1 if two local features fall into the same regions partitioned by visual words and 0 otherwise.
Abstract: In visual recognition, the images are frequently modeled as unordered collections of local features (bags). We show that bag-of-words representations commonly used in conjunction with linear classifiers can be viewed as special match kernels, which count 1 if two local features fall into the same regions partitioned by visual words and 0 otherwise. Despite its simplicity, this quantization is too coarse, motivating research into the design of match kernels that more accurately measure the similarity between local features. However, it is impractical to use such kernels for large datasets due to their significant computational cost. To address this problem, we propose efficient match kernels (EMK) that map local features to a low dimensional feature space and average the resulting vectors to form a set-level feature. The local feature maps are learned so their inner products preserve, to the best possible, the values of the specified kernel function. Classifiers based on EMK are linear both in the number of images and in the number of local features. We demonstrate that EMK are extremely efficient and achieve the current state of the art in three difficult computer vision datasets: Scene-15, Caltech-101 and Caltech-256.
253 citations
References
More filters
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
"Distinctive Image Features from Sca..." refers background or methods in this paper
...The initial implementation of this approach (Lowe, 1999) simply located keypoints at the location and scale of the central sample point....
[...]
...Earlier work by the author (Lowe, 1999) extended the local feature approach to achieve scale invariance....
[...]
...More details on applications of these features to recognition are available in other pape rs (Lowe, 1999; Lowe, 2001; Se, Lowe and Little, 2002)....
[...]
...To efficiently detect stable keypoint locations in scale space, we have proposed (Lowe, 1999) using scalespace extrema in the difference-of-Gaussian function convolved with the image, D(x, y, σ ), which can be computed from the difference of two nearby scales separated by a constant multiplicative…...
[...]
...More details on applications of these features to recognition are available in other papers (Lowe, 1999, 2001; Se et al., 2002)....
[...]
Book•
01 Jan 2000TL;DR: In this article, the authors provide comprehensive background material and explain how to apply the methods and implement the algorithms directly in a unified framework, including geometric principles and how to represent objects algebraically so they can be computed and applied.
Abstract: From the Publisher:
A basic problem in computer vision is to understand the structure of a real world scene given several images of it. Recent major developments in the theory and practice of scene reconstruction are described in detail in a unified framework. The book covers the geometric principles and how to represent objects algebraically so they can be computed and applied. The authors provide comprehensive background material and explain how to apply the methods and implement the algorithms directly.
15,558 citations
01 Jan 2001
TL;DR: This book is referred to read because it is an inspiring book to give you more chance to get experiences and also thoughts and it will show the best book collections and completed collections.
Abstract: Downloading the book in this website lists can give you more advantages. It will show you the best book collections and completed collections. So many books can be found in this website. So, this is not only this multiple view geometry in computer vision. However, this book is referred to read because it is an inspiring book to give you more chance to get experiences and also thoughts. This is simple, read the soft file of the book and you get it.
14,282 citations
"Distinctive Image Features from Sca..." refers background in this paper
...A more general solution would be to solve for the fundamental matrix (Luong and Faugeras, 1996; Hartley and Zisserman, 2000)....
[...]
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: 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