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
Proceedings Article•
21 Jun 2010
TL;DR: It is shown that the reasons underlying the performance of various pooling methods are obscured by several confounding factors, such as the link between the sample cardinality in a spatial pool and the resolution at which low-level features have been extracted.
Abstract: Many modern visual recognition algorithms incorporate a step of spatial 'pooling', where the outputs of several nearby feature detectors are combined into a local or global 'bag of features', in a way that preserves task-related information while removing irrelevant details. Pooling is used to achieve invariance to image transformations, more compact representations, and better robustness to noise and clutter. Several papers have shown that the details of the pooling operation can greatly influence the performance, but studies have so far been purely empirical. In this paper, we show that the reasons underlying the performance of various pooling methods are obscured by several confounding factors, such as the link between the sample cardinality in a spatial pool and the resolution at which low-level features have been extracted. We provide a detailed theoretical analysis of max pooling and average pooling, and give extensive empirical comparisons for object recognition tasks.
1,239 citations
17 Jun 2007
TL;DR: An unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions that alleviates the over-parameterization problems that plague purely supervised learning procedures, and yields good performance with very few labeled training samples.
Abstract: We present an unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions. The resulting feature extractor consists of multiple convolution filters, followed by a feature-pooling layer that computes the max of each filter output within adjacent windows, and a point-wise sigmoid non-linearity. A second level of larger and more invariant features is obtained by training the same algorithm on patches of features from the first level. Training a supervised classifier on these features yields 0.64% error on MNIST, and 54% average recognition rate on Caltech 101 with 30 training samples per category. While the resulting architecture is similar to convolutional networks, the layer-wise unsupervised training procedure alleviates the over-parameterization problems that plague purely supervised learning procedures, and yields good performance with very few labeled training samples.
1,232 citations
23 Jun 2008
TL;DR: It is argued that two practices commonly used in image classification methods, have led to the inferior performance of NN-based image classifiers: Quantization of local image descriptors (used to generate "bags-of-words ", codebooks) and Computation of 'image-to-image' distance, instead of ' image- to-class' distance.
Abstract: State-of-the-art image classification methods require an intensive learning/training stage (using SVM, Boosting, etc.) In contrast, non-parametric nearest-neighbor (NN) based image classifiers require no training time and have other favorable properties. However, the large performance gap between these two families of approaches rendered NN-based image classifiers useless. We claim that the effectiveness of non-parametric NN-based image classification has been considerably undervalued. We argue that two practices commonly used in image classification methods, have led to the inferior performance of NN-based image classifiers: (i) Quantization of local image descriptors (used to generate "bags-of-words ", codebooks). (ii) Computation of 'image-to-image' distance, instead of 'image-to-class' distance. We propose a trivial NN-based classifier - NBNN, (Naive-Bayes nearest-neighbor), which employs NN- distances in the space of the local image descriptors (and not in the space of images). NBNN computes direct 'image- to-class' distances without descriptor quantization. We further show that under the Naive-Bayes assumption, the theoretically optimal image classifier can be accurately approximated by NBNN. Although NBNN is extremely simple, efficient, and requires no learning/training phase, its performance ranks among the top leading learning-based image classifiers. Empirical comparisons are shown on several challenging databases (Caltech-101 ,Caltech-256 and Graz-01).
1,228 citations
Book•
31 Dec 2006TL;DR: In this article, the basic motion models underlying alignment and stitching algorithms are described, and effective direct (pixel-based) and feature-based alignment algorithms, and blending algorithms used to produce seamless mosaics.
Abstract: This tutorial reviews image alignment and image stitching algorithms. Image alignment algorithms can discover the correspondence relationships among images with varying degrees of overlap. They are ideally suited for applications such as video stabilization, summarization, and the creation of panoramic mosaics. Image stitching algorithms take the alignment estimates produced by such registration algorithms and blend the images in a seamless manner, taking care to deal with potential problems such as blurring or ghosting caused by parallax and scene movement as well as varying image exposures. This tutorial reviews the basic motion models underlying alignment and stitching algorithms, describes effective direct (pixel-based) and feature-based alignment algorithms, and describes blending algorithms used to produce seamless mosaics. It ends with a discussion of open research problems in the area.
1,226 citations
TL;DR: This paper presents RGB-D Mapping, a full 3D mapping system that utilizes a novel joint optimization algorithm combining visual features and shape-based alignment to achieve globally consistent maps.
Abstract: RGB-D cameras (such as the Microsoft Kinect) are novel sensing systems that capture RGB images along with per-pixel depth information. In this paper we investigate how such cameras can be used for building dense 3D maps of indoor environments. Such maps have applications in robot navigation, manipulation, semantic mapping, and telepresence. We present RGB-D Mapping, a full 3D mapping system that utilizes a novel joint optimization algorithm combining visual features and shape-based alignment. Visual and depth information are also combined for view-based loop-closure detection, followed by pose optimization to achieve globally consistent maps. We evaluate RGB-D Mapping on two large indoor environments, and show that it effectively combines the visual and shape information available from RGB-D cameras.
1,223 citations
Cites methods from "Distinctive Image Features from Sca..."
...The SIFT features of Lowe (2004) are commonly used as well as fast descriptors based on random trees from Calonder et al. (2008), which can be computed for any desired keypoints, such as the FAST keypoints described by Rosten and Drummond (2006)....
[...]
...The major additions are: • we utilize re-projection error for frame-to-frame alignment RANSAC and demonstrate that it performs better than the Euclidean-space RANSAC used in Henry et al. (2010); • we use FAST features and Calonder descriptors instead of scale-invariant feature transform (SIFT); • we improve the efficiency of loop closure detection through place recognition; • we improve global optimization by using sparse bundle adjustment (SBA) and compare it with TORO; • we show how to incorporate ICP constraints into SBA, a crucial component in featureless areas....
[...]
...Se and Jasiobedzki (2008) use a stereo camera combined with SIFT features to create 3D models of environments, but make no provision for loop closure or global consistency....
[...]
...The related work of Droeschel et al. (2009) uses sparse features (SIFT) only and focuses on 2D motions on a robot platform....
[...]
...Andreasson and Lilienthal (2010) also use SIFT features, with depth interpolated from a laser scanner, to estimate full 6D registration....
[...]
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