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
TL;DR: Experiments show that the vision system is accurate, robust, and capable of dealing with an incomplete landing target, whilst the overall implementation shows the practicability of real-time onboard target tracking and closed-loop control.
Abstract: We present a vision system design for landing an unmanned aerial vehicle on a ship's flight deck autonomously. The edge information from the international landing target is used to perform line segment detection, feature point mapping and clustering. Then a cascade filtering scheme is applied for target recognition. Meanwhile, the 4 DoF pose of the vehicle with respect to the target is estimated. The vision system has been implemented on the Asctec Pelican quadrotor in conjunction with a state estimator to perform real-time target recognition and tracking. An onboard controller is designed to close the control loop. Experiments show that the vision system is accurate, robust, and capable of dealing with an incomplete landing target, whilst the overall implementation shows the practicability of real-time onboard target tracking and closed-loop control.
98 citations
Cites methods from "Distinctive Image Features from Sca..."
...Apart from the works listed above, it’s worth mentioning that some feature based methods such as the scale invariant feature transform (SIFT) and the speed-up robust features (SURF) have been adopted in some works for UAV shipboard landing (Lowe 2004; Bay et al. 2008)....
[...]
21 Jul 2013
TL;DR: This paper presents a new method for consistent editing of photo collections that automatically enforces consistent appearance of images that share content without any user input, and demonstrates the usefulness of the approach using a number of personal and professional photo collections, as well as internet collections.
Abstract: With dozens or even hundreds of photos in today's digital photo albums, editing an entire album can be a daunting task. Existing automatic tools operate on individual photos without ensuring consistency of appearance between photographs that share content. In this paper, we present a new method for consistent editing of photo collections. Our method automatically enforces consistent appearance of images that share content without any user input. When the user does make changes to selected images, these changes automatically propagate to other images in the collection, while still maintaining as much consistency as possible. This makes it possible to interactively adjust an entire photo album in a consistent manner by manipulating only a few images.Our method operates by efficiently constructing a graph with edges linking photo pairs that share content. Consistent appearance of connected photos is achieved by globally optimizing a quadratic cost function over the entire graph, treating user-specified edits as constraints in the optimization. The optimization is fast enough to provide interactive visual feedback to the user. We demonstrate the usefulness of our approach using a number of personal and professional photo collections, as well as internet collections.
98 citations
Additional excerpts
...Bag of visual words [Sivic and Zisserman 2003]: A histogram of densely sampled SIFT descriptors [Lowe 2004], quantized by a codebook of size 600....
[...]
01 Dec 2013
TL;DR: A semantic-aware co-indexing algorithm to jointly embed two strong cues into the inverted indexes: local invariant features that are robust to delineate low-level image contents, and semantic attributes from large-scale object recognition that may reveal image semantic meanings.
Abstract: Inverted indexes in image retrieval not only allow fast access to database images but also summarize all knowledge about the database, so that their discriminative capacity largely determines the retrieval performance. In this paper, for vocabulary tree based image retrieval, we propose a semantic-aware co-indexing algorithm to jointly embed two strong cues into the inverted indexes: 1) local invariant features that are robust to delineate low-level image contents, and 2) semantic attributes from large-scale object recognition that may reveal image semantic meanings. For an initial set of inverted indexes of local features, we utilize 1000 semantic attributes to filter out isolated images and insert semantically similar images to the initial set. Encoding these two distinct cues together effectively enhances the discriminative capability of inverted indexes. Such co-indexing operations are totally off-line and introduce small computation overhead to online query cause only local features but no semantic attributes are used for query. Experiments and comparisons with recent retrieval methods on 3 datasets, i.e., UKbench, Holidays, Oxford5K, and 1.3 million images from Flickr as distractors, manifest the competitive performance of our method.
97 citations
TL;DR: High-resolution topography derived from SfM revealed to be essential in the sediment connectivity analysis and, therefore, in the estimation of eroded materials, when comparing them to those derived from the rainfall simulation methodology.
97 citations
Cites background from "Distinctive Image Features from Sca..."
..., 2012), in the SfM, matches are made between points across many photographswithout prior knowledge of the camera position (Lowe, 2004)....
[...]
...…the position of the camera or the positions of some points are known prior to scene reconstruction (Fonstad et al., 2013; Verhoeven et al., 2012; Westoby et al., 2012), in the SfM, matches are made between points across many photographswithout prior knowledge of the camera position (Lowe, 2004)....
[...]
TL;DR: This paper will present a survey of the articles accepted for the special issue, and a detailed comparison and discussion of the corresponding experimental results, in order to assess which are the advantages and disadvantages of each approach.
97 citations
Cites methods from "Distinctive Image Features from Sca..."
...Then two different descriptors are used in order to represent the image: an extended version of the SIFT descriptor [18], able to encode local gradients in a rotation-invariant manner, and a variant of the CoALBP descriptor [11], namely the Gradient-Oriented Co-occurrence of LBP (GoC-LBP): the main idea of the GoC-LBP is to evaluate the orientation of the local gradient in the neighborhood of each pixel....
[...]
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