Fast explicit diffusion for accelerated features in nonlinear scale spaces
01 Jan 2013-
TL;DR: A novel and fast multiscale feature detection and description approach that exploits the benefits of nonlinear scale spaces and introduces a Modified-Local Difference Binary (M-LDB) descriptor that is highly efficient, exploits gradient information from the non linear scale space, is scale and rotation invariant and has low storage requirements.
Abstract: We propose a novel and fast multiscale feature detection and description approach that exploits the benefits of nonlinear scale spaces. Previous attempts to detect and describe features in nonlinear scale spaces such as KAZE [1] and BFSIFT [6] are highly time consuming due to the computational burden of creating the nonlinear scale space. In this paper we propose to use recent numerical schemes called Fast Explicit Diffusion (FED) [3, 4] embedded in a pyramidal framework to dramatically speed-up feature detection in nonlinear scale spaces. In addition, we introduce a Modified-Local Difference Binary (M-LDB) descriptor that is highly efficient, exploits gradient information from the nonlinear scale space, is scale and rotation invariant and has low storage requirements. Our features are called Accelerated-KAZE (A-KAZE) due to the dramatic speed-up introduced by FED schemes embedded in a pyramidal framework.
Citations
More filters
TL;DR: ORB-SLAM as discussed by the authors is a feature-based monocular SLAM system that operates in real time, in small and large indoor and outdoor environments, with a survival of the fittest strategy that selects the points and keyframes of the reconstruction.
Abstract: This paper presents ORB-SLAM, a feature-based monocular simultaneous localization and mapping (SLAM) system that operates in real time, in small and large indoor and outdoor environments. The system is robust to severe motion clutter, allows wide baseline loop closing and relocalization, and includes full automatic initialization. Building on excellent algorithms of recent years, we designed from scratch a novel system that uses the same features for all SLAM tasks: tracking, mapping, relocalization, and loop closing. A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation. We present an exhaustive evaluation in 27 sequences from the most popular datasets. ORB-SLAM achieves unprecedented performance with respect to other state-of-the-art monocular SLAM approaches. For the benefit of the community, we make the source code public.
4,522 citations
TL;DR: A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation.
Abstract: This paper presents ORB-SLAM, a feature-based monocular SLAM system that operates in real time, in small and large, indoor and outdoor environments. The system is robust to severe motion clutter, allows wide baseline loop closing and relocalization, and includes full automatic initialization. Building on excellent algorithms of recent years, we designed from scratch a novel system that uses the same features for all SLAM tasks: tracking, mapping, relocalization, and loop closing. A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation. We present an exhaustive evaluation in 27 sequences from the most popular datasets. ORB-SLAM achieves unprecedented performance with respect to other state-of-the-art monocular SLAM approaches. For the benefit of the community, we make the source code public.
3,807 citations
Cites methods from "Fast explicit diffusion for acceler..."
...On the other hand keyframe-based approaches [3] estimate the map using only selected frames, called keyframes, allowing to perform more costly but accurate bundle adjustment optimizations, as mapping is not tied to frame-rate....
[...]
TL;DR: This paper aims at presenting a brief but almost self-contented introduction to the most important approaches dedicated to vision-based camera localization along with a survey of several extension proposed in the recent years.
Abstract: Augmented reality (AR) allows to seamlessly insert virtual objects in an image sequence. In order to accomplish this goal, it is important that synthetic elements are rendered and aligned in the scene in an accurate and visually acceptable way. The solution of this problem can be related to a pose estimation or, equivalently, a camera localization process. This paper aims at presenting a brief but almost self-contented introduction to the most important approaches dedicated to vision-based camera localization along with a survey of several extension proposed in the recent years. For most of the presented approaches, we also provide links to code of short examples. This should allow readers to easily bridge the gap between theoretical aspects and practical implementations.
506 citations
Cites background from "Fast explicit diffusion for acceler..."
...more robust, and accelerated for real-time detection [3]....
[...]
TL;DR: This survey introduces feature detection, description, and matching techniques from handcrafted methods to trainable ones and provides an analysis of the development of these methods in theory and practice, and briefly introduces several typical image matching-based applications.
Abstract: As a fundamental and critical task in various visual applications, image matching can identify then correspond the same or similar structure/content from two or more images. Over the past decades, growing amount and diversity of methods have been proposed for image matching, particularly with the development of deep learning techniques over the recent years. However, it may leave several open questions about which method would be a suitable choice for specific applications with respect to different scenarios and task requirements and how to design better image matching methods with superior performance in accuracy, robustness and efficiency. This encourages us to conduct a comprehensive and systematic review and analysis for those classical and latest techniques. Following the feature-based image matching pipeline, we first introduce feature detection, description, and matching techniques from handcrafted methods to trainable ones and provide an analysis of the development of these methods in theory and practice. Secondly, we briefly introduce several typical image matching-based applications for a comprehensive understanding of the significance of image matching. In addition, we also provide a comprehensive and objective comparison of these classical and latest techniques through extensive experiments on representative datasets. Finally, we conclude with the current status of image matching technologies and deliver insightful discussions and prospects for future works. This survey can serve as a reference for (but not limited to) researchers and engineers in image matching and related fields.
474 citations
Cites methods from "Fast explicit diffusion for acceler..."
...An accelerated version called AKAZA (Alcantarilla and Solutions 2011) is implemented by embedding the fast explicit diffusion in a pyramidal framework to dramatically speedup feature detection in nonlinear scale spaces....
[...]
03 Mar 2018
TL;DR: SIFT and BRISK are found to be the most accurate algorithms while ORB and BRK are most efficient and a benchmark for researchers, regardless of any particular area is set.
Abstract: Image registration is the process of matching, aligning and overlaying two or more images of a scene, which are captured from different viewpoints. It is extensively used in numerous vision based applications. Image registration has five main stages: Feature Detection and Description; Feature Matching; Outlier Rejection; Derivation of Transformation Function; and Image Reconstruction. Timing and accuracy of feature-based Image Registration mainly depend on computational efficiency and robustness of the selected feature-detector-descriptor, respectively. Therefore, choice of feature-detector-descriptor is a critical decision in feature-matching applications. This article presents a comprehensive comparison of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK algorithms. It also elucidates a critical dilemma: Which algorithm is more invariant to scale, rotation and viewpoint changes? To investigate this problem, image matching has been performed with these features to match the scaled versions (5% to 500%), rotated versions (0° to 360°), and perspective-transformed versions of standard images with the original ones. Experiments have been conducted on diverse images taken from benchmark datasets: University of OXFORD, MATLAB, VLFeat, and OpenCV. Nearest-Neighbor-Distance-Ratio has been used as the feature-matching strategy while RANSAC has been applied for rejecting outliers and fitting the transformation models. Results are presented in terms of quantitative comparison, feature-detection-description time, feature-matching time, time of outlier-rejection and model fitting, repeatability, and error in recovered results as compared to the ground-truths. SIFT and BRISK are found to be the most accurate algorithms while ORB and BRISK are most efficient. The article comprises rich information that will be very useful for making important decisions in vision based applications and main aim of this work is to set a benchmark for researchers, regardless of any particular area.
339 citations
Cites methods from "Fast explicit diffusion for acceler..."
...In this article, SIFT (blobs) [13], SURF (blobs) [14], KAZE (blobs) [15], AKAZE (blobs) [16], ORB (corners) [17], and BRISK (corners) [18] algorithms are compared for image matching and registration....
[...]
...presented Accelerated-KAZE (AKAZE) algorithm in 2013 [16], which is also based on nonlinear diffusion filtering like KAZE but its non-linear scale spaces are constructed using a computationally efficient framework called Fast Explicit Diffusion (FED)....
[...]
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
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.
14,708 citations
"Fast explicit diffusion for acceler..." refers methods in this paper
...The best known multiscale feature detection and description approaches are SIFT [11] and SURF [3], SURF being less computationally demanding than SIFT....
[...]
...We consider a nearest neighbor distance ratio matching criteria [11] using a distance ratio value between descriptor distances of 0....
[...]
07 May 2006
TL;DR: A novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
Abstract: In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features). It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descriptors (in casu, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods to the essential. This leads to a combination of novel detection, description, and matching steps. The paper presents experimental results on a standard evaluation set, as well as on imagery obtained in the context of a real-life object recognition application. Both show SURF's strong performance.
13,011 citations
"Fast explicit diffusion for acceler..." refers methods in this paper
...We consider the OpenCV implementations of BRISK, ORB, SIFT and SURF since these implementations are highly optimized in terms of speed....
[...]
...This method increases repeatability and distinctiveness with respect to SIFT and SURF thanks to the use of nonlinear diffusion filtering....
[...]
...With the proliferation of camera-enabled mobile devices that have limited computational resources, new features have appeared that aim to reduce computational complexity while keeping up to the performance of methods such as SIFT and SURF....
[...]
...Both approaches make use of the Gaussian scale space, either by constructing the Gaussian scale space in a pyramidal framework such as in SIFT, or by approximating Gaussian derivatives through box filters as in SURF....
[...]
...The best known multiscale feature detection and description approaches are SIFT [11] and SURF [3], SURF being less computationally demanding than SIFT....
[...]
TL;DR: A new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced, chosen to vary spatially in such a way as to encourage intra Region smoothing rather than interregion smoothing.
Abstract: A new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced. The diffusion coefficient is chosen to vary spatially in such a way as to encourage intraregion smoothing rather than interregion smoothing. It is shown that the 'no new maxima should be generated at coarse scales' property of conventional scale space is preserved. As the region boundaries in the approach remain sharp, a high-quality edge detector which successfully exploits global information is obtained. Experimental results are shown on a number of images. Parallel hardware implementations are made feasible because the algorithm involves elementary, local operations replicated over the image. >
12,560 citations
"Fast explicit diffusion for acceler..." refers methods in this paper
...We consider one of the two conductivity functions introduced in the seminal work of Perona and Malik [14], although other conductivity functions are also possible....
[...]
...We consider one of the two conductivity functions introduced in the seminal work of Perona and Malik [13], although other conductivity functions are also possible....
[...]
06 Nov 2011
TL;DR: This paper proposes a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise, and demonstrates through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations.
Abstract: Feature matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods rely on costly descriptors for detection and matching. In this paper, we propose a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise. We demonstrate through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations. The efficiency is tested on several real-world applications, including object detection and patch-tracking on a smart phone.
8,702 citations
"Fast explicit diffusion for acceler..." refers methods in this paper
...ORB and BRISK features are much faster to compute than SIFT and SURF, while showing comparable performance mainly for small image transformations....
[...]
...ORB [15] and BRISK [10] speed-up feature detection and description by combining modifications of the FAST corner detector [14] and binary descriptors based on BRIEF [4] with scale and rotation invariance....
[...]
...Binary descriptors (such as those used in BRIEF, ORB and BRISK) have enjoyed widespread use lately since they can be computed and matched very efficiently....
[...]
...ORB [16] and BRISK [11] speed-up feature detection and description by combining modifications of the FAST corner detector [15] and binary descriptors based on BRIEF [5] with scale and rotation invariance....
[...]
...For BRISK, ORB, SURF and SIFT we used their OpenCV implementations, while for KAZE we use the original library which is also OpenCV-based1....
[...]