BRIEF: Computing a Local Binary Descriptor Very Fast

Calonder, Michael; Lepetit, Vincent; Özuysal, Mustafa; Trzciński, Tomasz Piotr; Strecha, Christoph; Fua, Pascal

doi:10.1109/tpami.2011.222

Cited by 693 publications

(491 citation statements)

References 35 publications

Supporting

Mentioning

471

Contrasting

Unclassified

Order By: Relevance

“…-We demonstrate that, despite learning a separate representation for each individual keypoint similar to [3,8,9,19], our approach does not require a brute-force search in a large descriptor set when coupled with the LSH [2] approach to compute the list of K near neighbors. -We show that our approach is relatively descriptor independent and it extends the matching range of several binary descriptors: BRIEF [5], ORB [21], BRISK [10], FREAK [1], and LATCH [11], which has recently been shown to outperform state-of-the-art binary descriptors.…”

Section: Figmentioning

confidence: 78%

“…5 Recognition rate improves when we exploit the information in the first ten near neighbors as opposed to using just the nearest neighbor. Note that the improvement is most significant when the recognition rate is low (3)(4)(5)(6) and the number of matches may not be enough for correct registration of the test image. The performance improves as M is increased from 4 to 8, however increasing M beyond 10 degrades performance due to the exponentially increasing number of parameters in the probabilistic model that requires even more training data.…”

Section: Recognition Rate Over Ground Truth Correspondencesmentioning

confidence: 99%

“…The binary descriptors (such as [1,5,10,11,18,21,22]) are extensively used in real-time applications for object detection This work was supported by the TÜBİTAK project 113E496.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Instance detection by keypoint matching beyond the nearest neighbor

Uzyıldırım

Özuysal

2016

SIViP

View full text Add to dashboard Cite

The binary descriptors are the representation of choice for real-time keypoint matching. However, they suffer from reduced matching rates due to their discrete nature. We propose an approach that can augment their performance by searching in the top K near neighbor matches instead of just the single nearest neighbor one. To pick the correct match out of the K near neighbors, we exploit statistics of descriptor variations collected for each keypoint in an off-line training phase. This is a similar approach to those that learn a patch specific keypoint representation. Unlike these approaches, we only use a keypoint specific score to rank the list of K near neighbors. Since this list can be efficiently computed with approximate nearest neighbor algorithms, our approach scales well to large descriptor sets.

show abstract

Section: Figmentioning

confidence: 78%

Section: Recognition Rate Over Ground Truth Correspondencesmentioning

confidence: 99%

See 1 more Smart Citation

Instance detection by keypoint matching beyond the nearest neighbor

Uzyıldırım

Özuysal

2016

SIViP

View full text Add to dashboard Cite

show abstract

“…More recently, Larsen et al [81] made use of multi-local N-jet descriptors that do not rely on a spatial statistics of receptive field responses as used in the SIFT and SURF descriptors or their analogues. A notable observation from experimental results is that very good performance can be obtained with coarsely quantized even binary image descriptors (Pietikäinen et al [131], Linde and Lindeberg [88], Calonder et al [26]). Moreover, Zhang et al [158] have demonstrated what can be gained in computer vision by considering biologically inspired image descriptors.…”

Section: Related Workmentioning

confidence: 99%

Image Matching Using Generalized Scale-Space Interest Points

Lindeberg

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The performance of matching and object recognition methods based on interest points depends on both the properties of the underlying interest points and the choice of associated image descriptors. This paper demonstrates advantages of using generalized scale-space interest point detectors in this context for selecting a sparse set of points for computing image descriptors for image-based matching. For detecting interest points at any given scale, we make use of the Laplacian ∇ 2 norm L, the determinant of the Hessian det H norm L and four new unsigned or signed Hessian feature strength measures D 1,norm L,D 1,norm L, D 2,norm L and D 2,norm L, which are defined by generalizing the definitions of the Harris and Shi-and-Tomasi operators from the second moment matrix to the Hessian matrix. Then, feature selection over different scales is performed either by scale selection from local extrema over scale of scale-normalized derivates or by linking features over scale into feature trajectories and computing a significance measure from an integrated measure of normalized feature strength over scale. A theoretical analysis is presented of the robustness of the differential entities underlying these interest points under image deformations, in terms of invariance properties under affine image deformations or approximations thereof. Disregarding the effect of the rotationally symmetric scale-space smoothing operation, the determinant of the Hessian det H norm L is a truly affine covariant differential entity and the Hessian feature strength measures D 1,norm L andD 1,norm L have a major contribution from the affine covariant determinant of the Hessian, implying that local extrema of these differen- It is shown how these generalized scale-space interest points allow for a higher ratio of correct matches and a lower ratio of false matches compared to previously known interest point detectors within the same class. The best results are obtained using interest points computed with scale linking and with the new Hessian feature strength measures D 1,norm L,D 1,norm L and the determinant of the Hessian det H norm L being the differential entities that lead to the best matching performance under perspective image transformations with significant foreshortening, and better than the more commonly used Laplacian operator, its difference-of-Gaussians approximation or the Harris-Laplace operator. We propose that these generalized scale-space interest points, when accompanied by associated local scale-invariant image descriptors, should allow for better performance of interest point based methods for image-based matching, object recognition and related visual tasks.

show abstract

“…ORB [10] and BRISK [11] speed-up feature detection and description by combining modifications of the FAST corner detector [12] and binary descriptors based on BRIEF [13] with scale and rotation invariance. ORB and BRISK feature are much faster to compute than SIFT and SURF, while showing comparable performance.…”

Section: Introductionmentioning

confidence: 99%

Fast Image Diffusion for Feature Detection and Description

Liu¹,

Wu²,

Liu³

2016

IJCTE

View full text Add to dashboard Cite

Abstract-In this paper, we introduce a new multiscale 2D feature detection and description method based on optimal O(1) bilateral filter feature (OBFF). Existing methods detect and describe features by analyzing the scale space generated by linear and nonlinear diffusion kernel function, like Gaussian scale space and anisotropic diffusion scale space. By using the anisotropic diffusion scale space, KAZE features achieve significant progress on the 2D feature detection by using the anisotropic diffusion scale space. It makes the blurring locally adaptive and retains better feature localization accuracy and distinctiveness than the SIFT method. Our method OBFF also generates the nonlinear scale space of image to detect the local feature. The optimal bilateral filter is advantage in object boundary preserving and antinoise ability and dramatically speed up feature detection in nonlinear scale space. We use the benchmark datasets to compare our method with state-of-the-art approaches.Index Terms-Bilateral filter, nonlinear scale space, feature detection, SIFT, binary descriptor.

show abstract

BRIEF: Computing a Local Binary Descriptor Very Fast

Cited by 693 publications

References 35 publications

Instance detection by keypoint matching beyond the nearest neighbor

Instance detection by keypoint matching beyond the nearest neighbor

Image Matching Using Generalized Scale-Space Interest Points

Fast Image Diffusion for Feature Detection and Description

Contact Info

Product

Resources

About