#### DMCA

## SURF: Speeded Up Robust Features

### Cached

### Download Links

- [lear.inrialpes.fr]
- [imagine.enpc.fr]
- [www.vision.ee.ethz.ch]
- [nichol.as]
- [nichol.as]
- [www.cse.unr.edu]
- [nichol.as]
- [www.cse.unr.edu]
- [nichol.as]
- DBLP

### Other Repositories/Bibliography

Venue: | ECCV |

Citations: | 838 - 12 self |

### Citations

8753 | Distinctive image features from scale-invariant keypoints
- Lowe
(Show Context)
Citation Context ...ations. Skew, anisotropic scaling, and perspective effects are assumed to be second-order effects, that are covered to some degree by the overall robustness of the descriptor. As also claimed by Lowe =-=[2]-=-, the additional complexity of full affine-invariant features often has a negative impact on their robustness and does not pay off, unless really large viewpoint changes are to be expected. In some ca... |

3201 | Rapid object detection using a boosted cascade of simple features
- Viola, Jones
- 2001
(Show Context)
Citation Context ...h increases not only the matching speed, but also the robustness of the descriptor. In order to make the paper more self-contained, we succinctly discuss the concept of integral images, as defined by =-=[23]-=-. They allow for the fast implementation of box type convolution filters. The entry of an integral image IΣ(x) atalocation x =(x, y) represents the sum of all pixels in the input image I of a rectangu... |

2661 | Object recognition from local scale-invariant features
- Lowe
- 1999
(Show Context)
Citation Context ...sed a (scale-adapted) Harris measure or the determinant of the Hessian matrix to select the location, and thesSURF: Speeded Up Robust Features 3 Laplacian to select the scale. Focusing on speed, Lowe =-=[12]-=- approximated the Laplacian of Gaussian (LoG) by a Difference of Gaussians (DoG) filter. Several other scale-invariant interest point detectors have been proposed. Examples are the salient region dete... |

2418 | A combined corner edge detector.
- Harris, Stephens
- 1988
(Show Context)
Citation Context ...nted. Finally, section 5 shows the experimental results and section 6 concludes the paper. 2 Related Work Interest Point Detectors The most widely used detector probably is the Harris corner detector =-=[10]-=-, proposed back in 1988, based on the eigenvalues of the second-moment matrix. However, Harris corners are not scale-invariant. Lindeberg introduced the concept of automatic scale selection [1]. This ... |

1742 | A Performance Evaluation of Local Descriptors
- Mikolajczyk, Schmid
- 2005
(Show Context)
Citation Context ...res [21], and descriptors representing the distribution of smaller-scale features within the interest point neighbourhood. The latter, introduced by Lowe [2], have been shown to outperform the others =-=[7]-=-. This can be explained by the fact that they capture a substantial amount of information about the spatial intensity patterns, while at the same time being robust to small deformations or localisatio... |

1451 | An affine invariant interest point detector
- Mikolajczyk, Schmid
- 2002
(Show Context)
Citation Context ...eature detectors have been proposed that can cope with longer viewpoint changes. However, these fall outside the scope of this paper. By studying the existing detectors and from published comparisons =-=[15, 8]-=-, we can conclude that (1) Hessian-based detectors are more stable and repeatable than their Harris-based counterparts. Using the determinant of the Hessian matrix rather than its trace (the Laplacian... |

1072 | The design and use of steerable filters
- Freeman, Adelson
- 1991
(Show Context)
Citation Context ...ost accuracy. Feature Descriptors An even larger variety of feature descriptors has been proposed, like Gaussian derivatives [16], moment invariants [17], complex features [18, 19], steerable filters =-=[20]-=-, phase-based local features [21], and descriptors representing the distribution of smaller-scale features within the interest point neighbourhood. The latter, introduced by Lowe [2], have been shown ... |

996 | Robust wide baseline stereo from maximally stable extremal regions
- Matas, Chum, et al.
(Show Context)
Citation Context ...nts, like reducing the descriptor’s dimension and complexity, while keeping it sufficiently distinctive. A wide variety of detectors and descriptors have already been proposed in the literature (e.g. =-=[1, 2, 3, 4, 5, 6]-=-). Also, detailed comparisons and evaluations on benchmarking datasets have been performed [7, 8, 9]. While constructing our fast detector and descriptor, we built on the insights gained from this pre... |

840 |
The structure of images
- Koenderink
- 1984
(Show Context)
Citation Context ...the convolution of the Gaussian second order derivative ∂ 2 ∂x 2 g(σ) with the image I in point x, and similarly for Lxy(x, σ)andLyy(x, σ). Gaussians are optimal for scale-space analysis, as shown in =-=[24]-=-. In practice, however, the Gaussian needs to be discretised and cropped (Fig. 1 left half), and even with Gaussian filters aliasing still occurs as soon as the resulting images are sub-sampled. Also,... |

709 | Feature Detection with Automatic Scale Selection
- Lindeberg
- 1998
(Show Context)
Citation Context ...ector [10], proposed back in 1988, based on the eigenvalues of the second-moment matrix. However, Harris corners are not scale-invariant. Lindeberg introduced the concept of automatic scale selection =-=[1]-=-. This allows to detect interest points in an image, each with their own characteristic scale. He experimented with both the determinant of the Hessian matrix as well as the Laplacian (which correspon... |

571 | Pca-sift: A more distinctive representation for local image descriptors
- Ke, Sukthankar
- 2004
(Show Context)
Citation Context ...interest point and stores the bins in a 128-dimensional vector (8 orientation bins for each of the 4 × 4 location bins). Various refinements on this basic scheme have been proposed. Ke and Sukthankar =-=[4]-=- applied PCA on the gradient image. This PCA-SIFT yields a 36dimensional descriptor which is fast for matching, but proved to be less distinctive than SIFT in a second comparative study by Mikolajczyk... |

400 | Indexing based on scale invariant interest points
- Mikolajczyk, Schmid
- 2001
(Show Context)
Citation Context ...ct bloblike structures. Mikolajczyk and Schmid refined this method, creating robust and scale-invariant feature detectors with high repeatability, which they coined Harris-Laplace and Hessian-Laplace =-=[11]-=-. They used a (scale-adapted) Harris measure or the determinant of the Hessian matrix to select the location, and thesSURF: Speeded Up Robust Features 3 Laplacian to select the scale. Focusing on spee... |

358 | A comparison of affine region detectors
- Mikolajczyk, Tuytelaars, et al.
- 2005
(Show Context)
Citation Context ...) (see Fig. 6, discussed below). The descriptor evaluations are shown for all sequences except the Bark sequence (see Fig. 4 and 7). For the detectors, we use the repeatability score, as described in =-=[9]-=-. This indicates how many of the detected interest points are found in both images, relative to the lowest total number of interest points found (where only the part of the image that is visible in bo... |

305 | Reliable feature matching across widely separated views
- Baumberg
- 2000
(Show Context)
Citation Context ... at a low cost in terms of lost accuracy. Feature Descriptors An even larger variety of feature descriptors has been proposed, like Gaussian derivatives [16], moment invariants [17], complex features =-=[18, 19]-=-, steerable filters [20], phase-based local features [21], and descriptors representing the distribution of smaller-scale features within the interest point neighbourhood. The latter, introduced by Lo... |

211 |
Multi-view matching for unordered image sets, how do I organize my holiday snaps
- Schaffalitzky, Zisserman
- 2007
(Show Context)
Citation Context ... at a low cost in terms of lost accuracy. Feature Descriptors An even larger variety of feature descriptors has been proposed, like Gaussian derivatives [16], moment invariants [17], complex features =-=[18, 19]-=-, steerable filters [20], phase-based local features [21], and descriptors representing the distribution of smaller-scale features within the interest point neighbourhood. The latter, introduced by Lo... |

153 | Invariant features from interest point groups
- Brown, Lowe
- 2002
(Show Context)
Citation Context ...aximum suppression in a 3 × 3 × 3 neighbourhood is applied. The maxima of the determinant of the Hessian matrix are then interpolated in scale and image space with the method proposed by Brown et al. =-=[27]-=-. Scale space interpolation is especially important in our case, as the difference in scale betweens6 H. Bay, T. Tuytelaars, and L. Van Gool Fig. 2. Left: Detected interest points for a Sunflower fiel... |

95 | Scale-invariant Shape Features for Recognition of Object Categories
- Jurie, Schmid
- 2004
(Show Context)
Citation Context ...ve been proposed. Examples are the salient region detector proposed by Kadir and Brady [13], which maximises the entropy within the region, and the edge-based region detector proposed by Jurie et al. =-=[14]-=-. They seem less amenable to acceleration though. Also, several affine-invariant feature detectors have been proposed that can cope with longer viewpoint changes. However, these fall outside the scope... |

84 |
Saliency and Image Description
- Kadir, Brady, et al.
- 2001
(Show Context)
Citation Context ...ussian (LoG) by a Difference of Gaussians (DoG) filter. Several other scale-invariant interest point detectors have been proposed. Examples are the salient region detector proposed by Kadir and Brady =-=[13]-=-, which maximises the entropy within the region, and the edge-based region detector proposed by Jurie et al. [14]. They seem less amenable to acceleration though. Also, several affine-invariant featur... |

49 | Multi-scale Phase-based Local Features
- Carneiro, Jepson
- 2003
(Show Context)
Citation Context ... An even larger variety of feature descriptors has been proposed, like Gaussian derivatives [16], moment invariants [17], complex features [18, 19], steerable filters [20], phase-based local features =-=[21]-=-, and descriptors representing the distribution of smaller-scale features within the interest point neighbourhood. The latter, introduced by Lowe [2], have been shown to outperform the others [7]. Thi... |

44 | Moment invariants for recognition under changing viewpoint and illumination," Computer Vision and Image Understanding
- Mindru, Tuytelaars, et al.
- 2004
(Show Context)
Citation Context ...the DoG can bring speed at a low cost in terms of lost accuracy. Feature Descriptors An even larger variety of feature descriptors has been proposed, like Gaussian derivatives [16], moment invariants =-=[17]-=-, complex features [18, 19], steerable filters [20], phase-based local features [21], and descriptors representing the distribution of smaller-scale features within the interest point neighbourhood. T... |

42 |
Gool, ”Wide baseline stereo based on local, affinely invariant regions
- Tuytelaars, Van
- 2000
(Show Context)
Citation Context ...nts, like reducing the descriptor’s dimension and complexity, while keeping it sufficiently distinctive. A wide variety of detectors and descriptors have already been proposed in the literature (e.g. =-=[1, 2, 3, 4, 5, 6]-=-). Also, detailed comparisons and evaluations on benchmarking datasets have been performed [7, 8, 9]. While constructing our fast detector and descriptor, we built on the insights gained from this pre... |

35 | General intensity transformations and differential invariants
- Florack, Romeny, et al.
- 1994
(Show Context)
Citation Context ...(2) approximations like the DoG can bring speed at a low cost in terms of lost accuracy. Feature Descriptors An even larger variety of feature descriptors has been proposed, like Gaussian derivatives =-=[16]-=-, moment invariants [17], complex features [18, 19], steerable filters [20], phase-based local features [21], and descriptors representing the distribution of smaller-scale features within the interes... |

35 |
Discrete Scale-Space Theory and the Scale-Space Primal Sketch
- Lindeberg
- 1991
(Show Context)
Citation Context ...ng images are sub-sampled. Also, the property that no new structures can appear while going to lower resolutions may have been proven in the 1D case, but is known to not apply in the relevant 2D case =-=[25]-=-. Hence, the importance of the Gaussian seems to have been somewhat overrated in this regard, and here we test a simpler alternative. As Gaussian filters are non-ideal in any case, and given Lowe’s su... |

28 | BRETZNER L.: Real-Time Scale Selection in Hybrid Multi-Scale Representations
- LINDEBERG
- 2003
(Show Context)
Citation Context ...tives scale accordingly. Thus, for example, our 27 × 27 filter corresponds to σ =3× 1.2 =3.6 =s. Furthermore, as the Frobenius norm remains constant for our filters, they are already scale normalised =-=[26]-=-. In order to localise interest points in the image and over scales, a nonmaximum suppression in a 3 × 3 × 3 neighbourhood is applied. The maxima of the determinant of the Hessian matrix are then inte... |

22 | Vision based Modeling and Localization for Planetary Exploration Rovers
- Se, Ng, et al.
- 2004
(Show Context)
Citation Context ...e the most appealing descriptor for practical uses, and hence also the most widely used nowadays. It is distinctive and relatively fast, which is crucial for on-line applications. Recently, Se et al. =-=[22]-=- implemented SIFT on a Field Programmable Gate Array (FPGA) and improved its speed by an order of magnitude. However, the high dimensionality of the descriptor is a drawback of SIFT at the matching st... |