Open Access
Abstract: Distinctive Image Features from Scale-Invariant Keypoints
TLDR
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.read more
Citations
More filters
Patent
Fast subspace projection of descriptor patches for image recognition
TL;DR: In this paper, a set of pre-generated sparse projection vectors and sparsely sampled pixel information for a plurality of pixels across the plurality of scale levels is used to generate a descriptor for a keypoint in the scale space.
Proceedings ArticleDOI
Localized contourlet features in vehicle make and model recognition
TL;DR: A novel localized feature detection method in Contourlet transform domain that is capable of increasing the classification rates up to 4%, as compared to the previously proposedcontourlet based vehicle MMR approach in which the features are non-localized and thus results in sub-optimal classification.
Proceedings ArticleDOI
Content Based Video Retrieval Using Spatiotemporal Salient Objects
Han-ping Gao,Zu-qiao Yang +1 more
TL;DR: This paper proposes a fusion method for motion and spatial saliency integration to detect spatiotemporal salient objects, based on both attention analysis and interest point trajectory tracking, which provides a practical approach to narrow the semantic gap.
Patent
Efficient descriptor extraction over multiple levels of an image scale space
TL;DR: In this paper, a local feature descriptor for a point in an image is generated by sparsely sampling a plurality of smoothed orientation maps corresponding to two or more scale spaces from the plurality of scale spaces.
Proceedings ArticleDOI
Substation remote infrared image registration based on multi-scale Harris corner and hierarchical guiding match strategy
Xinghua Zhang,Dongmei Wu +1 more
TL;DR: A substation remote infrared image registration method based on multi-scale Harris corner and hierarchical guiding match strategy that has acquired high registration accuracy and short time and good stability, all controlled within 6~7 seconds.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
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.
Proceedings ArticleDOI
Object recognition from local scale-invariant features
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.
Proceedings ArticleDOI
A Combined Corner and Edge Detector
Chris Harris,Mike Stephens +1 more
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.
Book ChapterDOI
SURF: speeded up robust features
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.
Journal ArticleDOI
A performance evaluation of local descriptors
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.