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
01 May 2019
TL;DR: The study showed that there are still many challenges ahead for this emerging area owing to the complex nature of deep learning and wide coverage of smart city applications, and pointed out a number of future directions related to deep learning efficiency, emergent deep learning paradigms, knowledge fusion and privacy preservation.
Abstract: Rapid urbanization has brought about great challenges to our daily lives, such as traffic congestion, environmental pollution, energy consumption, public safety, and so on. Research on smart cities aims to address these issues with various technologies developed for the Internet of Things. Very recently, the research focus has shifted toward processing of massive amount of data continuously generated within a city environment, e.g., physical and participatory sensing data on traffic flow, air quality, and health care. Techniques from computational intelligence have been applied to process and analyze such data, and to extract useful knowledge that helps citizens better understand their surroundings and informs city authorities to provide better and more efficient public services. Deep learning, as a relatively new paradigm in computational intelligence, has attracted substantial attention of the research community and demonstrated greater potential over traditional techniques. This paper provides a survey of the latest research on the convergence of deep learning and smart city from two perspectives: while the technique-oriented review pays attention to the popular and extended deep learning models, the application-oriented review emphasises the representative application domains in smart cities. Our study showed that there are still many challenges ahead for this emerging area owing to the complex nature of deep learning and wide coverage of smart city applications. We pointed out a number of future directions related to deep learning efficiency, emergent deep learning paradigms, knowledge fusion and privacy preservation, and hope these would move the relevant research one step further in creating truly distributed intelligence for smart cities.
99 citations
Cites methods from "Distinctive Image Features from Sca..."
...The number of rows representative handcrafted features include Scale-Invariant Feature Transform (SIFT) [48] and Histogram of Oriented Gradients (HOG) [49]....
[...]
...representative handcrafted features include Scale-Invariant Feature Transform (SIFT) [48] and Histogram of Oriented Gradients (HOG) [49]....
[...]
TL;DR: Recent research findings in animal biometrics are presented, with a strong focus on cattle biometric identifiers such as muzzle prints, iris patterns, and retinal vascular patterns, which may drive future research directions.
99 citations
Cites methods from "Distinctive Image Features from Sca..."
...In Awad et al. (2013b), the authors applied the Scale-Invariant Feature Transform (SIFT) algorithm, combined with a Random Sample Consensus (RANSAC) algorithm, and in doing so they improved the identification accuracy using the previously collected database....
[...]
...In Sun et al. (2013), the authors used SIFT (Lowe, 1999, 2004; Mikolajczyk and Schmid, 2005) as a feature extractor for identifying bovine animals....
[...]
...Recently, Noviyanto and Arymurthy (2013) presented a study of using SIFT features and SIFT features combined with a refinement technique for improving identification accuracy....
[...]
...Moreover, the extraction time of SIFT features can be drastically reduced by using modern parallel processing techniques (Awad, 2013)....
[...]
TL;DR: This paper presents a method for estimating six degrees of freedom camera motions from central catadioptric images in man-made environments by decoupling the rotation and the translation and shows that the line-based approach allows to estimate the absolute attitude at each frame, without error accumulation.
99 citations
TL;DR: This work proposes multimodal hypergraph (MMHG) to characterize the complex associations between landmark images and designs a novel content-based visual landmark search system based on MMHG to facilitate effective search.
Abstract: While content-based landmark image search has recently received a lot of attention and became a very active domain, it still remains a challenging problem. Among the various reasons, high diverse visual content is the most significant one. It is common that for the same landmark, images with a wide range of visual appearances can be found from different sources and different landmarks may share very similar sets of images. As a consequence, it is very hard to accurately estimate the similarities between the landmarks purely based on single type of visual feature. Moreover, the relationships between landmark images can be very complex and how to develop an effective modeling scheme to characterize the associations still remains an open question. Motivated by these concerns, we propose multimodal hypergraph (MMHG) to characterize the complex associations between landmark images. In MMHG, images are modeled as independent vertices and hyperedges contain several vertices corresponding to particular views. Multiple hypergraphs are firstly constructed independently based on different visual modalities to describe the hidden high-order relations from different aspects. Then, they are integrated together to involve discriminative information from heterogeneous sources. We also propose a novel content-based visual landmark search system based on MMHG to facilitate effective search. Distinguished from the existing approaches, we design a unified computational module to support query-specific combination weight learning. An extensive experiment study on a large-scale test collection demonstrates the effectiveness of our scheme over state-of-the-art approaches.
99 citations
Cites methods from "Distinctive Image Features from Sca..."
...In this paper, densely sampling strategy is employed to detect interest points and scale invariant feature transform [45] is used to describe image patches....
[...]
01 Feb 2017
TL;DR: This study not only reviews typical deep learning algorithms in computer vision and signal processing but also provides detailed information on how to apply deep learning to specific areas such as road crack detection, fault diagnosis, and human activity detection.
Abstract: Deep learning is a subfield of machine learning, which aims to learn a hierarchy of features from input data. Nowadays, researchers have intensively investigated deep learning algorithms for solving challenging problems in many areas such as image classification, speech recognition, signal processing, and natural language processing. In this study, we not only review typical deep learning algorithms in computer vision and signal processing but also provide detailed information on how to apply deep learning to specific areas such as road crack detection, fault diagnosis, and human activity detection. Besides, this study also discusses the challenges of designing and training deep neural networks.
99 citations
Cites background from "Distinctive Image Features from Sca..."
...Comparedwith hand-crafted features, for example, Local Binary Patterns (LBP) [55] and Scale Invariant Feature Transform (SIFT) [56], which need additional classifiers to solve vision problems [57–59], the CNNs can learn the features and the classifiers jointly and provide superior performance....
[...]
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