Object recognition from local scale-invariant features
20 Sep 1999-Vol. 2, pp 1150-1157
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.
Citations
More filters
TL;DR: It is argued that a concerted approach is required to create and disseminate simple and reliable workflows to ensure that the highly automated workflows adopted by archaeologists in contract-led contexts are robust and reliable and underpinned by guidance and knowledge exchange.
154 citations
Dissertation•
01 Jan 2005TL;DR: An algorithmic approach to learning similarity from examples of what objects are deemed similar according to the task-specific notion of similarity at hand, as well as optional negative examples, which allows to predict when two previously unseen examples are similar and to efficiently search a very large database for examples similar to a query.
Abstract: The right measure of similarity between examples is important in many areas of computer science. In particular it is a critical component in example-based learning methods. Similarity is commonly defined in terms of a conventional distance function, but such a definition does not necessarily capture the inherent meaning of similarity, which tends to depend on the underlying task. We develop an algorithmic approach to learning similarity from examples of what objects are deemed similar according to the task-specific notion of similarity at hand, as well as optional negative examples. Our learning algorithm constructs, in a greedy fashion, an encoding of the data. This encoding can be seen as an embedding into a space, where a weighted Hamming distance is correlated with the unknown similarity. This allows us to predict when two previously unseen examples are similar and, importantly, to efficiently search a very large database for examples similar to a query.
This approach is tested on a set of standard machine learning benchmark problems. The model of similarity learned with our algorithm provides and improvement over standard example-based classification and regression. We also apply this framework to problems in computer vision: articulated pose estimation of humans from single images, articulated tracking in video, and matching image regions subject to generic visual similarity. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)
154 citations
TL;DR: The accuracy in object space obtained by GNSS-supported orientation of four photogrammetric blocks acquired by a senseFly eBee RTK and all flown according to the same flight plan at 80 m above ground over a test field is reported on.
Abstract: UAV Photogrammetry today already enjoys a largely automated and efficient data processing pipeline. However, the goal of dispensing with Ground Control Points looks closer, as dual-frequency GNSS receivers are put on board. This paper reports on the accuracy in object space obtained by GNSS-supported orientation of four photogrammetric blocks, acquired by a senseFly eBee RTK and all flown according to the same flight plan at 80 m above ground over a test field. Differential corrections were sent to the eBee from a nearby ground station. Block orientation has been performed with three software packages: PhotoScan, Pix4D and MicMac. The influence on the checkpoint errors of the precision given to the projection centers has been studied: in most cases, values in Z are critical. Without GCP, the RTK solution consistently achieves a RMSE of about 2–3 cm on the horizontal coordinates of checkpoints. In elevation, the RMSE varies from flight to flight, from 2 to 10 cm. Using at least one GCP, with all packages and all test flights, the geocoding accuracy of GNSS-supported orientation is almost as good as that of a traditional GCP orientation in XY and only slightly worse in Z.
153 citations
Cites methods from "Object recognition from local scale..."
...Tie points extraction is executed by feature matching with SIFT operator [59]....
[...]
TL;DR: Three categories of methods are reviewed and compared, including those based on hand-engineered features, learned features and weakly supervised learning, and a number of popular datasets aiming for facilitating the development of new segmentation algorithms.
153 citations
Patent•
30 Apr 2007TL;DR: In this article, the authors present an alternative or improved data structure created by multiple filtering operations to generate a plurality of filtered images as well as data structures for storing the filtered images themselves, e.g. as stored in memory or transmitted through a network.
Abstract: Methods and apparatus for operating on images are described, in particular methods and apparatus for interest point detection and/or description working under different scales and with different rotations, e.g. for scale- invariant and rotation-invariant interest point detection and/or description. The present invention can provide improved or alternative apparatus and methods for matching interest points either in the same image or in a different image. The present invention can provide alternative or improved software for implementing any of the methods of the invention. The present invention can provide alternative or improved data structures created by multiple filtering operations to generate a plurality of filtered images as well as data structures for storing the filtered images themselves, e.g. as stored in memory or transmitted through a network. The present invention can provide alternative or improved data structures including descriptors of interest points in images, e.g. as stored in memory or transmitted through a network as well as datastructures associating such descriptors with an original copy of the image or an image derived therefrom, e.g. a thumbnail image.
153 citations
References
More filters
[...]
TL;DR: In this paper, color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models, and they can differentiate among a large number of objects.
Abstract: Computer vision is moving into a new era in which the aim is to develop visual skills for robots that allow them to interact with a dynamic, unconstrained environment. To achieve this aim, new kinds of vision algorithms need to be developed which run in real time and subserve the robot's goals. Two fundamental goals are determining the identity of an object with a known location, and determining the location of a known object. Color can be successfully used for both tasks.
This dissertation demonstrates that color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models. It shows that color histograms are stable object representations in the presence of occlusion and over change in view, and that they can differentiate among a large number of objects. For solving the identification problem, it introduces a technique called Histogram Intersection, which matches model and image histograms and a fast incremental version of Histogram Intersection which allows real-time indexing into a large database of stored models. It demonstrates techniques for dealing with crowded scenes and with models with similar color signatures. For solving the location problem it introduces an algorithm called Histogram Backprojection which performs this task efficiently in crowded scenes.
5,672 citations
TL;DR: It is shown how the boundaries of an arbitrary non-analytic shape can be used to construct a mapping between image space and Hough transform space, which makes the generalized Houghtransform a kind of universal transform which can beused to find arbitrarily complex shapes.
4,310 citations
TL;DR: A near real-time recognition system with 20 complex objects in the database has been developed and a compact representation of object appearance is proposed that is parametrized by pose and illumination.
Abstract: The problem of automatically learning object models for recognition and pose estimation is addressed. In contrast to the traditional approach, the recognition problem is formulated as one of matching appearance rather than shape. The appearance of an object in a two-dimensional image depends on its shape, reflectance properties, pose in the scene, and the illumination conditions. While shape and reflectance are intrinsic properties and constant for a rigid object, pose and illumination vary from scene to scene. A compact representation of object appearance is proposed that is parametrized by pose and illumination. For each object of interest, a large set of images is obtained by automatically varying pose and illumination. This image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the object is represented as a manifold. Given an unknown input image, the recognition system projects the image to eigenspace. The object is recognized based on the manifold it lies on. The exact position of the projection on the manifold determines the object's pose in the image. A variety of experiments are conducted using objects with complex appearance characteristics. The performance of the recognition and pose estimation algorithms is studied using over a thousand input images of sample objects. Sensitivity of recognition to the number of eigenspace dimensions and the number of learning samples is analyzed. For the objects used, appearance representation in eigenspaces with less than 20 dimensions produces accurate recognition results with an average pose estimation error of about 1.0 degree. A near real-time recognition system with 20 complex objects in the database has been developed. The paper is concluded with a discussion on various issues related to the proposed learning and recognition methodology.
2,037 citations
TL;DR: This paper addresses the problem of retrieving images from large image databases with a method based on local grayvalue invariants which are computed at automatically detected interest points and allows for efficient retrieval from a database of more than 1,000 images.
Abstract: This paper addresses the problem of retrieving images from large image databases. The method is based on local grayvalue invariants which are computed at automatically detected interest points. A voting algorithm and semilocal constraints make retrieval possible. Indexing allows for efficient retrieval from a database of more than 1,000 images. Experimental results show correct retrieval in the case of partial visibility, similarity transformations, extraneous features, and small perspective deformations.
1,756 citations
"Object recognition from local scale..." refers background or methods in this paper
...This allows for the use of more distinctive image descriptors than the rotation-invariant ones used by Schmid and Mohr, and the descriptor is further modified to improve its stability to changes in affine projection and illumination....
[...]
...For the object recognition problem, Schmid & Mohr [19] also used the Harris corner detector to identify interest points, and then created a local image descriptor at each interest point from an orientation-invariant vector of derivative-of-Gaussian image measurements....
[...]
..., Schmid & Mohr [19]) has shown that efficient recognition can often be achieved by using local image descriptors sampled at a large number of repeatable locations....
[...]
...However, recent research on the use of dense local features (e.g., Schmid & Mohr [19]) has shown that efficient recognition can often be achieved by using local image descriptors sampled at a large number of repeatable locations....
[...]
TL;DR: A robust approach to image matching by exploiting the only available geometric constraint, namely, the epipolar constraint, is proposed and a new strategy for updating matches is developed, which only selects those matches having both high matching support and low matching ambiguity.
1,574 citations
"Object recognition from local scale..." refers methods in this paper
...[23] used the Harris corner detector to identify feature locations for epipolar alignment of images taken from differing viewpoints....
[...]