Scale invariant feature matching with wide angle images

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014

In this paper we propose a new approach to compute the scale space of any central projection system, such as catadioptric, fisheye or conventional cameras. Since these systems can be explained using a unified model, the single parameter that defines each type of system is used to automatically compute the corresponding Riemannian metric. This metric, is combined with the partial differential equations framework on manifolds, allows us to compute the Laplace-Beltrami (LB) operator, enabling the computation of the scale space of any central projection system. Scale space is essential for the intrinsic scale selection and neighborhood description in features like SIFT. We perform experiments with synthetic and real images to validate the generalization of our approach to any central projection system. We compare our approach with the best-existing methods showing competitive results in all type of cameras: catadioptric, fisheye, and perspective.

IEEE Transactions on Robotics, 2012

Keypoint detection and matching is of fundamental importance for many applications in computer and robot vision. The association of points across different views is problematic because image features can undergo significant changes in appearance. Unfortunately, state-of-the-art methods, like the scale-invariant feature transform (SIFT), are not resilient to the radial distortion that often arises in images acquired by cameras with microlenses and/or wide field-of-view. This paper proposes modifications to the SIFT algorithm that substantially improve the repeatability of detection and effectiveness of matching under radial distortion, while preserving the original invariance to scale and rotation. The scale-space representation of the image is obtained using adaptive filtering that compensates the local distortion, and the keypoint description is carried after implicit image gradient correction. Unlike competing methods, our approach avoids image resampling (the processing is carried out in the original image plane), it does not require accurate camera calibration (an approximate modeling of the distortion is sufficient), and it adds minimal computational overhead. Extensive experiments show the advantages of our method in establishing point correspondence across images with radial distortion.

We propose the -dimensional scale invariant feature transform ( -SIFT) method for extracting and matching salient features from scalar images of arbitrary dimensionality, and compare this method's performance to other related features. The proposed features extend the concepts used for 2-D scalar images in the computer vision SIFT technique for extracting and matching distinctive scale invariant features. We apply the features to images of arbitrary dimensionality through the use of hyperspherical coordinates for gradients and multidimensional histograms to create the feature vectors. We analyze the performance of a fully automated multimodal medical image matching technique based on these features, and successfully apply the technique to determine accurate feature point correspondence between pairs of 3-D MRI images and dynamic CT data.

Image Processing, IEEE …, 2009

We present a fully automated multimodal medical image matching technique. Our method extends the concepts used in the computer vision SIFT technique for extracting and matching distinctive scale invariant features in 2D scalar images to scalar images of arbitrary dimensionality. This extension involves using hyperspherical coordinates for gradients and multidimensional histograms to create the feature vectors. These features were successfully applied to determine accurate feature point correspondence between pairs of medical images (3D) and dynamic volumetric data (3D+time).

This paper proposes a novel approach of line matching across images captured by different types of cameras, from perspective to omnidirectional ones. Based on the spherical mapping, this method utilizes spherical SIFT point features to boost line matching and searches line correspondences using an affine invariant measure of similarity. It permits to unify the commonest cameras and to process heterogeneous images with the least distortion of visual information.

International Journal of Machine Learning and Computing, 2012

Image registration can find similarities between one image and another one from the same scene taken by different angles. Registration is widely used in robot localization, remote sensing, medical imaging and etc. In this paper, a new method based on the image geometrical features has introduced by using two important characteristics of image scale and image rotation. Feature points of two images by SIFT algorithm has extracted. Then, an initial matching is estimated based on descriptor matrix of SIFT features with nearest neighbor (NN) criterion. The novel geometrical method is used for discarding incorrect matched points. Finally, the correct image is recognized by the number of matched points.

International Journal of Computer Vision, 2004

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.

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images, 2010

This paper presents a novel methodology to perform consistent matching between visual features of a pair of images, particularly in the case of point-of-view changes between shots. Traditionally, such correspondences are determined by computing the similarity between descriptor vectors associated with each point which are obtained by invariant descriptors. Our methodology first obtains a coarse global registration among images, which constrains the correspondence space. Then, it analyzes the similarity among descriptors, thus reducing both the number and the severity of mismatches. The approach is sufficiently generic to be used with many feature descriptor methods. We present several experimental results that show significant increase both in accuracy and the number of successful matches.

2007

Abstract This document describes the implementation of several features previously developed [2], extending the 2D scale invariant feature transform (SIFT)[4, 5] for images of arbitrary dimensionality, such as 3D medical image volumes and time series, using ITK 1. Specifically, we provide a scale invariant implementation of a weighted histogram of gradient feature, a rotationally invariant version of the histogram feature, and a SIFT-like feature, adapted to handle images of arbitrary dimensionality.

2005

This paper describes a novel multi-view matching framework based on a new type of invariant feature. Our features are located at Harris corners in discrete scale-space and oriented using a blurred local gradient. This defines a rotationally invariant frame in which we sample a feature descriptor, which consists of an 8 × 8 patch of bias/gain normalised intensity values. The density of features in the image is controlled using a novel adaptive non-maximal suppression algorithm, which gives a better spatial distribution of features than previous approaches. Matching is achieved using a fast nearest neighbour algorithm that indexes features based on their low frequency Haar wavelet coefficients. We also introduce a novel outlier rejection procedure that verifies a pairwise feature match based on a background distribution of incorrect feature matches. Feature matches are refined using RANSAC and used in an automatic 2D panorama stitcher that has been extensively tested on hundreds of sample inputs.

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.

2016

People are paying more attention to the use of Spherical Panorama Images (SPIs) for many applications. In order to apply SPIs in photogrammetric application such as land mapping or navigation like frame images do, conjugate points matching and the relative relationship between SPIs are important issues. Through observing the moving pattern of conjugate points, the relative positions and orientation between camera stations may be solved. In this study, images captured by Ladybug 5 system developed by Point Grey were used for experiment, image features were extracted and matched by Speed-Up Robust Features (SURF) algorithm (Bay, 2008), and the concept of Random Sample Consensus (RANSAC) was applied to improve the accuracy of conjugate points matching. Although RANSAC general model is not well enough to detect the features on SPIs, we proposed a method using Essential Matrix model to improve this deficiency. Once the conjugate points are found, the relationship between image stations c...

2011 International Conference on Computer Vision, 2011

In this paper we propose a new approach to compute the scale space of any omnidirectional image acquired with a central catadioptric system. When these cameras are central they are explained using the sphere camera model, which unifies in a single model, conventional, paracatadioptric and hypercatadioptric systems. Scale space is essential in the detection and matching of interest points, in particular scale invariant points based on Laplacian of Gaussians, like the well known SIFT. We combine the sphere camera model and the partial differential equations framework on manifolds, to compute the Laplace-Beltrami (LB) operator which is a second order differential operator required to perform the Gaussian smoothing on catadioptric images. We perform experiments with synthetic and real images to validate the generalization of our approach to any central catadioptric system.

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2009

In the recent past, the recognition and localization of objects based on local point features has become a widely accepted and utilized method. Among the most popular features are currently the SIFT features, the more recent SURF features, and region-based features such as the MSER. For time-critical application of object recognition and localization systems operating on such features, the SIFT features are too slow (500-600 ms for images of size 640×480 on a 3 GHz CPU). The faster SURF achieve a computation time of 150-240 ms, which is still too slow for active tracking of objects or visual servoing applications. In this paper, we present a combination of the Harris corner detector and the SIFT descriptor, which computes features with a high repeatability and very good matching properties within approx. 20 ms. While just computing the SIFT descriptors for computed Harris interest points would lead to an approach that is not scaleinvariant, we will show how scale-invariance can be achieved without a time-consuming scale space analysis. Furthermore, we will present results of successful application of the proposed features within our system for recognition and localization of textured objects. An extensive experimental evaluation proves the practical applicability of our approach.

2005

This paper presents a new method for feature matching between pairs of one-dimensional panoramic images for use in navigation and localization by a mobile robot equipped with an omnidirectional camera. We extract locally scaleinvariant feature points from the scale space of such images, and collect color information and shape properties of the scale-space surface in a feature descriptor. We define a matching cost based on these descriptors, and present a novel dynamic programming method to establish globally optimal feature correspondences between images taken by a moving robot. Our method can handle arbitrary rotations and large numbers of missing features. It is also robust to significant changes in lighting conditions and viewing angle, and in the presence of some occlusion.