Generic Corner Research Articles

Improved feature point extraction and mismatch eliminating algorithm

ABSTRACT For the existing image matching algorithms, some inherent shortcomings, such as high mismatch rate and low computational efficiency, give rise to a bad influence on the performance of Visual Simultaneous Localization and Mapping (VSLAM). In this paper, a Grid-Based Motion Statistics for Fast and Random Sample Consensus (GMS-RANSAC) method combining with Multi-Probe Location Sensitive Hash (LSH)-based Adaptive and Generic Corner Detection Based on the Accelerated Segment Test and Oriented FAST and Rotated BRIEF (AGAST-ORB) algorithm is proposed to improve the real time and accuracy of image matching. To this end, the AGAST algorithm and the multi-probe LSH algorithm are firstly integrated into the traditional ORB algorithm to obtain the initial matching set. Specifically, the image feature points are extracted by the AGAST algorithm and then the main direction of feature points is given according to the intensity centroid method to guarantee the rotary invariant of feature points. Based on the extracted feature points, the multi-probe LSH algorithm, benefiting from its high time efficiency, is used to generate the initial matching pairs. In what follows, a GMS-RANSAC algorithm, which is improved by adding a directional similarity constraint model and the traditional RANSAC algorithm, is performed to improve the accuracy of eliminating result further. Finally, the performance test is implemented via a Mikolajczyk standard data set and it is verified that the proposed algorithm has higher matching precision and matching efficiency than traditional image matching algorithms.

An Efficient and Geometric-Distortion-Free Binary Robust Local Feature.

An efficient and geometric-distortion-free approach, namely the fast binary robust local feature (FBRLF), is proposed. The FBRLF searches the stable features from an image with the proposed multiscale adaptive and generic corner detection based on the accelerated segment test (MAGAST) to yield an optimum threshold value based on adaptive and generic corner detection based on the accelerated segment test (AGAST). To overcome the problem of image noise, the Gaussian template is applied, which is efficiently boosted by the adoption of an integral image. The feature matching is conducted by incorporating the voting mechanism and lookup table method to achieve a high accuracy with low computational complexity. The experimental results clearly demonstrate the superiority of the proposed method compared with the former schemes regarding local stable feature performance and processing efficiency.

Building Corner Detection in Aerial Images with Fully Convolutional Networks.

In aerial images, corner points can be detected to describe the structural information of buildings for city modeling, geo-localization, and so on. For this specific vision task, the existing generic corner detectors perform poorly, as they are incapable of distinguishing corner points on buildings from those on other objects such as trees and shadows. Recently, fully convolutional networks (FCNs) have been developed for semantic image segmentation that are able to recognize a designated kind of object through a training process with a manually labeled dataset. Motivated by this achievement, an FCN-based approach is proposed in the present work to detect building corners in aerial images. First, a DeepLab model comprised of improved FCNs and fully-connected conditional random fields (CRFs) is trained end-to-end for building region segmentation. The segmentation is then further improved by using a morphological opening operation to increase its accuracy. Corner points are finally detected on the contour curves of building regions by using a scale-space detector. Experimental results show that the proposed building corner detection approach achieves an F-measure of 0.83 in the test image set and outperforms a number of state-of-the-art corner detectors by a large margin.

Formal Theory of Cornered Asymptotically Hyperbolic Einstein Metrics

This paper makes a formal study of asymptotically hyperbolic Einstein metrics given, as conformal infinity, a conformal manifold with boundary. The space on which such an Einstein metric exists thus has a finite boundary in addition to the usual infinite boundary and a corner where the two meet. On the finite boundary, a constant mean curvature umbilic condition is imposed. First, recent work of Nozaki, Takayanagi, and Ugajin is generalized and extended showing that such metrics cannot have smooth compactifications for generic corners embedded in the infinite boundary. A model linear problem is then studied: a formal expansion at the corner is derived for eigenfunctions of the scalar Laplacian subject to certain boundary conditions. In doing so, scalar ODEs are studied that are of relevance for a broader class of boundary value problems and also for the Einstein problem. Next, unique formal existence at the corner, up to order at least equal to the boundary dimension, of Einstein metrics in a cornered asymptotically hyperbolic normal form which are polyhomogeneous in polar coordinates is demonstrated for arbitrary smooth conformal infinity. Finally it is shown that, in the special case that the finite boundary is taken to be totally geodesic, there is an obstruction to existence beyond this order, which defines a conformal hypersurface invariant.

A novel Gravity-FREAK feature extraction and Gravity-KLT tracking registration algorithm based on iPhone MEMS mobile sensor in mobile environment.

Based on the traditional Fast Retina Keypoint (FREAK) feature description algorithm, this paper proposed a Gravity-FREAK feature description algorithm based on Micro-electromechanical Systems (MEMS) sensor to overcome the limited computing performance and memory resources of mobile devices and further improve the reality interaction experience of clients through digital information added to the real world by augmented reality technology. The algorithm takes the gravity projection vector corresponding to the feature point as its feature orientation, which saved the time of calculating the neighborhood gray gradient of each feature point, reduced the cost of calculation and improved the accuracy of feature extraction. In the case of registration method of matching and tracking natural features, the adaptive and generic corner detection based on the Gravity-FREAK matching purification algorithm was used to eliminate abnormal matches, and Gravity Kaneda-Lucas Tracking (KLT) algorithm based on MEMS sensor can be used for the tracking registration of the targets and robustness improvement of tracking registration algorithm under mobile environment.

Condition R and holomorphic mappings of domains with generic corners

A piecewise smooth domain is said to have generic corners if the corners are generic CR manifolds. It is shown that a biholomorphic mapping from a piecewise smooth pseudoconvex domain with generic corners in complex Euclidean space that satisfies Condition R to another domain extends as a smooth diffeomorphism of the respective closures if and only if the target domain is also piecewise smooth with generic corners and satisfies Condition R. Further it is shown that a proper map from a domain with generic corners satisfying Condition R to a product domain of the same dimension extends continuously to the closure of the source domain in such a way that the extension is smooth on the smooth part of the boundary. In particular, the existence of such a proper mapping forces the smooth part of the boundary of the source to be Levi degenerate.

Bilateral arcs using “averaged beam's eye views”: A simplified technique for delivering 3-D based conformal radiotherapy

The purpose of this study is to describe a conformal radiotherapy technique for treating only the prostate with bilateral 120° arcs using “averaged beams-eye-views” (A-BEV). For this study a CT scan from a patient with a large prostate but with a low risk for seminal vesicle involvement was chosen for comparing several different treatment techniques. Dose volume histograms (DVHs) of the prostate, femoral heads, bladder, and rectum were compared for plans using “standard” bilateral 120 degree unblocked arcs (8 × 8 and 9 × 9 cm), similar sized arcs with “generic” (small corner) blocks applied, arcs using hand drawn “semi-conformal” blocks added, and arcs using the A-BEV. The A-BEV was generated by averaging the shapes of fixed lateral and oblique BEVs from a six-field plan. These arc techniques were compared to four-field conformal (4-FC) and six-field conformal (6-FC) techniques. The addition of generic corner blocks to a 9 × 9 field resulted in a more favorable dose distribution than using open unblocked 9 × 9 arcs. The technique employing the A-BEV resulted in an improvement in the DVHs compared to other arc techniques and to 4-FC techniques. The dose volume histograms associated with using this technique approached those associated with using a 6-FC technique. Treating only the prostate with blocked arcs generated using an A-BEV results in an improved dose distribution compared to unblocked arcs and 4-FC techniques. This blocked arc technique also results in a DVH that is comparable to using a more complex 6-FC technique. Blocks that are drawn on manually reduce the dose to the surrounding normal tissues but are associated with a greater risk of underdosing the target volume. This problem is diminished when computer generated conformal blocks are used.

Holomorphic Mappings of Domains with Generic Corners

Holomorphic Mappings of Domains with Generic Corners

Holomorphic mappings of domains with generic corners

The boundary behavior of a biholomorphic mapping f f between two domains with real analytic, generic, nondegenerate corners in C n {{\mathbf {C}}^n} is considered. Under certain minimal regularity assumptions on f f it is shown that f f continues holomorphically past the boundary.