Gradient operators for feature extraction from omnidirectional panoramic images

doi:10.1016/J.PATREC.2014.12.010

Home
/
Papers
/
Gradient operators for feature extraction from omnidirectional panoramic images

Journal Article•DOI•

Gradient operators for feature extraction from omnidirectional panoramic images

Kenji Hara¹, Kohei Inoue¹, Kiichi Urahama¹•Institutions (1)

Kyushu University¹

01 Mar 2015-Pattern Recognition Letters (North-Holland)-Vol. 54, pp 89-96

TL;DR: An extension of the Laplacian operator and the class of differential corner detectors for omnidirectional panoramic images covering 360° views is proposed that solves two problems of nonuniformity of spatial resolution and spherical polar coordinates singularity.

read less

About: This article is published in Pattern Recognition Letters.The article was published on 2015-03-01. It has received 15 citations till now. The article focuses on the topics: Laplace operator & Spherical coordinate system.

...read moreread less

Citations

PDF

Open Access

More filters

Journal Article•DOI•

Quaternion-Michelson Descriptor for Color Image Classification

[...]

Rushi Lan¹, Yicong Zhou¹•Institutions (1)

University of Macau¹

01 Nov 2016-IEEE Transactions on Image Processing

TL;DR: A simple yet powerful framework called quaternion-Michelson descriptor (QMD) to extract local features for color image classification and proposes two novel quaternionic Michelson contrast binary pattern descriptors from different perspectives.

...read moreread less

Abstract: In this paper, we develop a simple yet powerful framework called quaternion-Michelson descriptor (QMD) to extract local features for color image classification. Unlike traditional local descriptors extracted directly from the original (raw) image space, QMD is derived from the Michelson contrast law and the quaternionic representation (QR) of color images. The Michelson contrast is a stable measurement of image contents from the viewpoint of human perception, while QR is able to handle all the color information of the image holisticly and to preserve the interactions among different color channels. In this way, QMD integrates both the merits of Michelson contrast and QR. Based on the QMD framework, we further propose two novel quaternionic Michelson contrast binary pattern descriptors from different perspectives. Experiments and comparisons on different color image classification databases demonstrate that the proposed framework and descriptors outperform several state-of-the-art methods.

...read moreread less

46 citations

Cites background from "Gradient operators for feature extr..."

...The authors are with the Department of Computer and Information Science, University of Macau, Macau 999078, China (e-mail: rslan2012@gmail.com; yicongzhou@umac.mo)....
[...]

Journal Article•DOI•

Spherepix: A Data Structure for Spherical Image Processing

[...]

Juan David Adarve¹, Robert Mahony¹•Institutions (1)

Australian National University¹

01 Apr 2017

TL;DR: The spherepix data structure is introduced, consisting of a collection of overlapping (near orthogonal) grid patches covering the sphere's surface, and it is claimed that the additional computational cost of data interpolation and data reconciliation is easily compensated by the computational saving and algorithmic simplicity of applying existing image processing subroutines in the grid patches.

...read moreread less

Abstract: This letter introduces the “spherepix” data structure for efficient implementation of low-level image processing operations on spherical images. Efficient implementation of low-level image processing depends heavily on separability of the convolution kernels that form the fundamental building blocks of most algorithms. Due to the curvature of the sphere, it is not possible to place an orthogonal grid pixelation globally on its surface, making direct application of classical separable kernel convolutions impossible. In the spherepix data structure, we propose an alternative approach consisting of a collection of overlapping (near orthogonal) grid patches covering the sphere's surface. Close to the boundaries of patches, we introduce data interpolation between patch grids to ensure information flow between grid patches. After each image processing subroutine, we reconcile data in the overlapping regions to homogenize the global data representation. We claim that the additional computational cost of data interpolation and data reconciliation is easily compensated by the computational saving and algorithmic simplicity of applying existing image processing subroutines in the grid patches. The approach is demonstrated by implementing a SIFT feature point algorithm in spherepix coordinates and comparing precision, recall, and computational cost of the proposed approach to documented modifications of the SIFT algorithm specifically developed for implementation on spherical images.

...read moreread less

12 citations

Cites methods from "Gradient operators for feature extr..."

...This grid has been used for SIFT feature point extraction [9]....
[...]

Journal Article•DOI•

Research and implementation of digital 3D panoramic visual communication technology based on virtual reality

[...]

Guangchao Zhang, Xinyue Kou

27 Apr 2021-International Journal of Communication Systems

TL;DR: The chromaticity calibration of digital camera and projection equipment is used to eliminate the coupling difference between the two and estimate the spectral reflectance of the three‐color channel of the object and separate the specular reflection component and the diffuse reflection component, at the same time correct the color and specular reflectanceOf the object itself, and analyze the influence of reflection on the color of the projection light source.

...read moreread less

8 citations

Cites background from "Gradient operators for feature extr..."

...The images are merged into one to achieve the purpose of image stitching.(21,22) The advantage is that the amount of calculation is small, the accuracy is high, the adaptability is good, and the matching effect is better; the disadvantage is that the feature point detection takes a long time....
[...]

Journal Article•DOI•

Yin-Yang-Zhong grid

[...]

Hiroshi Hayashi¹, Akira Kageyama¹•Institutions (1)

Kobe University¹

15 Jan 2016-Journal of Computational Physics

TL;DR: For numerical simulations inside a sphere, an overset grid system, Yin-Yang-Zhong grid, is proposed, an extension of the Yin- Yang grid, which is widely used in various simulations in spherical shell geometry.

...read moreread less

7 citations

Cites background from "Gradient operators for feature extr..."

...The Yin–Yang grid is now successfully applied in geophysics [17–20], planetary/space physics [21–23], solar physics [24–26], astrophysics [27–30], and image processing [31]....
[...]

Journal Article•DOI•

A triangle mesh-based corner detection algorithm for catadioptric images

[...]

Tran Dang Khoa Phan¹•Institutions (1)

University of Da Nang¹

19 May 2018-The Imaging Science Journal

TL;DR: In this article, the authors proposed a new image corner detection algorithm for catadioptric images, which is an important aspect of many computer vision problems involving catadiopric images.

...read moreread less

Abstract: As with conventional images corner detection is an important aspect of many computer vision problems involving catadioptric images. However, classical image processing algorithms are no longer appr...

...read moreread less

6 citations

Cites background from "Gradient operators for feature extr..."

...A traditional rectangular grid, which subdivides a sphere based on a geographic coordinates (longitude and latitude angles), does not conform to the main criteria for a discrete global grid because the area and shape of cells are not generally similar [19, 22]....
[...]

References

PDF

Open Access

More filters

Proceedings Article•DOI•

A Combined Corner and Edge Detector

[...]

Chris Harris, Mike Stephens

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.

...read moreread less

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.

...read moreread less

13,993 citations

"Gradient operators for feature extr..." refers background in this paper

...Corner detectors are divided into differential (Kitchen and Rosenfeld, 1982; Zuniga and Haralick, 1983; Lindeberg, 1994; Harris and Stephens, 1988) and non-differential (Moravec, 1977; Smith and Brady, 1997) types....
[...]

Journal Article•DOI•

SUSAN—A New Approach to Low Level Image Processing

[...]

Stephen M. Smith¹, J. Michael Brady¹•Institutions (1)

University of Oxford¹

01 May 1997-International Journal of Computer Vision

TL;DR: This paper describes a new approach to low level image processing; in particular, edge and corner detection and structure preserving noise reduction and the resulting methods are accurate, noise resistant and fast.

...read moreread less

Abstract: This paper describes a new approach to low level image processing; in particular, edge and corner detection and structure preserving noise reduction. Non-linear filtering is used to define which parts of the image are closely related to each individual pixel; each pixel has associated with it a local image region which is of similar brightness to that pixel. The new feature detectors are based on the minimization of this local image region, and the noise reduction method uses this region as the smoothing neighbourhood. The resulting methods are accurate, noise resistant and fast. Details of the new feature detectors and of the new noise reduction method are described, along with test results.

...read moreread less

3,669 citations

"Gradient operators for feature extr..." refers background in this paper

...Harris and Stephens, 1988) and non-differential (Moravec, 1977; Smith and Brady, 1997) types....
[...]
...Corner detectors are divided into differential (Kitchen and Rosenfeld, 1982; Zuniga and Haralick, 1983; Lindeberg, 1994; Harris and Stephens, 1988) and non-differential (Moravec, 1977; Smith and Brady, 1997) types....
[...]

Book•

Scale-space theory in computer vision

[...]

Tony Lindeberg

31 Dec 1993

TL;DR: A basic problem when deriving information from measured data, such as images, originates from the fact that objects in the world, and hence image structures, exist as meaningful entities only over measured data.

...read moreread less

Abstract: A basic problem when deriving information from measured data, such as images, originates from the fact that objects in the world, and hence image structures, exist as meaningful entities only over ...

...read moreread less

2,452 citations

"Gradient operators for feature extr..." refers background in this paper

...(12); γ = 1 corresponds to the Kitchen-Rosenfeld corner detector (Kitchen and Rosenfeld, 1982), γ = 0 to the Zuniga-Haralick corner detector (Zuniga and Haralick, 1983), and γ = 3 to the Lindeberg corner detector (Lindeberg, 1994), as mentioned earlier....
[...]
...(12) has the value 1 for the Kitchen-Rosenfeld corner detector (Kitchen and Rosenfeld, 1982), the value 0 for the Zuniga-Haralick corner detector (Zuniga and Haralick, 1983), and the value 3 for the Lindeberg corner detector (Lindeberg, 1994), respectively....
[...]
...Corner detectors are divided into differential (Kitchen and Rosenfeld, 1982; Zuniga and Haralick, 1983; Lindeberg, 1994; Harris and Stephens, 1988) and non-differential (Moravec, 1977; Smith and Brady, 1997) types....
[...]

Proceedings Article•DOI•

Spherical wavelets: efficiently representing functions on the sphere

[...]

Peter Schröder¹, Wim Sweldens²•Institutions (2)

University of South Carolina¹, Katholieke Universiteit Leuven²

15 Sep 1995

TL;DR: This paper shows how biorthogonal wavelets with custom properties can be constructed with the lifting scheme, and gives examples of functions defined on the sphere, and shows how they can be efficiently represented with spherical wavelets.

...read moreread less

Abstract: Wavelets have proven to be powerful bases for use in numerical analysis and signal processing. Their power lies in the fact that they only require a small number of coefficients to represent general functions and large data sets accurately. This allows compression and efficient computations. Classical constructions have been limited to simple domains such as intervals and rectangles. In this paper we present a wavelet construction for scalar functions defined on the sphere. We show how biorthogonal wavelets with custom properties can be constructed with the lifting scheme. The bases are extremely easy to implement and allow fully adaptive subdivisions. We give examples of functions defined on the sphere, such as topographic data, bidirectional reflection distribution functions, and illumination, and show how they can be efficiently represented with spherical wavelets. CR

...read moreread less

766 citations

"Gradient operators for feature extr..." refers background in this paper

...Until now, in order to deal with fully-omnidirectional view images, a few approaches of mapping the omnidirectional data onto a polyhedron that closely approximates the spherical surface was proposed (Li and Hai, 2010; Li, 2013; Schroder and Sweldens, 1995)....
[...]

Proceedings Article•

Towards automatic visual obstacle avoidance

[...]

Hans P. Morevec¹•Institutions (1)

Stanford University¹

22 Aug 1977

TL;DR: This report describes ongoing research on a working system which drives a vehicle through cluttered environments under computer control, guided by images perceived through an onboard television camera.

...read moreread less

Abstract: This report describes ongoing research on a working system which drives a vehicle through cluttered environments under computer control, guided by images perceived through an onboard television camera. The emphasis is on reliable and fast low level visual techniques which determine the existence and location of objects in the world, but do not identify them

...read moreread less

727 citations