scispace - formally typeset
Search or ask a question
Author

Mahzad Kalantari

Bio: Mahzad Kalantari is an academic researcher from Institut de Recherche en Communications et Cybernétique de Nantes. The author has contributed to research in topics: Solver & Translation (geometry). The author has an hindex of 6, co-authored 15 publications receiving 167 citations. Previous affiliations of Mahzad Kalantari include Institut géographique national & University of Nantes.

Papers
More filters
Journal ArticleDOI
TL;DR: The elements necessary to build a specific algebraic solver are given in this paper, allowing for a real-time implementation and the results on real and synthetic data show the efficiency of this method.
Abstract: This paper presents a new method to solve the relative pose between two images, using three pairs of homologous points and the knowledge of the vertical direction. The vertical direction can be determined in two ways: The first requires direct physical measurements such as the ones provided by an IMU (inertial measurement unit). The other uses the automatic extraction of the vanishing point corresponding to the vertical direction in an image. This knowledge of the vertical direction solves two unknowns among the three parameters of the relative rotation, so that only three homologous couples of points are requested to position a couple of images. Rewriting the coplanarity equations thus leads to a much simpler solution. The remaining unknowns resolution is performed by "hiding a variable" approach. The elements necessary to build a specific algebraic solver are given in this paper, allowing for a real-time implementation. The results on real and synthetic data show the efficiency of this method.

67 citations

Journal ArticleDOI
TL;DR: In this article, Kreisen et al. proposed an automated vanishing point detection method based on the theorem of Thales, which uses a RANSAC method modified to improve its speed by using accumulation techniques (Hough transform or otherwise).
Abstract: A new automated approach for vanishing point detection in images of urban scenes is described. This method is based on the theorem of Thales. The main contribution of this paper is the automatic and simultaneous detection of all vanishing points of the image, achieved by converting this problem into the detection of circles in a complex cloud of points, in which each point corresponds to a segment and is associated with an uncertainty. This extraction of circles uses a RANSAC method, modified to improve its speed by using accumulation techniques (Hough transform or otherwise). This robust estimation is then refined by least squares error propagation using the individual variances of each segment. The algorithm is robust, its accuracy is optimised and it is entirely automatic. Its successful operation has been tested on a large number of images of varied urban scenes. Resume Un algorithme entierement automatique de detection de points de fuite dans des images de scenes urbaines est presente. Cette approche s’appuie sur un theoreme classique (theoreme de Thales), qui permet de transformer le probleme de detection des points de fuite a partir de segments et leur incertitude en un probleme de detection de cercles dans un nuage de points (chaque point correspond a un segment, et a chaque point on associe une incertitude). L’extraction de cercles utilise une methode robuste de type RANSAC, modifiee pour etre tres rapide par rapport a des techniques accumulatives (de type Hough ou autres). Cette estimation robuste est ensuite raffinee par une propagation d’incertitude par moindres carres exploitant les variances individuelles de chaque segment. L’algorithme developpe est robuste, sa precision est la meilleure au sens des moindres carres compte tenu des incertitudes associees aux segments detectes, et en outre il est entierement automatique. Son bon fonctionnement a ete teste sur un grand nombre d’images representant des paysages urbains varies. Zusammenfassung Es wird ein neuer, automatisierter Ansatz zur Bestimmung von Fluchtpunkten in Bildern urbaner Szenen vorgestellt. Die Methode basiert auf dem Satz des Thales. Der wesentliche Beitrag ist die automatische und simultane Detektion aller Fluchtpunkte eines Bildes durch Invertierung dieses Problems in die Aufgabe der Bestimmung von Kreisen in komplexen Punktwolken, in denen jeder Punkt zu einem Segment gehort und mit einer Unsicherheit behaftet ist. Die Extraktion von Kreisen nutzt die RANSAC Methode, die zur Geschwindigkeitssteigerung modifiziert wurde, und sich auf Akkumulationstechniken, wie z.B. die Hough Transformation stutzt. Diese robuste Schatzung wird abschliesend durch Fehlerfortpflanzung nach der Methode der Kleinsten Quadrate unter Ausnutzung der individuellen Varianzen jedes Segments verfeinert. Der Algorithmus arbeitet vollautomatisch, ist robust und die Genauigkeit ist optimiert. Die erfolgreiche Anwendung wurde an einer grosen Anzahl Bildern verschiedenster Stadtszenen getestet. Resumen Este articulo describe un procedimiento completamente automatico para la deteccion de puntos de fuga en imagenes de escenas urbanas. El principio se apoya en un teorema clasico (el teorema de Tales) que permite transformar el problema de la deteccion de los puntos de fuga a partir de segmentos y de su incertidumbre, en un problema de deteccion de circulos dentro de una nube de puntos en la que cada punto corresponde a un segmento y a cada punto se le asocia una incertidumbre. La extraccion de circulos utiliza un metodo robusto tipo RANSAC modificado para mejorar su velocidad comparado con tecnicas de acumulacion del tipo transformada de Hough u otras. Esta estimacion robusta se refina posteriormente mediante propagacion del error por minimos cuadrados utilizando las varianzas individuales de cada segmento. El algoritmo desarrollado es robusto, su precision es la mejor en el sentido de minimos cuadrados teniendo en cuenta las incertidumbres asociadas a los segmentos detectados y, ademas, es completamente automatico. Su buen funcionamiento se ha evaluado procesando muchas imagenes de escenas urbanas variadas.

25 citations

Book ChapterDOI
09 Jan 2009
TL;DR: The methodology presented does not mix the rotation and translation parameters, which results in correct behavior and accuracy for situations otherwise known as quite unfavorable, such as planar scenes, or panoramic sets of images (with a null base length).
Abstract: The goal of this paper is to estimate directly the rotation and translation between two stereoscopic images with the help of five homologous points. The methodology presented does not mix the rotation and translation parameters, which is comparably an important advantage over the methods using the well-known essential matrix. This results in correct behavior and accuracy for situations otherwise known as quite unfavorable, such as planar scenes, or panoramic sets of images (with a null base length), while providing quite comparable results for more "standard" cases. The resolution of the algebraic polynomials resulting from the modeling of the coplanarity constraint is made with the help of powerful algebraic solver tools (the Grobner bases and the Rational Univariate Representation).

21 citations

01 Jan 2008
TL;DR: A simple and robust geometry embedded into a larger frame of image work starting with an efficient vanishing point extraction without any prior information about the scene and any knowledge of intrinsic parameters of the optics used is proposed.
Abstract: This paper deals with the retrieval of vanishing points in uncalibrated images. Many authors did work on that subject in the computer vision field because the vanishing point represents a major information. In our case, starting with this information gives the orientation of the images at the time of the acquisition or the classification of the different directions of parallel lines from an unique view. The goal of this paper is to propose a simple and robust geometry embedded into a larger frame of image work starting with an efficient vanishing point extraction without any prior information about the scene and any knowledge of intrinsic parameters of the optics used.After this fully automatic classification of all segments belonging to the same vanishing point, the error analysis of the vanishing points found gives the covariance matrix on the vanishing point and on the orientation angles of the camera, when using the fact that the 3D directions of lines corresponding to the vanishing points are horizontal or vertical. A validation of estimated parameters with the help of the photo-theodolite has been experimented that demonstrate the interest of the method for real case. The algorithm has been tested on the database of a set of 100 images available on line.

14 citations

01 Jan 2007
TL;DR: A simple and cheap tool has been developed for measuring shards of old ceramics, found in archaeological yards, based on a digital camera, and various photogrammetric and computer vision freeware completed by home-made software developments.
Abstract: A simple and cheap tool has been developed for measuring shards of old ceramics, found in archaeological yards. It is based on a digital camera, and various photogrammetric and computer vision freeware completed by home-made software developments. The paper presents the equipment used for the acquisition of the images, and the processing software for the various steps. This software is mainly based on algorithms originating from computer vision community, and from more classical photogrammetry. Some intermediate results are presented, the final output of the present work being a very dense cloud of points describing the geometry of the surface of the shard, that may be post processed by many off-the-shelf drawing commercial software, depending on the needs of the archaeologists.

12 citations


Cited by
More filters
Proceedings ArticleDOI
01 Jan 2011
TL;DR: A novel framework for combining the merits of inertial and visual data from a monocular camera to accumulate estimates of local motion incrementally and reliably reconstruct the trajectory traversed is presented.
Abstract: The increasing demand for real-time high-precision Visual Odometry systems as part of navigation and localization tasks has recently been driving research towards more versatile and scalable solutions. In this paper, we present a novel framework for combining the merits of inertial and visual data from a monocular camera to accumulate estimates of local motion incrementally and reliably reconstruct the trajectory traversed. We demonstrate the robustness and efficiency of our methodology in a scenario with challenging camera dynamics, and present a comprehensive evaluation against ground-truth data.

199 citations

Journal ArticleDOI
18 May 2009-Sensors
TL;DR: The goal is to establish the suitability of the SIFT technique for automatic tie point extraction and approximate DSM (Digital Surface Model) generation, and to develop an auto- Adaptive SIFT operator, which has been validated on several aerial images, with particular attention to large scale aerial images acquired using mini-UAV systems.
Abstract: In the photogrammetry field, interest in region detectors, which are widely used in Computer Vision, is quickly increasing due to the availability of new techniques. Images acquired by Mobile Mapping Technology, Oblique Photogrammetric Cameras or Unmanned Aerial Vehicles do not observe normal acquisition conditions. Feature extraction and matching techniques, which are traditionally used in photogrammetry, are usually inefficient for these applications as they are unable to provide reliable results under extreme geometrical conditions (convergent taking geometry, strong affine transformations, etc.) and for bad-textured images. A performance analysis of the SIFT technique in aerial and close-range photogrammetric applications is presented in this paper. The goal is to establish the suitability of the SIFT technique for automatic tie point extraction and approximate DSM (Digital Surface Model) generation. First, the performances of the SIFT operator have been compared with those provided by feature extraction and matching techniques used in photogrammetry. All these techniques have been implemented by the authors and validated on aerial and terrestrial images. Moreover, an auto-adaptive version of the SIFT operator has been developed, in order to improve the performances of the SIFT detector in relation to the texture of the images. The Auto-Adaptive SIFT operator (A2 SIFT) has been validated on several aerial images, with particular attention to large scale aerial images acquired using mini-UAV systems.

150 citations

Book ChapterDOI
05 Sep 2010
TL;DR: A novel minimal case solution to the calibrated relative pose problem using 3 point correspondences for the case of two known orientation angles is presented and it is shown that the new 3-point algorithm can cope with planes and even collinear points.
Abstract: It this paper we present a novel minimal case solution to the calibrated relative pose problemusing 3 point correspondences for the case of two known orientation angles. This case is relevant when a camera is coupled with an inertial measurement unit (IMU) and it recently gained importance with the omnipresence of Smartphones (iPhone, Nokia N900) that are equippedwith accelerometers tomeasure the gravity normal. Similar to the 5-point (6-point), 7-point, and 8-point algorithm for computing the essential matrix in the unconstrained case, we derive a 3-point, 4-point and, 5-point algorithm for the special case of two known orientation angles. We investigate degenerate conditions and show that the new 3-point algorithm can cope with planes and even collinear points. We will show a detailed analysis and comparison on synthetic data and present results on cell phone images. As an additional application we demonstrate the algorithm on relative pose estimation for a micro aerial vehicle's (MAV) camera-IMU system.

137 citations

Book ChapterDOI
08 Nov 2010
TL;DR: New simple closed-form solutions to two minimal absolute pose problems for the case of known vertical direction, which result in solving one polynomial equation of degree two in one variable and one, respectively two, systems of linear equations and can be efficiently solved in a closed- form.
Abstract: In this paper we provide new simple closed-form solutions to two minimal absolute pose problems for the case of known vertical direction In the first problem we estimate absolute pose of a calibrated camera from two 2D-3D correspondences and a given vertical direction In the second problem we assume camera with unknown focal length and radial distortion and estimate its pose together with the focal length and the radial distortion from three 2D-3D correspondences and a given vertical direction The vertical direction can be obtained either by direct physical measurement by, eg, gyroscopes and inertial measurement units or from vanishing points constructed in images Both our problems result in solving one polynomial equation of degree two in one variable and one, respectively two, systems of linear equations and can be efficiently solved in a closed-form By evaluating our algorithms on synthetic and real data we demonstrate that both our solutions are fast, efficient and numerically stabled

109 citations

Book ChapterDOI
07 Oct 2012
TL;DR: This paper presents a new epipolar constraint for computing the rotation between two images independently of the translation, and shows for the first time how the constraint on the rotation has the advantage of remaining exact even in the case of translations converging to zero.
Abstract: In this paper, we present a new epipolar constraint for computing the rotation between two images independently of the translation. Against the common belief in the field of geometric vision that it is not possible to find one independently of the other, we show how this can be achieved by relatively simple two-view constraints. We use the fact that translation and rotation cause fundamentally different flow fields on the unit sphere centered around the camera. This allows to establish independent constraints on translation and rotation, and the latter is solved using the Grobner basis method. The rotation computation is completed by a solution to the cheiriality problem that depends neither on translation, nor on feature triangulations. Notably, we show for the first time how the constraint on the rotation has the advantage of remaining exact even in the case of translations converging to zero. We use this fact in order to remove the error caused by model selection via a non-linear optimization of rotation hypotheses. We show that our method operates in real-time and compare it to a standard existing approach in terms of both speed and accuracy.

96 citations