scispace - formally typeset
Search or ask a question
Author

Franck Jung

Bio: Franck Jung is an academic researcher from Institut géographique national. The author has contributed to research in topics: Solver & Vanishing point. The author has an hindex of 9, co-authored 19 publications receiving 252 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: To isolate new construction and buildings, which disappear, an algorithm that works in two steps by eliminating a large part of the scene without losing any actual changes by comparing a Digital Elevation Model for the two dates.
Abstract: Our goal is to detect changes in an aerial scene by comparing grey scale stereopairs taken several years apart in order to update a geographic database. A set of image locations that have a high likelihood to contain changes will be submitted to a human operator who will either reject the proposed change or validate it and update the database accordingly. We are mainly interested in changes in buildings. To isolate new construction and buildings, which disappear, we provide an algorithm that works in two steps. First, during a focusing phase, we eliminate a large part of the scene without losing any actual changes by comparing a Digital Elevation Model (DEM) for the two dates. Second, we classify the resulting regions of interest (ROI) based on four images—stereopairs of the area at the two dates. To decide whether or not the ROI contains a change, we classify each of the four images as “building” or “no-building”. This classifier is a combination of several decision trees induced from training data. Each node of each decision tree is identified with a graph of features which is more likely to occur on buildings than background. Finally, the classification results at the two different dates are compared. The final set of locations submitted to an operator omits less than 10% of the true changes. The false positive rate represents less than 5% of the scene surface.

73 citations

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


Cited by
More filters
Journal ArticleDOI
TL;DR: An exact and parameter-free algorithm to build scale-sets image descriptions whose sections constitute a monotone sequence of upward global minima of a multi-scale energy, which is called the “scale climbing” algorithm is introduced.
Abstract: This paper introduces a multi-scale theory of piecewise image modelling, called the scale-sets theory, and which can be regarded as a region-oriented scale-space theory The first part of the paper studies the general structure of a geometrically unbiased region-oriented multi-scale image description and introduces the scale-sets representation, a representation which allows to handle such a description exactly The second part of the paper deals with the way scale-sets image analyses can be built according to an energy minimization principle We consider a rather general formulation of the partitioning problem which involves minimizing a two-term-based energy, of the form � C + D, where D is a goodness-of-fit term and C is a regularization term We describe the way such energies arise from basic principles of approximate modelling and we relate them to operational rate/distorsion problems involved in lossy compression problems We then show that an important subset of these energies constitutes a class of multi-scale energies in that the minimal cut of a hierarchy gets coarser and coarser as parameter � increases This allows us to devise a fast dynamic-programming procedure to find the complete scale-sets representation of this family of minimal cuts Considering then the construction of the hierarchy from which the minimal cuts are extracted, we end up with an exact and parameter-free algorithm to build scale-sets image descriptions whose sections constitute a monotone sequence of upward global minima of a multi-scale energy, which is called the "scale climbing" algorithm This algorithm can be viewed as a continuation method along the scale dimension or as a minimum pursuit along the operational rate/distorsion curve Furthermore, the solution verifies a linear scale invariance property which allows to completely postpone the tuning of the scale parameter to a subsequent stage For computational reasons, the scale climbing algorithm is approximated by a pair-wise region merging scheme: however the principal properties of the solutions are kept Some results obtained with Mumford-Shah's piece-wise constant model and a variant are provided and different applications of the proposed multi-scale analyses are finally sketched

238 citations

Journal ArticleDOI
TL;DR: This paper proposes a change detection method based on stereo imagery and digital surface models generated with stereo matching methodology and provides a solution by the joint use of height changes and Kullback-Leibler divergence similarity measure between the original images.
Abstract: Building change detection is a major issue for urban area monitoring. Due to different imaging conditions and sensor parameters, 2-D information delivered by satellite images from different dates is often not sufficient when dealing with building changes. Moreover, due to the similar spectral characteristics, it is often difficult to distinguish buildings from other man-made constructions, like roads and bridges, during the change detection procedure. Therefore, stereo imagery is of importance to provide the height component which is very helpful in analyzing 3-D building changes. In this paper, we propose a change detection method based on stereo imagery and digital surface models (DSMs) generated with stereo matching methodology and provide a solution by the joint use of height changes and Kullback-Leibler divergence similarity measure between the original images. The Dempster-Shafer fusion theory is adopted to combine these two change indicators to improve the accuracy. In addition, vegetation and shadow classifications are used as no-building change indicators for refining the change detection results. In the end, an object-based building extraction method based on shape features is performed. For evaluation purpose, the proposed method is applied in two test areas, one is in an industrial area in Korea with stereo imagery from the same sensor and the other represents a dense urban area in Germany using stereo imagery from different sensors with different resolutions. Our experimental results confirm the efficiency and high accuracy of the proposed methodology even for different kinds and combinations of stereo images and consequently different DSM qualities.

202 citations

Journal ArticleDOI
TL;DR: This paper reviews the recent developments and applications of 3D CD using remote sensing and close-range data, in support of both academia and industry researchers who seek for solutions in detecting and analyzing 3D dynamics of various objects of interest.
Abstract: Due to the unprecedented technology development of sensors, platforms and algorithms for 3D data acquisition and generation, 3D spaceborne, airborne and close-range data, in the form of image based, Light Detection and Ranging (LiDAR) based point clouds, Digital Elevation Models (DEM) and 3D city models, become more accessible than ever before Change detection (CD) or time-series data analysis in 3D has gained great attention due to its capability of providing volumetric dynamics to facilitate more applications and provide more accurate results The state-of-the-art CD reviews aim to provide a comprehensive synthesis and to simplify the taxonomy of the traditional remote sensing CD techniques, which mainly sit within the boundary of 2D image/spectrum analysis, largely ignoring the particularities of 3D aspects of the data The inclusion of 3D data for change detection (termed 3D CD), not only provides a source with different modality for analysis, but also transcends the border of traditional top-view 2D pixel/object-based analysis to highly detailed, oblique view or voxel-based geometric analysis This paper reviews the recent developments and applications of 3D CD using remote sensing and close-range data, in support of both academia and industry researchers who seek for solutions in detecting and analyzing 3D dynamics of various objects of interest We first describe the general considerations of 3D CD problems in different processing stages and identify CD types based on the information used, being the geometric comparison and geometric-spectral analysis We then summarize relevant works and practices in urban, environment, ecology and civil applications, etc Given the broad spectrum of applications and different types of 3D data, we discuss important issues in 3D CD methods Finally, we present concluding remarks in algorithmic aspects of 3D CD

200 citations

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

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