Research interests

My publications


Imre E, Knorr S, Ozkalayci B, Topay U, Alatan AA, Sikora T (2007) Towards 3-D scene reconstruction from broadcast video, SIGNAL PROCESSING-IMAGE COMMUNICATION22(2)pp. 108-126 ELSEVIER SCIENCE BV
Mustafa A, Kim H, Imre HE, Hilton A (2014) Initial Disparity Estimation Using Sparse Matching for Wide-Baseline Dense,
Knorr S, Imre E, Oezkalayci B, Alatan AA, Sikora T (2007) A modular scheme for 2D/3D conversion of TV broadcast, THIRD INTERNATIONAL SYMPOSIUM ON 3D DATA PROCESSING, VISUALIZATION, AND TRANSMISSION, PROCEEDINGSpp. 703-710 IEEE COMPUTER SOC
Imre E, Gueduekbay U, Alatan AA (2007) Piecewise-planar 3D reconstruction in rate-distortion sense, 2007 3DTV CONFERENCEpp. 350-353 IEEE
Imre E, Berger M-O (2009) A 3-Component Inverse Depth Parameterization for Particle Filter SLAM, PATTERN RECOGNITION, PROCEEDINGS5748pp. 1-10 SPRINGER-VERLAG BERLIN
Imre E, Alatan AA, Gueduekbay U (2007) Rate-distortion guided piecewise planar 3D scene representation, 2007 IEEE 15TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS, VOLS 1-3pp. 225-228 IEEE
Imre E, Berger M-O, Noury N (2009) Improved Inverse-Depth Parameterization for Monocular Simultaneous Localization and Mapping, ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7pp. 1901-1906 IEEE
Blat J, Evans A, Kim H, Imre H, Polok L, Ila V, Nikolaidis N, Zamcik P, Tefas A, Smrz P, Hilton A, Pitas I (2015) Big Data Analysis for Media Production,Proceedings of the IEEE104(11)pp. 2085-2113 IEEE
A typical high-end film production generates several terabytes of data per day, either as footage from multiple cameras or as background information regarding the set (laser scans, spherical captures, etc). This paper presents solutions to improve the integration, and the understanding of the quality, of the multiple data sources, which are used both to support creative decisions on-set (or near it) and enhance the postproduction process. The main contributions covered in this paper are: a public multisource production dataset made available for research purposes, monitoring and quality assurance of multicamera set-ups, multisource registration, anthropocentric visual analysis for semantic content annotation, acceleration of 3D reconstruction, and integrated 2D-3D web visualization tools. Furthermore, this paper presents a toolset for analysis and visualisation of multi-modal media production datasets which enables onset data quality verification and management, thus significantly reducing the risk and time required in production. Some of the basic techniques used for acceleration, clustering and visualization could be applied to much larger classes of big data problems.
Imre HE, Guillemaut J-Y, Hilton ADM (2010) Moving Camera Registration for Multiple Camera Setups in Dynamic Scenes,Proceedings of the 21st British Machine Vision Conference
Many practical applications require an accurate knowledge of the extrinsic calibration (\ie, pose) of a moving camera. The existing SLAM and structure-from-motion solutions are not robust to scenes with large dynamic objects, and do not fully utilize the available information in the presence of static cameras, a common practical scenario. In this paper, we propose an algorithm that addresses both of these issues for a hybrid static-moving camera setup. The algorithm uses the static cameras to build a sparse 3D model of the scene, with respect to which the pose of the moving camera is estimated at each time instant. The performance of the algorithm is studied through extensive experiments that cover a wide range of applications, and is shown to be satisfactory.
Imre E, Knorr S, Alatan AA, Sikora T (2006) Prioritized sequential 3D reconstruction in video sequences with multiple motions, 2006 IEEE International Conference on Image Processing, ICIP 2006, Proceedingspp. 2969-2972 IEEE
Blat J, Evans A, Agenjo J, Kim H, Imre E, Hilton A, Tefas A, Nikolaidis N, Pitas I, Polok L, Smrz P, Zemcik P (2015) IMPART: BIG MEDIA DATA PROCESSING AND ANALYSIS FOR FILM PRODUCTION, 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) IEEE
Imre E, Alatan A, Knorr S, Sikora T (2006) Prioritized sequential 3D reconstruction in video sequences of dynamic scenes, 2006 IEEE 14th Signal Processing and Communications Applications, Vols 1 and 2pp. 916-919 IEEE
Imre E, Guillemaut J-Y, Hilton A (2011) Calibration of nodal and free-moving cameras in dynamic scenes for post-production,Proceedings - 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2011pp. 260-267 IEEE
In film production, many post-production tasks require the availability of accurate camera calibration information. This paper presents an algorithm for through-the-lens calibration of a moving camera for a common scenario in film production and broadcasting: The camera views a dynamic scene, which is also viewed by a set of static cameras with known calibration. The proposed method involves the construction of a sparse scene model from the static cameras, with respect to which the moving camera is registered, by applying the appropriate perspective-n-point (PnP) solver. In addition to the general motion case, the algorithm can handle the nodal cameras with unknown focal length via a novel P2P algorithm. The approach can identify a subset of static cameras that are more likely to generate a high number of scene-image correspondences, and can robustly deal with dynamic scenes. Our target applications include dense 3D reconstruction, stereoscopic 3D rendering and 3D scene augmentation, through which the success of the algorithm is demonstrated experimentally.
Imre E, Hilton A (2012) Through-the-Lens Synchronisation for Heterogeneous Camera Networks., BMVCpp. 1-11 BMVA Press
Imre E, Alatan AA, Gueduekbay U (2009) Rate-Distortion Efficient Piecewise Planar 3-D Scene Representation From 2-D Images, IEEE TRANSACTIONS ON IMAGE PROCESSING18(3)pp. 483-494 IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Imre E, Hilton A (2014) Covariance estimation for minimal geometry solvers via scaled unscented transformation, Computer Vision and Image Understanding0pp. ---
Imre E, Berger M-O, Noury N (2009) Improved inverse-depth parameterization for monocular simultaneous localization and mapping, Proceedings - IEEE International Conference on Robotics and Automationpp. 381-386
Imre E, Knorr S, Alatan AA, Sikora T (2006) Prioritized sequential 3D reconstruction in video sequences with multiple motions, Proceedings International Conference on Image Processing, Vols 1-7pp. 2969-2972 IEEE
Imre E, Guillemaut JY, Hilton A (2012) Through-the-lens multi-camera synchronisation and frame-drop detection for 3D reconstruction, Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012pp. 395-402
Synchronisation is an essential requirement for multiview 3D reconstruction of dynamic scenes. However, the use of HD cameras and large set-ups put a considerable stress on hardware and cause frame drops, which is usually detected by manually verifying very large amounts of data. This paper improves [9], and extends it with frame-drop detection capability. In order to spot frame-drop events, the algorithm fits a broken line to the frame index correspondences for each camera pair, and then fuses the pair wise drop hypotheses into a consistent, absolute frame-drop estimate. The success and the practical utility of the the improved pipeline is demonstrated through a number of experiments, including 3D reconstruction and free-viewpoint video rendering tasks. © 2012 IEEE.
Mustafa A, Kim H, Imre E, Hilton A (2015) Segmentation based features for wide-baseline multi-view reconstruction,2015 INTERNATIONAL CONFERENCE ON 3D VISIONpp. 282-290 IEEE
Solony M, Imre E, Ila V, Polok L, Kim H, Zemcik P (2015) Fast and accurate refinement method for 3D reconstruction from stereo spherical images, VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings3pp. 575-583
Realistic 3D models of the environment are beneficial in many fields, from natural or man-made structure inspection and volumetric analysis, to movie-making, in particular, special effects integration to natural scenes. Spherical cameras are becoming popular in environment modelling because they capture the full surrounding scene visible from the camera location as a consistent seamless image at once. In this paper, we propose a novel pipeline to obtain fast and accurate 3D reconstructions from spherical images. In order to have a better estimation of the structure, the system integrates a joint camera pose and structure refinement step. This strategy proves to be much faster, yet equally accurate, when compared to the conventional method, registration of a dense point cloud via iterative closest point (ICP). Both methods require an initial estimate for successful convergence. The initial positions of the 3D points are obtained from stereo processing of pair of spherical images with known baseline. The initial positions of the cameras are obtained from a robust wide-baseline matching procedure. The performance and accuracy of the 3D reconstruction pipeline is analysed through extensive tests on several indoor and outdoor datasets.
Imre E, Hilton A (2014) Order Statistics of RANSAC and Their Practical Application, International Journal of Computer Vision
For statistical analysis purposes, RANSAC is usually treated as a Bernoulli process: each hypothesis is a Bernoulli trial with the outcome outlier-free/contaminated; a run is a sequence of such trials. However, this model only covers the special case where all outlier-free hypotheses are equally good, e.g. generated from noise-free data. In this paper, we explore a more general model which obviates the noise-free data assumption: we consider RANSAC a random process returning the best hypothesis, (Formula presented.), among a number of hypotheses drawn from a finite set ((Formula presented.)). We employ the rank of (Formula presented.) within (Formula presented.) for the statistical characterisation of the output, present a closed-form expression for its exact probability mass function, and demonstrate that (Formula presented.)-distribution is a good approximation thereof. This characterisation leads to two novel termination criteria, which indicate the number of iterations to come arbitrarily close to the global minimum in (Formula presented.) with a specified probability. We also establish the conditions defining when a RANSAC process is statistically equivalent to a cascade of shorter RANSAC processes. These conditions justify a RANSAC scheme with dedicated stages to handle the outliers and the noise separately. We demonstrate the validity of the developed theory via Monte-Carlo simulations and real data experiments on a number of common geometry estimation problems. We conclude that a two-stage RANSAC process offers similar performance guarantees at a much lower cost than the equivalent one-stage process, and that a cascaded set-up has a better performance than LO-RANSAC, without the added complexity of a nested RANSAC implementation. © 2014 Springer Science+Business Media New York.
Imre E, Alatan AA, Gueduekbay U (2006) Rate-distortion based piecewise planar 3d scene geometry representation, 2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7pp. 2365-2368 IEEE
Knorr S, Sikora T, Imre E, Alatan AA (2006) A geometric segmentation approach for the 3D reconstruction of dynamic scenes in 2D video sequences, European Signal Processing Conference
In this paper, an algorithm is proposed to solve the multi-frame structure from motion (MFSfM) problem for monocular video sequences with multiple rigid moving objects. The algorithm uses the epipolar criterion to segment feature trajectories belonging to the background scene and each of the independently moving objects. As a large baseline length is essential for the reliability of the epipolar geometry, the geometric robust information criterion is employed for key-frame selection within the sequences. Once the features are segmented, corresponding objects are reconstructed individually using a sequential algorithm that is capable of prioritizing the frame pairs with respect to their reliability and information content. The experimental results on synthetic and real data demonstrate that our approach has the potential to effectively deal with the multi-body MFSfM problem.