Personal image

Radim Tylecek

[rah-dim tee-leh-chek]

PhD, supervisor R.Sara

CMP logo CVUT logo

Center for Machine Perception
Department of Cybernetics
Faculty of Electrical Engineering
Czech Technical University
Karlovo namesti 13, 121-35 Praha 2
Czech republic (EU)
E-mail:  tylecr1@cmp.felk.cvut.cz

I am currently with University of Edinburgh, School of Informatics.

CV: here, Google scholar

My Research


I am interested in Computer Vision. My postgraduate research at the CMP has focused on detection of regular structures and symmetric objects in images, for which we have constructed probabilistic models and employed both stochastic inference methods and machine learning.

I graduated from the Czech Technical University in Biomedical Engineering with my master thesis dealing with image-based reconstruction of 3D surface. We proposed a method based on depth map fusion and later complemented it with an accurate refinement method.

Symmetric Object Detection

icon My PhD thesis deals with application of symmetry principles to computer vision problems of object detection in images. The focus is put on the ways how our prior knowledge on translation, reflection and rotation symmetries can be encoded in probabilistic models. Conceptually the position of our object-centered approach lies between general symmetry detection and strongly informed procedural modeling.
In particular we present two previously published methods for parsing of facade images, where translation symmetry manifests in the structure of architectural elements like windows, doors and cornices. In both cases the structural model is based on local interactions between objects and the symmetry is represented in the spirit of Gestaltian grouping principles of proximity, similarity and continuity.
In addition the last method explores the remaining reflection and rotation symmetries. At this time the Bayesian inference is used to handle a hierarchical model extending from the low-level geometry of reflection symmetry to dihedral symmetry groups. Objectness and compactness priors are included to reduce ambiguity in the detection. The increased complexity of the model is compensated by utilization of an advanced inference method, which allows to rigorously reason about number of detected components by means of model selection. In result we show this approach improves performance on standard datasets, particularly in the case when multiple objects are present.

Probabilistic Models for Symmetric Object Detection in Images BIB
Czech Technical University, November 2015.

Spatial Pattern Templates

icon We propose a method for semantic parsing of images with regular structure. The structured objects are modeled in a densely connected CRF. The paper describes how to embody specific spatial relations in a representation called Spatial Pattern Templates (SPT), which allows us to capture regularity constraints of alignment and equal spacing in pairwise and ternary potentials.
Assuming the input image is pre-segmented to salient regions the SPT describe which segments could interact in the structured graphical model. The model parameters are learnt to describe the formal language of semantic labelings. Given an input image, a consistent labeling over its segments linked in the CRF is recognized as a word from this language.
The CRF framework allows us to apply efficient algorithms for both recognition and learning. We demonstrate the approach on the problem of facade image parsing and show that results comparable with state of the art methods.
Spatial Pattern Templates for Recognition of Objects with Regular Structure BIB
Proc. of GCPR, September 2013. (oral) Presentation.
Results: ECP-Monge eTrimsDB
Dataset: CMP Facade Database

Weak Structure Model

icon We present a method for recognition of structured images and demonstrate it on the detection of windows in facade images. Given an ability to obtain local low-level data evidence on primitive elements of a structure (like window in a facade image), we determine their most probable number, attribute values (location, size) and neighborhood relation.
The embedded structure is weakly modeled by pair-wise attribute constraints, which allow structure and attributes to mutually support each other. We use a very general framework of reversible jump MCMC, which allows simple implementation of a specific structure model and plug-in of almost arbitrary element classifiers.
We have chosen the domain of window recognition in facade images to demonstrate that the result is an efficient algorithm achieving performance of other strongly informed methods for regular structures.
Stochastic Recognition of Regular Structures in Facade Images BIB
IPSJ Trans. Computer Vision and Applications, May 2012. Demo.

A Weak Structure Model for Regular Pattern Recognition Applied to Facade Images
Proc. of ACCV, November 2010. (oral) Video.

Symmetries for Structural Recognition

We propose a method for semantic parsing of images with regular structure. The structured objects are modeled in a densely connected CRF. The paper describes how to embody specific spatial relations in a representation called Spatial Pattern Templates (SPT), which allows us to capture regularity constraints of alignment and equal spacing in pairwise and ternary potentials.
Assuming the input image is pre-segmented to salient regions the SPT describe which segments could interact in the structured graphical model. The model parameters are learnt to describe the formal language of semantic labelings. Given an input image, a consistent labeling over its segments linked in the CRF is recognized as a word from this language.
The CRF framework allows us to apply efficient algorithms for both recognition and learning. We demonstrate the approach on the problem of facade image parsing and show that results comparable with state of the art methods.

Modeling Symmetries for Stochastic Structural Recognition BIB
Stochastic Image Grammars workshop, Proc. of ICCV, November 2011.

Surface Mesh Refinement

We propose a pipeline for accurate 3D reconstruction from multiple images that deals with some of the possible sources of inaccuracy present in the input data.
Namely, we address the problem of inaccurate camera calibration by including a method adjusting the camera parameters in a global structure-and-motion problem, which is solved with a depth map for representation that is suitable to large scenes.
Secondly, we take the triangular mesh and calibration improved by the global method in the first phase to refine the surface both geometrically and radiometrically. Here we propose surface energy which combines photoconsistency with contour matching and minimize it with a gradient descent method.
Our main contribution lies in effective computation of the gradient that naturally balances weight between regularizing and data terms by employing scale space approach to find the correct local minimum.
The results are demonstrated on standard high-resolution datasets and a complex outdoor scene.


Refinement of Surface Mesh for Accurate Multi-View Reconstruction
International Journal of Virtual Reality, March 2010. (extended version, pre-print)
Presented at Modeling-3D workshop, Proc. of ACCV, September 2009. Supplemental video. Presentation.

Depth Map Fusion

We present a novel algorithm for image-based surface reconstruction from a set of calibrated images. The problem is formulated in Bayesian framework, where estimates of depth and visibility in a set of selected cameras are iteratively improved.
The core of the algorithm is the minimisation of overall geometric L2 error between measured 3D points and the depth estimates. In the visibility estimation task, the algorithm aims at outlier detection and noise suppression, as both types of errors are often present in the stereo output. The geometrical formulation allows for simultaneous refinement of the external camera parameters, which is an essential step for obtaining accurate results even when the calibration is not precisely known.
We show that the results obtained with our method are comparable to other state-of-the-art techniques.


Depth Map Fusion with Camera Position Refinement
Proc. of CVWW, February 2009. Presentation.

Representation of Geometric objects for 3D photography
Master thesis, CTU Prague, January 2008. Advisor: D.Martinec. Presentation (czech).
Awarded Dean's prize for outstanding Master thesis.

Projects

Teaching

Personal


I am enthusiastic outdoor photographer. You can check out some travel, nature and landscape photos in my gallery.

Links


Last update: 16.5.2016