scispace - formally typeset
E

Engin Türetken

Researcher at École Polytechnique Fédérale de Lausanne

Publications -  39
Citations -  2241

Engin Türetken is an academic researcher from École Polytechnique Fédérale de Lausanne. The author has contributed to research in topics: Integer programming & Tree structure. The author has an hindex of 15, co-authored 38 publications receiving 2015 citations. Previous affiliations of Engin Türetken include Swiss Center for Electronics and Microtechnology & École Normale Supérieure.

Papers
More filters
Journal ArticleDOI

Multiple Object Tracking Using K-Shortest Paths Optimization

TL;DR: This paper shows that reformulating that step as a constrained flow optimization results in a convex problem and takes advantage of its particular structure to solve it using the k-shortest paths algorithm, which is very fast.
Journal ArticleDOI

Automated Reconstruction of Dendritic and Axonal Trees by Global Optimization with Geometric Priors

TL;DR: A novel probabilistic approach to fully automated delineation of tree structures in noisy 2D images and 3D image stacks that uses the DIADEM metric to quantitatively evaluate the topological accuracy of the reconstructions and showed that the use of the geometric regularization yields a substantial improvement.
Journal ArticleDOI

Tracking Interacting Objects Using Intertwined Flows

TL;DR: This paper shows that by estimating jointly and globally the trajectories of different types of objects, the presence of the ones which were not initially detected based solely on image evidence can be inferred from the detections of the others.
Journal ArticleDOI

Multiscale Centerline Detection

TL;DR: This work reformulates centerline detection in terms of a regression problem, and shows that the method outperforms state-of-the-art techniques for various 2D and 3D datasets and shows an improvement above recent contour detection algorithms on the BSDS500 dataset.
Book ChapterDOI

Tracking Interacting Objects Optimally Using Integer Programming

TL;DR: By estimating jointly and globally the trajectories of different types of objects, the presence of the ones which were not initially detected based solely on image evidence can be inferred from the detections of the others.