Paula Craciun

PhD, INRIA Sophia Antipolis

Keywords: Stochastic Modeling, Marked Point Process, Multiple Target Tracking, SEM, Remote Sensing

Contact:
Mail: pauladotcraciunatinriadotfr
Phone: (33)4-92-38-75-68
Fax: (33)4-92-38-78-58
Postal address: INRIA Sophia Antipolis , 2004, route des Lucioles, 06902 Sophia Antipolis Cedex, France

Abstract:

My work at INRIA concerns automatic object detection and tracking on a sequence of satellite images taken from a geostationary orbit.

In particular, the intent is to consider techniques that do not focus on tracking individual objects but rather trying to estimate the density or the flow of the objects using statistical methods. One of the key issues is dealing with an increased number of objects, in a noisy environment. For this, stochastic geometry extended to time sequences is employed. Several applications, such as maritime traffic surveillance, vehicle traffic monitoring, will be considered.

Short Bio:

Paula I. Craciun received her master degree in Artificial Intelligence and Distributed Computing (2012), as well as a master degree in Astrophysics and Elementary Particles (2014), from the West University of Timisoara, Romania.

After a Master internship at INRIA-SAM in the AYIN team, she is currently PhD student registered at the ED-STIC of University of Nice Sophia-Antipolis, working with the AYIN team at INRIA-SAM. Her PhD work is funded by Airbus Defence and Space (ex-Astrium). Her main research interest lies in the field of distributed computing and statistical image analysis and processing. In particular, her work concerns statistical modeling of remotely sensed imagery as well as parallelization techniques.

Last publications:

Publications HAL de Paula,Craciun du labo/EPI ayin

2016

Conference papers

ref_biblio
Paula Craciun, Josiane Zerubia. Stochastic Geometry for Multiple Object Tracking in Fluorescence Microscopy. IEEE International Conference on Image Processing (ICIP), Sep 2016, Phoenix, United States. ⟨hal-01319757⟩
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01319757/file/ICIP-Craciun-2016.pdf BibTex

2015

Conference papers

ref_biblio
Paula Craciun, Mathias Ortner, Josiane Zerubia. Integrating RJMCMC and Kalman filters for multiple object tracking. GRETSI – Traitement du Signal et des Images, Sep 2015, Lyon, France. ⟨hal-01168336⟩
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01168336/file/GRETSI2015_final.pdf BibTex
ref_biblio
Paula Craciun, Mathias Ortner, Josiane Zerubia. Joint detection and tracking of moving objects using spatio-temporal marked point processes. IEEE Winter Conference on Applications of Computer Vision, Jan 2015, Hawaii, United States. ⟨hal-01104981⟩
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01104981/file/WACV15_CameraReady.pdf BibTex

Book sections

ref_biblio
Paula Craciun, Josiane Zerubia. High-resolution satellite imaging. Mathematics of Planet Earth: Mathematicians Reflect on How to Discover, Organize, and Protect Our Planet, Society for Industrial and Applied Mathematics (SIAM), 2015, 978-1-611973-70-9. ⟨hal-01159880⟩
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01159880/file/Section7.5.pdf BibTex

Theses

ref_biblio
Paula Crăciun. Stochastic geometry for automatic multiple object detection and tracking in remotely sensed high resolution image sequences. Other. Université Nice Sophia Antipolis, 2015. English. ⟨NNT : 2015NICE4095⟩. ⟨tel-01235255v2⟩
Accès au texte intégral et bibtex
https://theses.hal.science/tel-01235255/file/2015NICE4095.pdf BibTex

2014

Journal articles

ref_biblio
Paula Craciun, Josiane Zerubia. Unsupervised marked point process model for boat extraction and counting in harbors from high resolution optical remotely sensed images. Revue Française de Photogrammétrie et de Télédétection, 2014, 207, pp.33-44. ⟨hal-01119448⟩
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01119448/file/RFTP_eng.pdf BibTex

Conference papers

ref_biblio
Paula Craciun, Josiane Zerubia. Towards efficient simulation of marked point process models for boat extraction from high resolution optical remotely sensed images. IEEE IGARSS – International Geoscience and Remote Sensing Symposium, Jul 2014, Quebec, Canada. ⟨hal-01016874⟩
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01016874/file/IGARSS_14.pdf BibTex

2013

Journal articles

ref_biblio
Paula Craciun, Josiane Zerubia. Boat Extraction in Harbours From High Resolution Satellite Images Using Marked Point Processes. ERCIM News, 2013. ⟨hal-00939160⟩
Accès au bibtex
BibTex

Conference papers

ref_biblio
Paula Craciun, Josiane Zerubia. Unsupervised marked point process model for boat extraction in harbors from high resolution optical remotely sensed images. IEEE ICIP – International Conference on Image Processing, Sep 2013, Melbourne, Australia. ⟨hal-00867585⟩
Accès au texte intégral et bibtex
https://inria.hal.science/hal-00867585/file/ICIP_13.pdf BibTex
ref_biblio
Paula Craciun, Josiane Zerubia. Boat extraction in harbors from high resolution satellite images using mathematical morphology and marked point processes. GRETSI – Traitement du Signal et des Images, Sep 2013, Brest, France. ⟨hal-00867592⟩
Accès au texte intégral et bibtex
https://inria.hal.science/hal-00867592/file/GRETSI_13_FINAL.pdf BibTex