Camille Kurtz, PhD in Computer Science
Content-based image retrieval
Multiresolution imaging Background knowledge Hierarchical segmentation
Mathematical morphology Computer vision Remote sensing Medical Imaging
Research social networks
Download my Full résumé (pdf 0.8 Mb)
Current position (since Oct. 2012)
I am currently a post-doctoral fellow at the Stanford Quantitative Imaging Laboratory (QIL), Stanford University, Palo Alto (USA). My areas of expertise are image analysis and data mining for medical imaging applications. My post-doctoral work is focused on integrating semantic features to enhance the description of images for Content-Based Image Retrieval (CBIR) purpose.
The Stanford Quantitative Imaging Laboratory conducts research to extract and use objective information in images (quantitative measurements and controlled qualitative observations) in machine-processible form for radiology discovery and clinical applications. The Quantitative Imaging Laboratory is in the Stanford Department of Radiology in the Stanford University School of Medicine.
Department of Radiology
The Lucas Center for MR Spectroscopy and Imaging
1201 Welch Road
Palo Alto, CA
In the field of remote sensing image analysis, the recognition of complex patterns from satellite images presents several challenges related to the size, the accuracy and the complexity of the considered data. Indeed, due to the large amount of ground details provided by these images, the classical photo-interpretation approaches do not provide satisfactory results. In this context, it is then relevant to develop new automatic tools adapted to the extraction of complex patterns from such data.
In this thesis, we have proposed new region-based approaches (i.e., segmentation and classification) enabling to extract different levels of information from sets of images at different spatial resolutions. Indeed, such multiresolution sets of images provide different (complementary) views on the represented objects of interest and can be used to make easier the extraction process of these objects. The main principle of the proposed approach is to progressively extract and classify segments/objects of interest from the lowest to the highest resolution data, and then finally to determine complex patterns from VHSR images. This approach, inspired by the principle of photo-interpretation and human vision, merges hierarchical segmentation approaches with multiresolution clustering strategies combined to the integration of high-level background knowledge. The proposed framework has been validated in the context of the urban mapping of complex objects.
Experiments have been carried out on multiresolution sets of satellite images sensed over different cities. The results obtained have shown that the quality and the accuracy of the extracted patterns seem sufficient to further accurately perform both classification or object detection in an operational context.
Thesis manuscript (in French)
Illustration of multiresolution images
|Multiresolution set of images|
|1 pixel = 10 m x 10 m||1 pixel = 2.4 m x 2.4 m||1 pixel = 60 cm x 60 cm|
|Groundtruth maps associated|
|Segmentation / clustering results|
|Districts segmentation||Blocks segmentation||Buildings segmentation|
|These images are the property of the LIVE laboratory, University of Strasbourg (France)|
Research Articles in International Journals (3)
Research Articles in International Conference or Workshops Proceedings (5)
Research Articles in National Conference or Workshops Proceedings (3)
Submitted Research Articles (1)
Oral communications (5)
I am involved (and I have been involved) in different research projects related to medical imaging and remote sensing image analysis. Most of them are funded by the french Agence Nationale de la Recherche.
ANR FOSTER (2011 - 2013)
The FOSTER project ("Spatio-temporal data mining: application to the understanding and monitoring of soil erosion") is a three-year project launched in January 2011. This computer science project is founded by the French National Research Agency ANR. This project aims at providing to geologists a semi-automatic and complete process for monitoring soil erosion. This process will be based on multi-temporal very high resolution satellite images coupled with digital elevation model (DEM), sensor data and/or expert knowledge. The project will focus more precisely on two important aspects of this process: segmentation of satellite images based on collaborative methods, and construction of descriptive (patterns, clustering, …) and predictive (decision trees, …) spatio-temporal models.
ANR FODOMUST (2004 - 2008)
The FoDoMuSt project ("Multi-Strategic Data Mining") is a four-year project launched in September 2004 and finished in September 2008. FoDoMuSt is a research project about multi-strategic data mining for extraction and characterisation of urban vegetation based on a database of remote sensing images. The main idea is to improve the result of one clustering on some data by using a set of clustering methods and making them collaborate. Multi-strategic clustering methods can then be used to generate thematic maps (with different clusters for different ground occupations/uses). The proposed collaborative approaches proposed during this project have been validated in the context of remote sensing images analysis, with the collaboration of the Laboratoire Image et Ville (UMR CNRS/UDS 7011).
During my Phd, I have been a Teaching Assistant at the UFR de Mathématique et d'Informatique, University of Strasbourg (France). I taught around 150h(+) to undergraduate computer science students (Distributed computing, Computer architecture, Graphs and operational computation, etc.).
L1/S1 Physique : Environnements Informatiques
L2/S3 Informatique : Bases de données 1
L2/S4 Informatique : Architecture des ordinateurs
L2/S4 Informatique : Graphes et recherches opérationnelles
L3/S6 : Systèmes distribués
Master (M.Sc.) - Training course
Licence (B.Sc.) - Training course
This html template was designed and provided by Germain Forestier
A link to my parents' website