ACADEMIC MERITS:
I finished my PhD. in March 2017, under the supervision of Full Professor Javier Hernández-Andrés and Professor Eva Valero. The title of my thesis is Multispectral High Dynamic Range Polarimetric Imaging applied to scene segmentation and classification. I graduated with honors "Summa Cum Laude".
Different advanced techniques of digital imaging such as multispectral imaging, high dynamic range (HDR) imaging, polarimetric imaging or Near-Infra-Red imaging, have been developed and applied separately for years. Researchers are trying to merge some of these techniques together into a single integrated system. However this integration is rather challenging, specially if we are dealing with general purpose applications, such as capturing outdoor urban or natural scenes.
The dissertation proposes capturing system designs, as well as algorithms and processing techniques for improving and simplifying the systems currently present in the state of the art of these different imaging techniques. This way, high dynamic range multispectral polarimetric images in the visible and near infrared can be captured and processed for many applications such as image segmentation, objects or materials classification, vegetation monitoring, food inspection, remote sensing, surveillance, etc.
A new multispectral image capturing system is proposed, based on a novel generation of sensors which are still under development. Based on simulations, this work takes advantage of the spectral tunability of these sensors, and combines it with color filter arrays, to propose an imaging system with 36 spectral channels, achieving very good colorimetric and spectral performance for spectral reflectance estimation.
Besides, a new algorithm for the automatic capture of HDR images is proposed, called Adaptive Exposure Estimation (AEE). It can be implemented in any digital imaging system, and it works online, as the capturing is ongoing. It is adaptive to scene content without the need of any prior knowledge about the scene being captured. The proposed method allows the user to tune the performance of the algorithm, keeping the balance between exposure time and signal-to-noise ratio, by just adjusting two free parameters. It can also capture the full dynamic range of the scene (or region of interest), or just a part of it.
The proposed AEE algorithm is also adapted to multispectral polarimetric image capture. Based on a previous work which uses a Liquid Crystal Tunable Filter, a new full framework for capturing and processing 31-channels MultiSpectral HDR Polarimetric (MSHDRPol) images is proposed. New techniques for segmentation and classification of objects present in indoors scenes are proposed and tested. The results show that the algorithm outperforms other methods proposed in previous studies.
As an additional contribution, the whole capturing workflow is adapted to an 8-channels filter-wheel-based imaging system covering the visible and NIR ranges up to 1000 nm. Therefore a system and a framework able to automatically capture MultiSpectral HDR Polarimetric Visible and Near Infra-Red (MSHDRPolVISNIR) images of outdoor scenes are proposed.
A set of 8 outdoors scenes have been captured using the proposed system and methods and they will be made publicly available after the defense of this doctoral thesis.
I did an external internship in the Horiouchi & Hirai Lab, in the Color Image Engineering group, in the physics-based information processing area, at the Information Processing and Computer Sciences Department of the Information Sciences Division, at the Graduate School of advanced integration Science in Chiba University, Japan. I worked under the supervision of Professors Shoji Tominaga, Takahiko Horiuchi and Keita Hirai, during 3 months (from September 2015 to December 2015). In their laboratory, I researched about High Dynamic Range Multispectral polarimetric imaging. I researched how the image captures can be made to get full spectral HDR and polarimetric information of scene objects in order to segment them, and, if possible, classify them according to some material properties.
Different advanced techniques of digital imaging such as multispectral imaging, high dynamic range (HDR) imaging, polarimetric imaging or Near-Infra-Red imaging, have been developed and applied separately for years. Researchers are trying to merge some of these techniques together into a single integrated system. However this integration is rather challenging, specially if we are dealing with general purpose applications, such as capturing outdoor urban or natural scenes.
The dissertation proposes capturing system designs, as well as algorithms and processing techniques for improving and simplifying the systems currently present in the state of the art of these different imaging techniques. This way, high dynamic range multispectral polarimetric images in the visible and near infrared can be captured and processed for many applications such as image segmentation, objects or materials classification, vegetation monitoring, food inspection, remote sensing, surveillance, etc.
A new multispectral image capturing system is proposed, based on a novel generation of sensors which are still under development. Based on simulations, this work takes advantage of the spectral tunability of these sensors, and combines it with color filter arrays, to propose an imaging system with 36 spectral channels, achieving very good colorimetric and spectral performance for spectral reflectance estimation.
Besides, a new algorithm for the automatic capture of HDR images is proposed, called Adaptive Exposure Estimation (AEE). It can be implemented in any digital imaging system, and it works online, as the capturing is ongoing. It is adaptive to scene content without the need of any prior knowledge about the scene being captured. The proposed method allows the user to tune the performance of the algorithm, keeping the balance between exposure time and signal-to-noise ratio, by just adjusting two free parameters. It can also capture the full dynamic range of the scene (or region of interest), or just a part of it.
The proposed AEE algorithm is also adapted to multispectral polarimetric image capture. Based on a previous work which uses a Liquid Crystal Tunable Filter, a new full framework for capturing and processing 31-channels MultiSpectral HDR Polarimetric (MSHDRPol) images is proposed. New techniques for segmentation and classification of objects present in indoors scenes are proposed and tested. The results show that the algorithm outperforms other methods proposed in previous studies.
As an additional contribution, the whole capturing workflow is adapted to an 8-channels filter-wheel-based imaging system covering the visible and NIR ranges up to 1000 nm. Therefore a system and a framework able to automatically capture MultiSpectral HDR Polarimetric Visible and Near Infra-Red (MSHDRPolVISNIR) images of outdoor scenes are proposed.
A set of 8 outdoors scenes have been captured using the proposed system and methods and they will be made publicly available after the defense of this doctoral thesis.
I did an external internship in the Horiouchi & Hirai Lab, in the Color Image Engineering group, in the physics-based information processing area, at the Information Processing and Computer Sciences Department of the Information Sciences Division, at the Graduate School of advanced integration Science in Chiba University, Japan. I worked under the supervision of Professors Shoji Tominaga, Takahiko Horiuchi and Keita Hirai, during 3 months (from September 2015 to December 2015). In their laboratory, I researched about High Dynamic Range Multispectral polarimetric imaging. I researched how the image captures can be made to get full spectral HDR and polarimetric information of scene objects in order to segment them, and, if possible, classify them according to some material properties.
This is an Erasmus Mundus Excellence masters program. It is an international mobility master, taught in English by 4 European universities: University of Granada, Spain; University Jean Monnet, Saint Etienne, France; University of Eastern Finland, Joensuu, Finland, and Gjøvik University College, Gjøvik, Norway.
My mobility was: first year (first and second semesters) in Granada, Spain, third semester in Joensuu, Finland, and Master Thesis (fourth semester) in Granada.
My Master Thesis topic was "Spectral Reflectance Estimation using reconfigurable Transverse Field Detectors", in collaboration with Polytechnic University of Milan, Italy. My student rank for the whole masters program was 1st/24.
My mobility was: first year (first and second semesters) in Granada, Spain, third semester in Joensuu, Finland, and Master Thesis (fourth semester) in Granada.
My Master Thesis topic was "Spectral Reflectance Estimation using reconfigurable Transverse Field Detectors", in collaboration with Polytechnic University of Milan, Italy. My student rank for the whole masters program was 1st/24.
My bachelor degree was obtained in Málaga, Spain. I chose the specialization in Image and Sound. I studied how image, sound, video and data signals were acquired, processed, sent and received. I studied courses such as Digital image processing, Video systems, Television, Electro-acoustics, Digital Audio, Theory of signal, circuits and electronics, Digital circuits, Analogical and digital communications, etc. My Bachelor thesis was an intelligent database of Earth's surface images, with automatic classification of surface types from Google Earth's RGB images.
During the last semester of my PhD., I started a second bachelor degree in Optics and Optometry. The complete program is a 4 years one, but I finished it in 3 years.
OTHER MERITS:
VISUM summer School (Vision Understanding and Machine intelligence). Organized by University of Porto (Portugal). Subjects: Deep Learning, Structure from Motion, Modelling and simulation, Social signal processing, Biometrics and security, Document analysis and Industry session. Winner of "best poster award".
|