Scientific direction Development of key enabling technologies
Transfer of knowledge to industry

PhD : selection by topics

Engineering science >> Computer science and software
7 proposition(s).

Person re-identification and cross-domain adaptability

Département Intelligence Ambiante et Systèmes Interactifs (LIST)

Vision & Ingénierie des Contenus (SAC)

01-02-2019

SL-DRT-19-0283

romaric.audigier@cea.fr

Automatically re-identifying people viewed by cameras is a key functionality for videoprotection applications. It consists in retrieving occurrences of a person from a set of images. Despite the many studies on this topic in the past few years, modeling human appearance remains a challenge. Indeed, re-identification models have to discriminate distinct people (in spite of their possible similarity) while being robust against the high variability of their visual appearance (caused by their posture, lighting conditions, camera viewpoint, sensitivity and resolution, ?). Besides, partial occlusion and alignment errors on the detected people have to be coped with. Even if deep supervised learning methods have been greatly improving re-identification performances on some academic datasets, difficulties remain for real implementations in operational environments. Indeed, a model trained on a specific dataset usually does not perform well if applied on other datasets as it is. Furthermore, manual data annotation in the target domain is a tedious thus costly task. In this thesis, we will study the appearance model adaptability to target domains in which only data without annotation is available. Unsupervised transfer learning methods can be used. The proposed approaches will cope with scalability issues in order to address large datasets.

Adaptive CMOS Image Sensor for smart vision systems

Département Architectures Conception et Logiciels Embarqués (LIST-LETI)

Laboratoire Circuits Intégrés, Intelligents pour l'Image

01-10-2019

SL-DRT-19-0335

william.guicquero@cea.fr

The aim of this thesis is to explore new kind of smart vision sensor architectures using for enhance the sensor reactivity and for simplify the image processing. The studied vision system will use new 3D microelectronic technologies from CEA-leti. These technologies are capable to stack several integrated circuits. The main advantage is to propose a high density of interconnections between them, allowing connection at the pixel level. This characteristic allows us to think about a totally new architecture of the image processing chain of a basic imager (readout, amplification, compensation, colorization, tone mapping) in order to improve the agility, a better image quality, a better energy efficiency, with a low silicon footprint. The PhD student will benefit during his 3-years thesis of the expertise and the scientific excellence of the CEA leti to attend objectives with a high level of innovation through international patents and publications. The dynamic and autonomous candidate, will have a microelectronic master degree, specialized in analog integrated circuit design. A good knowledge of circuit design CAD tools will be important (Cadence, and also Matlab) and good knowledge in image processing will be appreciated. This thesis will start with the state of the art study, then the PhD student will define the optimal architecture. Finally, a test chip will be designed and tested. It will demonstrate the scientific and industrial potentialities of the proposed solutions.

Massively parallel in-memory computing architecture

Département Architectures Conception et Logiciels Embarqués (LIST-LETI)

Laboratoire Intégration Silicium des Architectures Numériques

01-10-2019

SL-DRT-19-0364

romain.lemaire@cea.fr

Systems-on-chip (SoCs) for embedded computing have always been constrained by memory bandwidth. Nowadays, with the development of application data-intensive, cost (latency, energy) related to memory access for data computation are significantly increasing. A new computing paradigm consisting in performing data computation within the memory (IMC: In-Memory Computing) has been proposed: the idea is to process data where they are stored in order to save energy and latency. Clear separation between computing and storage units is vanishing leading to very new architectures. The objective of this thesis work is to define a massively parallel in-memory computing architecture supporting the interconnection of a matrix of computing tiles based on IMC memory for parallel execution (multiprocessor) and parallel data access (multiple memory banks). The thesis will be based on on-going work in the lab related to SRAM memory and will address higher density memory types. The subject will require an exploratory approach through modeling of the proposed architecture in relation with the targeted applications (big data, artificial intelligence). Design and silicon implementation of innovative blocks of the architecture will validate to proposed concepts.

Study of new solutions for the security of embedded systems

Département Systèmes

Laboratoire Sécurité des Objets et des Systèmes Physiques

01-09-2019

SL-DRT-19-0426

pierre-henri.thevenon@cea.fr

In recent years, the number of connected systems has increased exponentially and is expected to reach several tens of billions by 2020. Most of these devices integrate seldom, if ever, security and can create massive attacks involving a large number of objects. In the embedded systems used in IOT and I-IOT, hardware and software solutions currently exist and provide cryptographic primitives to secure a communication interface or data storage. However, these solutions are not always correctly implemented and didn't deal with all the issues of security. Based on the study of existing attack scenarios, standards and regulatory documents, this thesis will define the needs in terms of security of an embedded system throughout its life cycle. Particular attention should be paid to threat detection, hardware and software integrity, system resilience, and the definition of a new commissioning interface. New solutions will be studied and developed in order to address issues not integrated in current embedded devices. The implementation of these new solutions will be the first step in the development of a new component called a security supervisor. One day, this component could be integrated in most of embedded systems in order to strengthen defence in depth.

Resistant and resilient processor to fault attacks and side-channel attacks

Département Systèmes

Laboratoire Sécurité des Objets et des Systèmes Physiques

01-09-2019

SL-DRT-19-0608

olivier.savry@cea.fr

Crypto-processors are not the only ones that are sensitive to fault attacks and side-channel attacks, CPUs are also prone to those flaws. Unfortunately, their sensitivities to these threats are poorly known. The objective of this thesis will be to characterize the consequences of these faults and leaks. New horizontal-type side-channel attacks based on machine learning can be experimented to go back to the executed code. Based on this knowledge, the PhD student will implement a processor core on FPGA completely resistant to intentional faults and side-channel attacks. Fault countermeasures solutions are often based on redundancy (spatial and temporal redundancy, error detector and corrector code, ...) that only increase the leakage and therefore the vulnerability to side-channel attacks. This approach is innovative as it aims to resolve this dilemma. The detection of faults is not the only constraint to be taken into account, however, it will be necessary to ensure that the CPU is resilient and able to restart from a stable state as close as possible to the erroneous state.

Machine learning based simulation of realistic signals for an enhanced automatic diagnostic in non-destructive testing applications

Département Imagerie Simulation pour le Contrôle (LIST)

Laboratoire Simulation et Modélisation en Electro-magnétisme

01-09-2019

SL-DRT-19-0657

roberto.miorelli@cea.fr

Model based solutions for automatic diagnostic in the field on non-destructive testing are currently a topic of great interest in both academic and industrial communities. Their ultimate objective is to provide a qualitative or quantitative evaluation of the inspected material state (sound, flawed, flawed with anomaly dimensions or criticality) in an industrial context like a production line. Such tools, providing inputs for real-time process control, contribute to the general trend in Europe that aims at modernizing Industry and services [1]. The CEA LIST institute is an internationally recognized research institution in the field of nondestructive testing. It develops the CIVA software [2], which offers multi-physics models and is considered as a leading product for simulation for NDT applications. Accurate models able to reproduce experimental signals prove very helpful in an inversion process aiming at classifying or characterizing flaws [3]. However, as they do not account for disturbances and parameters variability occurring during an experimental acquisition, simulated signals inherently look ?perfect? and are, for instance, easily distinguishable from experimental data. This PhD subject aims at improving the match between simulation and experimental data, by augmenting the simulation with another contribution on can generally refer to as ?noise?. The strategy proposed to obtain such noise contribution is to apply machine-learning techniques like dictionary learning to a set of representative experimental data. Alternatively, a deep learning model can be trained to analyze real data and then distinguish between contents (flaw signals) and style (the rest, which is not simulated by physical models). Afterwards, the augmented simulation tool will be able to reproduce closely experimental data, take into account specific discrepancies due to a particular environment and reproduce the variability observed experimentally. It will thus enhance the performance of model based tools developed at CEA LIST for sensibility analysis, management of uncertainty and diagnostic. REFERENCES [1] http://ec.europa.eu/research/participants/portal/desktop/en/opportunities/h2020/topics/dt-fof-08-2019.html [2] www.extende.com [3] M. Salucci et al., "Real-Time NDT-NDE Through an Innovative Adaptive Partial Least Squares SVR Inversion Approach," in IEEE Transactions on Geoscience and Remote Sensing, vol. 54, no. 11, pp. 6818-6832, Nov. 2016

Embedded perception system for real time 4D scene analysis

Département Architectures Conception et Logiciels Embarqués (LIST-LETI)

Laboratoire Adéquation Algorithmes Architecture

01-12-2019

SL-DRT-19-0712

stephane.chevobbe@cea.fr

With the growing number of autonomous systems the needs of environment perceptions explode in the embedded systems. These systems integrate a wide variety of sensors and of perception functions. They often model the near environment with a collection of mostly independent specific functions. The goal of this work is to design a new embedded perception system, taking advantage of several sensors and temporal measurements to generate a 3D model understandable by a higher-level application. It could, for example, generates a 3D mesh of a scene with semantic and dynamic information. The targeted application domain is the extended reality. Firstly, the candidate will develop a golden applicative 3D modeling pipeline based on the latest algorithms on a PC. Next, he will imagine and define a embedded system with several sensors and will adapt the algorithms to minimize the energy consumption and reduce the execution latency.

Voir toutes nos offres