Les travaux présentés dans ce manuscrit proposent une architecture de processeur à chemin de données reconfigurable (PCDR) dédiée aux traitements d'images bas niveau. Afin de répondre aux exigences de ce domaine de traitements, le processeur, baptisé SeeProc et basé sur une architecture RISC, intègre dans son chemin de données des unités de calcul spécifiquement dédiées au traitement de données pixeliques sous forme matricielle. Ces unités peuvent être configurées en nombre et en fonctionnalité en fonction de l'application visée. La topologie d'interconnexion du chemin de données est assurée dynamiquement via un dispositif de type crossbar. De plus, pour rendre la programmation de SeeProc accessible à des utilisateurs n'ayant pas de notions d'électronique numérique, un langage assembleur dédié et une méthodologie d'optimisation ont été développés. / The work presented in this manuscript suggest an architecture of a reconfigurable datapath processor (RDP) dedicated to low-level image processing. To meet the requirements of this field, the processor, called SeeProc and based on a RISC architecture, includes in its datapath customs processing elements specifically dedicated to the computation of image data in matrix form. These units can be configured in number and functionality depending on the application. The datapath interconnection topology is provided dynamically using a crossbar device. In addition, to make the programming accessible to users with no knowledge of electronics digital, a dedicated assembly language and an optimization methodology have been developed.

Wireless Vision Sensor Networks (WVSNs) is an emerging field which has attracted a number of potential applications because of smaller per node cost, ease of deployment, scalability and low power stand alone solutions. WVSNs consist of a number of wireless Vision Sensor Nodes (VSNs). VSN has limited resources such as embedded processing platform, power supply, wireless radio and memory.  In the presence of these limited resources, a VSN is expected to perform complex vision tasks for a long duration of time without battery replacement/recharging. Currently, reduction of processing and communication energy consumptions have been major challenges for battery operated VSNs. Another challenge is to propose generic solutions for a VSN so as to make these solutions suitable for a number of applications. To meet these challenges, this thesis focuses on energy efficient and programmable VSN architecture for machine vision systems which can classify objects based on binary data. In order to facilitate generic solutions, a taxonomy has been developed together with a complexity model which can be used for systems’ classification and comparison without the need for actual implementation. The proposed VSN architecture is based on tasks partitioning between a VSN and a server as well as tasks partitioning locally on the node between software and hardware platforms. In relation to tasks partitioning, the effect on processing, communication energy consumptions, design complexity and lifetime has been investigated. The investigation shows that the strategy, in which front end tasks up to segmentation, accompanied by a bi-level coding, are implemented on Field Programmable Platform (FPGA) with small sleep power, offers a generalized low complexity and energy efficient VSN architecture. The implementation of data intensive front end tasks on hardware reconfigurable platform reduces processing energy. However, there is a scope for reducing communication energy, related to output data. This thesis also explores data reduction techniques including image coding, region of interest coding and change coding which reduces output data significantly. For proof of concept, VSN architecture together with tasks partitioning, bi-level video coding, duty cycling and low complexity background subtraction technique has been implemented on real hardware and functionality has been verified for four applications including particle detection system, remote meter reading, bird detection and people counting. The results based on measured energy values shows that, depending on the application, the energy consumption can be reduced by a factor of approximately 1.5 up to 376 as compared to currently published VSNs. The lifetime based on measured energy values showed that for a sample period of 5 minutes, VSN can achieve 3.2 years lifetime with a battery of 37.44 kJ energy. In addition to this, proposed VSN offers generic architecture with smaller design complexity on hardware reconfigurable platform and offers easy adaptation for a number of applications as compared to published systems.

Dans la plupart des applications de robotique, un système de vision apporte une amélioration significative de la perception de l’environnement. La vision panoramique est particulièrement intéressante car elle rend possible une perception omnidirectionnelle. Elle est cependant rarement utilisée en pratique à cause des limitations technologiques découlant des méthodes la permettant. La grande majorité de ces méthodes associent des caméras, des miroirs, des grands angles et des systèmes rotatifs ensembles pour créer des champs de vision élargis. Les principaux défauts de ces méthodes sont les importantes distorsions des images et l’hétérogénéité de la résolution. Certaines autres méthodes permettant des résolutions homogènes, prodiguent un flot de données très important qui est difficile à traiter en temps réel et sont soit trop lents soit manquent de précision. Pour résoudre ces problèmes, nous proposons la réalisation d’une caméra panoramique intelligente qui présente plusieurs améliorations technologiques par rapport aux autres caméras linéaires rotatives. Cette caméra capture des panoramas cylindriques homogènes avec une résolution de 6600 × 2048 pixels. La synchronisation de la capture avec la position angulaire est possible grâce à une plateforme rotative de précision. Nous proposons aussi une solution au problème que pose le gros flot de données avec l’implémentation d’un extracteur de primitives qui sélectionne uniquement les primitives invariantes des images pour donner un système panoramique de vision qui ne transmet que les données pertinentes. Le système a été modélisé et une méthode de calibrage spécifiquement conçue pour les systèmes cylindriques rotatifs est présentée. Enfin, une application de localisation et de reconstruction 3D est décrite pour montrer une utilisation pratique dans une application de type Simultaneous Localization And Mapping ( SLAM ). / In most robotic applications, vision systems can significantly improve the perception of the environment. The panoramic view has particular attractions because it allows omnidirectional perception. However, it is rarely used because the methods that provide panoramic views also have significant drawbacks. Most of these omnidirectional vision systems involve the combination of a matrix camera and a mirror, rotating matrix cameras or a wide angle lens. The major drawbacks of this type of sensors are in the great distortions of the images and the heterogeneity of the resolution. Some other methods, while providing homogeneous resolutions, also provide a huge data flow that is difficult to process in real time and are either too slow or lacking in precision. To address these problems, we propose a smart panoramic vision system that presents technological improvements over rotating linear sensor methods. It allows homogeneous 360 degree cylindrical imaging with a resolution of 6600 × 2048 pixels and a precision turntable to synchronize position with acquisition. We also propose a solution to the bandwidth problem with the implementation of a feature etractor that selects only the invariant feaures of the image in such a way that the camera produces a panoramic view at high speed while delivering only relevant information. A general geometric model has been developped has been developped to describe the image formation process and a caligration method specially designed for this kind of sensor is presented. Finally, localisation and structure from motion experiments are described to show a practical use of the system in SLAM applications.

Master’s thesis is describing main terms in machine vision. It defines the basic working principles, its advantages and disadvantages. It is dividing machine vision systems into several classes. The thesis is solving design of an end effector, of an inspection process and program for smart camera Siemens SIMATIC VS722A, of a program for KUKA KR3 and of mutual communication. At the end the demonstrational application verifying the functionality of entire system is introduced.

Diploma thesis deals with a robot vision and its application to the problem of manipulation of coincidentally placed objects. There is mentioned an overview of current principles of the most frequently used vision systems on the market. With regard to the required task to be solved, there are mentioned various possibilities of using basic softsensors during the recognition of different objects. The objective of this Diploma thesis is also programming and realization of a demonstration application applying knowledge of PLC programming, knowledge of expert programming KRL language (for KUKA robots), knowledge of designing scripts for smart camera in Spectation software and knowledge of network communication among all devices used in this case.

Diploma thesis refers about design of vision system for industrial robot.

This thesis deals with the possibilities of 3D vision. The theoretical part describes the principles of machine vision, constitutes the basic elements, description and the methods of measurement and 3D. The practical part is focused on the design of experimental workplace, which is consists of conveyor, experimental stand, industrial robot and PLC control. The system used to recognize and grasp objects undirected. Construction chapter focuses on the treatment needs of the conveyor for sensing applications and design of experimental stand with linear axis, which is equipped with camera and lasers. Furthermore solved by a communication network between the elements of work includes the design of their communications with the description of the control of its individual elements.

Människan har alltid utvecklat produkter för att förenkla sin vardag i hemmet. Ett område som växer snabbt är sakernas Internet där smarta ansluta enheter tillhör. Intentionen med smarta kameror är övervakning där man har möjlighet att bevaka sin intelligenta kamera trådlöst från exempelvis en smartmobil. Utmaningar med de intelligenta anslutna kamerorna är att hur kan man få kunskap om spionage, attacker och skador. Många av dessa smarta kameror har mindre resurser tillgängliga, och har då inte möjlighet att implementera optimala säkerhetsmekanismer. Även om dessa smarta enheter kan berika tillvaron och skapa trygghet med sin övervakning, så möjliggör också den smarta kameran nya sätt för angripare att göra intrång, då enheten är uppkopplade mot Internet.Syftet med den här uppsatsen är att undersöka vilken öppen data som finns tillgänglig på Internet om uppkopplade kameror. Detta genom att skapa ett program för att extrahera publik tillgänglig information om smarta kameror som är synliga för alla som har tillgång till Internet, och då också tillgång till Shodans sökmotor. Den öppna datan påvisar sårbarheter som kan utnyttjas för att göra intrång. Sårbarheterna som fanns hos de uppkopplade kamerorna på grund av tillgängligheten på Shodan var osäker konfigurations hantering och otillräcklig autentisering. Genom att belysa befintliga sårbarheter i smarta kameror som finns idag, kunna bidra till hur man med publik tillgänglig information kan få kunskap om sårbarheter hos smarta produkter. Med bakgrund till att sårbarheter finns och den smarta kameran är uppkopplad mot Internet, kan det vara så att det är fler än ägaren till den smarta kameran som övervakar hemmet. / Humans have always developed products to simplify their everyday lives in the home environment. A fast growing area is the Internet of Things where smart connect devices belong. The intention with smart cameras is surveillance where one can monitor their smart camera wireless from e.g a smartphone. Challenges with the intelligent connected cameras includes, how to get knowledge about espionage, attacks and damages. Many of these smart cameras have a reduced-size, low-power hardware with smaller resources available, and therefore unable to implement optimal security mechanisms. Although these connected cameras can enrich the safety and create security with their surveillance, the smart camera also allows new ways for attackers to intrude due to the devices are connected to the Internet.The purpose of this thesis is to investigate what kind of open data is available on the Internet from, connected cameras. This is done by creating a program to extract publicly available smart camera information that is visible to anyone who has access to the Internet, and thus access to Shodan’s search engine. The open data shows vulnerabilities that can potentially be exploited to intrude on devices. The vulnerabilities found in the connected cameras due to availability of Shodan, were insecure configuration management and insufficient authentication. By highlighting significant vulnerabilities in smart cameras found today, the thesis can contribute to how one with publicly available information can gain knowledge about vulnerabilities in smart devices. Given that vulnerabilities exist and the smart camera is connected to the Internet, it may be more than the owner of the smart camera that monitors the residence.

Driving while drowsy is a major cause behind road accidents, and exposes the driver to a much higher crash risk compared to driving while alert. Therefore, the use of assistive systems that monitor a driver’s level of vigilance and alert the fatigue driver can be significant in the prevention of accidents. This thesis introduces three different methods towards the detection of drivers’ drowsiness based on yawning measurement. All three approaches involve several steps, including the real time detection of the driver’s face, mouth and yawning. The last approach, which is the most accurate, is based on the Viola-Jones theory for face and mouth detection and the back projection theory for measuring both the rate and the amount of changes in the mouth for yawning detection. Test results demonstrate that the proposed system can efficiently measure the aforementioned parameters and detect the yawning state as a sign of a driver’s drowsiness.

Driving while drowsy is a major cause behind road accidents, and exposes the driver to a much higher crash risk compared to driving while alert. Therefore, the use of assistive systems that monitor a driver’s level of vigilance and alert the fatigue driver can be significant in the prevention of accidents. This thesis introduces three different methods towards the detection of drivers’ drowsiness based on yawning measurement. All three approaches involve several steps, including the real time detection of the driver’s face, mouth and yawning. The last approach, which is the most accurate, is based on the Viola-Jones theory for face and mouth detection and the back projection theory for measuring both the rate and the amount of changes in the mouth for yawning detection. Test results demonstrate that the proposed system can efficiently measure the aforementioned parameters and detect the yawning state as a sign of a driver’s drowsiness.