Robotic industries are growing faster than in any other era with the demand and rise of in home robots or assisted robots. Such a robot should be able to navigate between different rooms in the house autonomously. For autonomous navigation, the robot needs to build a map of the surrounding unknown environment and localize itself within the map. For home robots, distinguishing between different rooms improves the functionality of the robot. In this research, Simultaneously Localization And Mapping (SLAM) utilizing a LiDAR sensor is used to construct the environment map. LiDAR is more accurate and not sensitive to light intensity compared to vision. The SLAM method used is Gmapping to create a map of the environment. Gmapping is one of the robust and user-friendly packages in the Robotic Operating System (ROS), which creates a more accurate map, and requires less computational power. The constructed map is then used for room categorization using Convolutional Neural Network (CNN). Since CNN is one of the powerful techniques to classify the rooms based on the generated 2D map images. To demonstrate the applicability of the approach, simulations and experiments are designed and performed on campus and an apartment environment. The results indicate the Gmapping provides an accurate map. Each room used in the experimental design, undergoes training by using the Convolutional Neural Network with a data set of different apartment maps, to classify the room that was mapped using Gmapping. The room categorization results are compared with other approaches in the literature using the same data set to indicate the performance. The classification results show the applicability of using CNN for room categorization for applications such as assisted robots.

When reconstructing the Earth in 3D, the imagery can come from various mediums, including satellites, planes, and drones. One significant benefit of utilizing drones in combination with a Visual Simultaneous Localization and Mapping (V-SLAM) system is that specific areas of the world can be accurately mapped in real-time at a low cost. Drones can essentially be equipped with any camera sensor, but most commercially available drones use a monocular rolling shutter camera sensor. Therefore, on behalf of Maxar Technologies, multiple monocular V-SLAM systems were studied during this thesis, and ORB-SLAM3 and LDSO were determined to be evaluated further. In order to provide an accurate and reproducible result, the methods were benchmarked on the public datasets EuRoC MAV and TUM monoVO, which includes drone imagery and outdoor sequences, respectively. A third dataset was collected with a DJI Mavic 2 Enterprise Dual drone to evaluate how the methods would perform with a consumer-friendly drone. The datasets were used to evaluate the two V-SLAM systems regarding the generated 3D map (point cloud) and estimated camera trajectory. The results showed that ORB-SLAM3 is less impacted by the artifacts caused by a rolling shutter camera sensor than LDSO. However, ORB-SLAM3 generates a sparse point cloud where depth perception can be challenging since it abstracts the images using feature descriptors. In comparison, LDSO produces a semi-dense 3D map where each point includes the pixel intensity, which improves the depth perception. Furthermore, LDSO is more suitable for dark environments and low-texture surfaces. Depending on the use case, either method can be used as long as the required prerequisites are provided. In conclusion, monocular V-SLAM systems are highly dependent on the type of sensor being used. The differences in the accuracy and robustness of the systems using a global shutter and a rolling shutter are significant, as the geometric artifacts caused by a rolling shutter are devastating for a pure visual pipeline. / <p>Examensarbetet är utfört vid Institutionen för teknik och naturvetenskap (ITN) vid Tekniska fakulteten, Linköpings universitet</p>

In this dissertation we present advances in developing an autonomous air vehicle capable of navigating through unknown, indoor environments. The problem imposes stringent limits on the computational power available onboard the vehicle, but the environment necessitates using 3D sensors such as stereo or RGB-D cameras whose data requires significant processing. We address the problem by proposing and developing key elements of a relative navigation scheme that moves as many processing tasks as possible out of the time-critical functions needed to maintain flight. We present in Chapter 2 analysis and results for an improved multirotor helicopter state estimator. The filter generates more accurate estimates by using an improved dynamic model for the vehicle and by properly accounting for the correlations that exist in the uncertainty during state propagation. As a result, the filter can rely more heavily on frequent and easy to process measurements from gyroscopes and accelerometers, making it more robust to error in the processing intensive information received from the exteroceptive sensors. In Chapter 3 we present BERT, a novel approach to map optimization. The goal of map optimization is to produce an accurate global map of the environment by refining the relative pose transformation estimates generated by the real-time navigation system. We develop BERT to jointly optimize the global poses and relative transformations. BERT exploits properties of independence and conditional independence to allow new information to efficiently flow through the network of transformations. We show that BERT achieves the same final solution as a leading iterative optimization algorithm. However, BERT delivers noticeably better intermediate results for the relative transformation estimates. The improved intermediate results, along with more readily available covariance estimates, make BERT especially applicable to our problem where computational resources are limited. We conclude in Chapter 4 with analysis and results that extend BERT beyond the simple example of Chapter 3. We identify important structure in the network of transformations and address challenges arising in more general map optimization problems. We demonstrate results from several variations of the algorithm and conclude the dissertation with a roadmap for future work.

Heavy reliance on GPS is preventing unmanned air systems (UAS) from being fully inte- grated for many of their numerous applications. In the absence of GPS, GPS-reliant UAS have difficulty estimating vehicle states resulting in vehicle failures. Additionally, naively using erro- neous measurements when GPS is available can result in significant state inaccuracies. We present a simultaneous localization and mapping (SLAM) solution to GPS-degraded navigation that al- lows vehicle state estimation and control independent of global information. Optionally, a global map can be constructed from odometry measurements and can be updated with GPS measurements while maintaining robustness against outliers.We detail a relative navigation SLAM framework that distinguishes a relative front end and global back end. It decouples the front-end flight critical processes, such as state estimation and control, from back-end global map construction and optimization. Components of the front end function relative to a locally-established coordinate frame, completely independent from global state information. The approach maintains state estimation continuity in the absence of GPS mea- surements or when there are jumps in the global state, such as after map optimization. A global graph-based SLAM back end complements the relative front end by constructing and refining a global map using odometry measurements provided by the front end.Unlike typical approaches that use GPS in the front end to estimate global states, our unique back end uses a virtual zero and virtual constraint to allow intermittent GPS measurements to be applied directly to the map. Methods are presented to reduce the scale of GPS induced costs and refine the map’s initial orientation prior to optimization, both of which facilitate convergence to a globally consistent map. The approach uses a state-of-the-art robust least-squares optimization algorithm called dynamic covariance scaling (DCS) to identify and reject outlying GPS measure- ments and loop closures. We demonstrate our system’s ability to generate globally consistent and aligned maps in GPS-degraded environments through simulation, hand-carried, and flight test re- sults.

D. Tech. (Department of Information Technology, Faculty of Applied and Computer Sciences), Vaal University of Technology. / Simultaneous Localization and Mapping (SLAM) is a significant problem that has been extensively researched in robotics. Its contribution to autonomous robot navigation has attracted researchers towards focusing on this area. In the past, various techniques have been proposed to address SLAM problem with remarkable achievements but there are several factors having the capability to degrade the effectiveness of SLAM technique. These factors include environmental noises (light intensity and shadow), dynamic environment, kidnap robot and computational cost. These problems create inconsistency that can lead to erroneous results in implementation. In the attempt of addressing these problems, a novel SLAM technique Known as DIK-SLAM was proposed. The DIK-SLAM is a SLAM technique upgraded with filtering algorithms and several re-modifications of Monte-Carlo algorithm to increase its robustness while taking into consideration the computational complexity. The morphological technique and Normalized Differences Index (NDI) are filters introduced to the novel technique to overcome shadow. The dark channel model and specular-to-diffuse are filters introduced to overcome light intensity. These filters are operating in parallel since the computational cost is a concern. The re-modified Monte-Carlo algorithm based on initial localization and grid map technique was introduced to overcome the issue of kidnap problem and dynamic environment respectively. In this study, publicly available dataset (TUM-RGBD) and a privately generated dataset from of a university in South Africa were employed for evaluation of the filtering algorithms. Experiments were carried out using Matlab simulation and were evaluated using quantitative and qualitative methods. Experimental results obtained showed an improved performance of DIK-SLAM when compared with the original Monte Carlo algorithm and another available SLAM technique in literature. The DIK-SLAM algorithm discussed in this study has the potential of improving autonomous robot navigation, path planning, and exploration while it reduces robot accident rates and human injuries.

Indiana University-Purdue University Indianapolis (IUPUI) / Simultaneous localization and mapping (SLAM) is a general device localization technique that uses realtime sensor measurements to develop a virtualization of the sensor's environment while also using this growing virtualization to determine the position and orientation of the sensor. This is useful for augmented reality (AR), in which a user looks through a head-mounted display (HMD) or viewfinder to see virtual components integrated into the real world. Visual SLAM (i.e., SLAM in which the sensor is an optical camera) is used in AR to determine the exact device/headset movement so that the virtual components can be accurately redrawn to the screen, matching the perceived motion of the world around the user as the user moves the device/headset. However, many potential AR applications may need access to more than device localization data in order to be useful; they may need to leverage environment data as well. Additionally, most SLAM solutions make the naive assumption that the environment surrounding the system is completely static (non-moving). Given these circumstances, it is clear that AR may benefit substantially from utilizing a SLAM solution that detects objects that move in the scene and ultimately provides localization data for each of these objects. This problem is known as the dynamic SLAM problem. Current attempts to address the dynamic SLAM problem often use machine learning to develop models that identify the parts of the camera image that belong to one of many classes of potentially-moving objects. The limitation with these approaches is that it is impractical to train models to identify every possible object that moves; additionally, some potentially-moving objects may be static in the scene, which these approaches often do not account for. Some other attempts to address the dynamic SLAM problem also localize the moving objects they detect, but these systems almost always rely on depth sensors or stereo camera configurations, which have significant limitations in real-world use cases. This dissertation presents a novel approach for registering and localizing unknown moving objects in the context of markerless, monocular, keyframe-based SLAM with no required prior information about object structure, appearance, or existence. This work also details a novel deep learning solution for determining SLAM map initialization suitability in structure-from-motion-based initialization approaches. This dissertation goes on to validate these approaches by implementing them in a markerless, monocular SLAM system called LUMO-SLAM, which is built from the ground up to demonstrate this approach to unknown moving object registration and localization. Results are collected for the LUMO-SLAM system, which address the accuracy of its camera localization estimates, the accuracy of its moving object localization estimates, and the consistency with which it registers moving objects in the scene. These results show that this solution to the dynamic SLAM problem, though it does not act as a practical solution for all use cases, has an ability to accurately register and localize unknown moving objects in such a way that makes it useful for some applications of AR without thwarting the system's ability to also perform accurate camera localization.

In modern combat aircraft, the most common localization method integrates a Global Navigation Satellite System (GNSS) with an Inertial Navigation System (INS). Although GNSS is the optimal choice for navigation, there are situations when the GNSS satellite signal is unavailable. This can happen due to various reasons such as jamming, physical obstacles, or technical failures. An alternative method to GNSS is utilizing Signals of Opportunity (SOP), which leverages signals not intended for navigation, such as those from cellular towers. These signals are transmitted from non-controllable sources, and challenges may arise due to the lack of guarantee regarding their quality and availability. Therefore, it is crucial that any estimation method utilizing SOP is robust to ensure accurate aircraft localization. This thesis investigates three different localization approaches to address this challenge. This study explores SOP sources with both known and unknown positions. For known signal source positions, an Extended Kalman Filter (EKF) based solution is utilized as a baseline to evaluate how well unknown signal sources can be used to estimate the aircraft's location. To address the challenge of unknown signal source positions, an EKF combined with a Simultaneous Localization and Mapping (SLAM) method, referred to as EKF SLAM, is used. In this case, the sources are introduced through two different approaches. The first approach, undelayed initialization, introduces the signal source directly when observed. The second approach, delayed initialization, involves inverse depth parameterization (IDP) and preprocessing of the signal source position before fully introducing it into the aircraft system. While both approaches outperform an unassisted INS approach, they do not achieve the same level of performance as when the source positions are known. Moreover, various factors, including the aircraft's trajectory, measurement noise, measurement frequency, and the initial covariance of new landmarks, influence the performance of the EKF SLAM approaches. Additionally, delayed initialization is strongly influenced by a threshold assessing landmark position estimate linearity, underscoring its sensitivity to accuracy. The concept behind delayed initialization aims to reduce the error of the signal source position before it is introduced to the system. This method has been proven to significantly reduce the signal source position error. However, its robustness is influenced by several factors, including the parallax angle, sudden changes in the aircraft's direction, and particularly the initial covariance of a landmark estimate. The accuracy of the aircraft's position is crucial, resulting in a trade-off between preprocessing and rapidly initializing a signal source position to the aircraft system. In contrast, undelayed initialization is less sensitive to trajectory changes, even though it introduces the signal sources with greater initial error. There is a significant difference in computational time when comparing known and unknown sources. As the number of sources increases, the computational time for unknown sources is more affected than for known sources. The delayed source initialization method increases computational time due to its preprocessing, especially as more sources are used. Conversely, initializing sources directly reduces the computational time, as no preprocessing is required. / I moderna stridsflygplan är den vanligaste lokaliseringsmetoden att integrera ett Global Navigation Satellite System (GNSS) med ett Inertial Navigation System (INS). Även om GNSS är det optimala valet för navigation finns det situationer när GNSS-satellitsignalen inte är tillgänglig. Detta kan inträffa på grund av olika orsaker som störningar, fysiska hinder eller tekniska fel. En alternativ metod till GNSS är att använda Signals of Opportunity (SOP), som utnyttjar signaler som inte är avsedda för navigation, till exempel de från mobilmaster. Dessa signaler kommer från okontrollerbara källor, vilket kan medföra utmaningar på grund av att deras kvalitet och tillgänglighet inte kan garanteras. Därför är det viktigt att varje lokaliseringsmetod som använder SOP är robust för att säkerställa en bra och korrekt flygplans positionering. Detta examensarbete undersöker tre olika lokaliseringsmetoder för att hantera denna utmaning. Denna studie utforskar SOP-källor med både kända och okända positioner. För kända positioner används en lösning baserad på ett Extended Kalman Filter (EKF) som en baslinje för att utvärdera hur väl okända signalkällor kan användas för att uppskatta flygplanets position. För att hantera utmaningen med okända signalkällors positioner används ett EKF kombinerad med en metod vid namn Simultaneous Localization and Mapping (SLAM), även kallad EKF SLAM. I detta fall introduceras källorna genom två olika tillvägagångssätt. Det första tillvägagångssättet, ofördröjd initialisering, introducerar signalkällan direkt när den observeras. Det andra tillvägagångssättet, fördröjd initialisering, involverar inverse depth parameterization (IDP) och förbearbetning av signalkällans position innan den introduceras i flygplanets lokaliseringssystem. Även om båda tillvägagångssätten presterar bättre än en oassisterad INS-metod uppnår de inte samma prestandanivå som när källornas position är kända. Dessutom påverkar olika faktorer prestandan hos EKF SLAM-metoderna, vilka främst är flygplanets flygbana, mätbrus, mätfrekvens och den initiala kovariansen av nya landmärken. Dessutom påverkas fördröjd initialisering starkt av en tröskel som bedömer linjäritet hos landmärkes positionen, vilket understryker dess känslighet för noggrannhet. Konceptet bakom fördröjd initialisering syftar till att minska felet i signalkällans position innan den introduceras i lokaliseringssystemet. Denna metod har visat sig kunna minska felet i signalkällans position avsevärt. Emellertid påverkas dess robusthet av flera faktorer, inklusive parallaxvinkeln, plötsliga förändringar i flygplanets riktning och särskilt den initiala kovariansen av uppskattningen av ett landmärkes position. Noggrannheten i flygplanets position är avgörande, vilket resulterar i en avvägning mellan förbearbetning och snabb initialisering av en signalkällas position till flygplanets lokaliseringssystem. Till skillnad från fördröjd initialisering är ofördröjd initialisering mindre känslig för förändringar i flygbanan, även om den introducerar signalkällorna med större initialt fel. Det finns en anmärkningsvärd skillnad i beräkningstid när man jämför kända och okända källors. När antalet källor ökar påverkas beräkningstiden för okända källor mer än för kända källor. Den fördröjda källinitialiseringsmetoden ökar beräkningstiden på grund av dess förbearbetning, särskilt när många källor används. Däremot minskar beräkningstiden när källor initialiseras direkt, eftersom ingen förbearbetning krävs.

In der heutigen Zeit spielt die Automatisierung eine immer bedeutendere Rolle, speziell im Bereich der Robotik entwickeln sich immer neue Einsatzgebiete, in denen der Mensch durch autonome Fahrzeuge ersetzt wird. Dabei orientiert sich der Großteil der eingesetzten Roboter an Streckenmarkierungen, die in den Einsatzumgebungen installiert sind. Bei diesen Systemen gibt es jedoch einen hohen Installationsaufwand, was die Entwicklung von Robotersystemen, die sich mithilfe ihrer verbauten Sensorik orientieren, vorantreibt. Es existiert zwar eine Vielzahl an Robotern die dafür verwendet werden können. Die Entwicklung der Steuerungssoftware ist aber immer noch Teil der Forschung. Für die Steuerung wird eine Umgebungskarte benötigt, an der sich der Roboter orientieren kann. Hierfür eignen sich besonders SLAM-Verfahren, die simultanes Lokalisieren und Kartographieren durchführen. Dabei baut der Roboter während seiner Bewegung durch den Raum mithilfe seiner Sensordaten eine Umgebungskarte auf und lokalisiert sich daran, um seine Position auf der Karte exakt zu bestimmen. Im Laufe dieser Arbeit wurden über 30 verschiedene SLAM Implementierungen bzw. Umsetzungen gefunden die das SLAM Problem lösen. Diese sind jedoch größtenteils an spezielle Systembzw. Umgebungsvoraussetzungen angepasste eigenständige Implementierungen. Es existiert keine öffentlich zugängliche Übersicht, die einen Vergleich aller bzw. des Großteils der Verfahren, z.B. in Bezug auf ihre Funktionsweise, Systemvoraussetzungen (Sensorik, Roboterplattform), Umgebungsvoraussetzungen (Indoor, Outdoor, ...), Genauigkeit oder Geschwindigkeit, gibt. Viele dieser SLAMs besitzen Implementierungen und Dokumentationen in denen ihre Einsatzgebiete, Testvoraussetzungen oder Weiterentwicklungen im Vergleich zu anderen SLAMVerfahren beschrieben werden, was aber bei der großen Anzahl an Veröffentlichungen das Finden eines passenden SLAM-Verfahrens nicht erleichtert. Bei einer solchen Menge an SLAM-Verfahren und Implementierungen stellen sich aus softwaretechnologischer Sicht folgende Fragen: 1. Besteht die Möglichkeit einzelne Teile des SLAM wiederzuverwenden? 2. Besteht die Möglichkeit einzelne Teile des SLAM dynamisch auszutauschen? Mit dieser Arbeit wird das Ziel verfolgt, diese beiden Fragen zu beantworten. Hierfür wird zu Beginn eine Übersicht über alle gefundenen SLAMs aufgebaut um diese in ihren grundlegenden Eigenschaften zu unterscheiden. Aus der Vielzahl von Verfahren werden die rasterbasierten Verfahren, welche Laserscanner bzw. Tiefenbildkamera als Sensorik verwenden, als zu untersuchende Menge ausgewählt. Diese Teilmenge an SLAM-Verfahren wird hinsichtlich ihrer nichtfunktionalen Eigenschaften genauer untersucht und versucht in Komponenten zu unterteilen, welche in mehreren verschiedenen Implementierungen wiederverwendet werden können. Anhand der extrahierten Komponenten soll ein Featurebaum aufgebaut werden, der dem Anwender einen Überblick und die Möglichkeit bereitstellt SLAM-Verfahren nach speziellen Kriterien (Systemvoraussetzungen, Umgebungen, ...) zusammenzusetzen bzw. zur Laufzeit anzupassen. Dafür müssen die verfügbaren SLAM Implementierungen und dazugehörigen Dokumentationen in Bezug auf ihre Gemeinsamkeiten und Unterschiede analysiert werden.

To navigate successfully in a previously unexplored environment, a mobile robot must be able to estimate the spatial relationships of the objects of interest accurately. A Simultaneous Localization and Mapping (SLAM) sys- tem employs its sensors to build incrementally a map of its surroundings and to localize itself in the map simultaneously. The aim of this research project is to develop a SLAM system suitable for self propelled household lawnmowers. The proposed bearing-only SLAM system requires only an omnidirec- tional camera and some inexpensive landmarks. The main advantage of an omnidirectional camera is the panoramic view of all the landmarks in the scene. Placing landmarks in a lawn field to define the working domain is much easier and more flexible than installing the perimeter wire required by existing autonomous lawnmowers. The common approach of existing bearing-only SLAM methods relies on a motion model for predicting the robot’s pose and a sensor model for updating the pose. In the motion model, the error on the estimates of object positions is cumulated due mainly to the wheel slippage. Quantifying accu- rately the uncertainty of object positions is a fundamental requirement. In bearing-only SLAM, the Probability Density Function (PDF) of landmark position should be uniform along the observed bearing. Existing methods that approximate the PDF with a Gaussian estimation do not satisfy this uniformity requirement. This thesis introduces both geometric and proba- bilistic methods to address the above problems. The main novel contribu- tions of this thesis are: 1. A bearing-only SLAM method not requiring odometry. The proposed method relies solely on the sensor model (landmark bearings only) without relying on the motion model (odometry). The uncertainty of the estimated landmark positions depends on the vision error only, instead of the combination of both odometry and vision errors. 2. The transformation of the spatial uncertainty of objects. This thesis introduces a novel method for translating the spatial un- certainty of objects estimated from a moving frame attached to the robot into the global frame attached to the static landmarks in the environment. 3. The characterization of an improved PDF for representing landmark position in bearing-only SLAM. The proposed PDF is expressed in polar coordinates, and the marginal probability on range is constrained to be uniform. Compared to the PDF estimated from a mixture of Gaussians, the PDF developed here has far fewer parameters and can be easily adopted in a probabilistic framework, such as a particle filtering system. The main advantages of our proposed bearing-only SLAM system are its lower production cost and flexibility of use. The proposed system can be adopted in other domestic robots as well, such as vacuum cleaners or robotic toys when terrain is essentially 2D.

Les travaux réalisés au cours de cette thèse s’inscrivent dans la problématique de localisation en temps réel d’une caméra par vision monoculaire. Dans la littérature, il existe différentes méthodes qui peuvent être classées en trois catégories. La première catégorie de méthodes considère une caméra évoluant dans un environnement complètement inconnu (SLAM). Cette méthode réalise une reconstruction enligne de primitives observées dans des images d’une séquence vidéo et utilise cette reconstruction pour localiser la caméra. Les deux autres permettent une localisation par rapport à un objet 3D de la scène en s’appuyant sur la connaissance, a priori, d’un modèle de cet objet (suivi basé modèle). L’une utilise uniquement l’information du modèle 3D de l’objet pour localiser la caméra, l’autre peut être considérée comme l’intermédiaire entre le SLAM et le suivi basé modèle. Cette dernière méthode consiste à localiser une caméra par rapport à un objet en utilisant, d’une part, le modèle de ce dernier et d’autre part, une reconstruction en ligne des primitives de l’objet d’intérêt. Cette reconstruction peut être assimilée à une mise à jour du modèle initial (suivi basé modèle avec mise à jour). Chacune de ces méthodes possède des avantages et des inconvénients. Dans le cadre de ces travaux de thèse, nous proposons une solution unifiant l’ensemble de ces méthodes de localisation dans un unique cadre désigné sous le terme de SLAM contraint. Cette solution, qui unifie ces différentes méthodes, permet de tirer profit de leurs avantages tout en limitant leurs inconvénients respectifs. En particulier, nous considérons que la caméra évolue dans un environnement partiellement connu, c’est-à-dire pour lequel un modèle (géométrique ou photométrique) 3D d’un objet statique de la scène est disponible. L’objectif est alors d’estimer de manière précise la pose de la caméra par rapport à cet objet 3D. L’information absolue issue du modèle 3D de l’objet d’intérêt est utilisée pour améliorer la localisation de type SLAM en incluant cette information additionnelle directement dans le processus d’ajustement de faisceaux. Afin de pouvoir gérer un large panel d’objets 3D et de scènes, plusieurs types de contraintes sont proposées dans ce mémoire. Ces différentes contraintes sont regroupées en deux approches. La première permet d’unifier les méthodes SLAM et de suivi basé modèle, en contraignant le déplacement de la caméra via la projection de primitives existantes extraites du modèle 3D dans les images. La seconde unifie les méthodes SLAM et de suivi basé modèle avec mise à jour en contraignant les primitives reconstruites par le SLAM à appartenir à la surface du modèle (unification SLAM et mise à jour du modèle). Les avantages de ces différents ajustements de faisceaux contraints, en terme de précision, de stabilité de recalage et de robustesse aux occultations, sont démontrés sur un grand nombre de données de synthèse et de données réelles. Des applications temps réel de réalité augmentée sont également présentées sur différents types d’objets 3D. Ces travaux ont fait l’objet de 4 publications internationales, de 2 publications nationales et d’un dépôt de brevet. / This thesis tackles the problem of real time location of a monocular camera. In the literature, there are different methods which can be classified into three categories. The first category considers a camera moving in a completely unknown environment (SLAM). This method performs an online reconstruction of the observed primitives in the images and uses this reconstruction to estimate the location of the camera. The two other categories of methods estimate the location of the camera with respect to a 3D object in the scene. The estimation is based on an a priori knowledge of a model of the object (Model-based). One of these two methods uses only the information of the 3D model of the object to locate the camera. The other method may be considered as an intermediary between the SLAM and Model-based approaches. It consists in locating the camera with respect to the object of interest by using, on one hand the 3D model of this object, and on the other hand an online reconstruction of the primitives of the latter. This last online reconstruction can be regarded as an update of the initial 3D model (Model-based with update). Each of these methods has advantages and disadvantages. In the context of this thesis, we propose a solution in order to unify all these localization methods in a single framework referred to as the constrained SLAM, by taking parts of their benefits and limiting their disadvantages. We, particularly, consider that the camera moves in a partially known environment, i.e. for which a 3D model (geometric or photometric) of a static object in the scene is available. The objective is then to accurately estimate the pose (position and orientation) of the camera with respect to this object. The absolute information provided by the 3D model of the object is used to improve the localization of the SLAM by directly including this additional information in the bundle adjustment process. In order to manage a wide range of 3D objets and scenes, various types of constraints are proposed in this study and grouped into two approaches. The first one allows to unify the SLAM and Model-based methods by constraining the trajectory of the camera through the projection, in the images, of the 3D primitives extracted from the model. The second one unifies the SLAM and Model-based with update methods, by constraining the reconstructed 3D primitives of the object to belong to the surface of the model (unification SLAM and model update). The benefits of the constrained bundle adjustment framework in terms of accuracy, stability, robustness to occlusions, are demonstrated on synthetic and real data. Real time applications of augmented reality are also presented on different types of 3D objects. This work has been the subject of four international publications, two national publications and one patent.