Finding salient features in an image, and matching them to their corresponding features in another image is an important step for many vision-based applications. Feature description plays an important role in the feature matching process. A robust feature descriptor must works with a number of image deformations and should be computationally efficient. For resource-limited systems, floating point and complex operations such as multiplication and square root are not desirable. This research first introduces a robust and efficient feature descriptor called PRObability (PRO) descriptor that meets these requirements without sacrificing matching accuracy. The PRO descriptor is further improved by incorporating only affine features for matching. While performing well, PRO descriptor still requires larger descriptor size, higher offline computation time, and more memory space than other binary feature descriptors. SYnthetic BAsis (SYBA) descriptor is developed to overcome these drawbacks. SYBA is built on the basis of a new compressed sensing theory that uses synthetic basis functions to uniquely encode or reconstruct a signal. The SYBA descriptor is designed to provide accurate feature matching for real-time vision applications. To demonstrate its performance, we develop algorithms that utilize SYBA descriptor to localize the soccer ball in a broadcast soccer game video, track ground objects for unmanned aerial vehicle, and perform motion analysis, and improve visual odometry accuracy for advanced driver assistance systems. SYBA provides high feature matching accuracy with computational simplicity and requires minimal computational resources. It is a hardware-friendly feature description and matching algorithm suitable for embedded vision applications.

GPS/IMU integrated systems are commonly used for vehicle navigation. The algorithm for this coupled system is normally based on Kalman filter. However, oscillated GPS measurements in the urban environment can lead to localization divergence easily. Moreover, heading estimation may be sensitive to magnetic interference if it relies on IMU with integrated magnetometer. This report tries to solve the localization problem on GPS oscillation and outage, based on adaptive extended Kalman filter(AEKF). In terms of the heading estimation, stereo visual odometry(VO) is fused to overcome the effect by magnetic disturbance. Vision-aided AEKF based algorithm is tested in the cases of both good GPS condition and GPS oscillation with magnetic interference. Under the situations considered, the algorithm is verified to outperform conventional extended Kalman filter(CEKF) and unscented Kalman filter(UKF) in position estimation by 53.74% and 40.09% respectively, and decrease the drifting of heading estimation. / GPS/IMU integrerade system används ofta för navigering av fordon. Algoritmen för detta kopplade system är normalt baserat på ett Kalmanfilter. Ett problem med systemet är att oscillerade GPS mätningar i stadsmiljöer enkelt kan leda till en lokaliseringsdivergens. Dessutom kan riktningsuppskattningen vara känslig för magnetiska störningar om den är beroende av en IMU med integrerad magnetometer. Rapporten försöker lösa lokaliseringsproblemet som skapas av GPS-oscillationer och avbrott med hjälp av ett adaptivt förlängt Kalmanfilter (AEKF). När det gäller riktningsuppskattningen används stereovisuell odometri (VO) för att försvaga effekten av magnetiska störningar genom sensorfusion. En Visionsstödd AEKF-baserad algoritm testas i fall med både goda GPS omständigheter och med oscillationer i GPS mätningar med magnetiska störningar. Under de fallen som är aktuella är algoritmen verifierad för att överträffa det konventionella utökade Kalmanfilteret (CEKF) och ”Unscented Kalman filter” (UKF) när det kommer till positionsuppskattning med 53,74% respektive 40,09% samt minska fel i riktningsuppskattningen.

<p>    </p> <p>Image data remains an important tool for post-event building assessment and documentation. After each natural hazard event, significant efforts are made by teams of engineers to visit the affected regions and collect useful image data. In general, a global positioning system (GPS) can provide useful spatial information for localizing image data. However, it is challenging to collect such information when images are captured in places where GPS signals are weak or interrupted, such as the indoor spaces of buildings. An inability to document the images’ locations would hinder the analysis, organization, and documentation of these images as they lack sufficient spatial context. This problem becomes more urgent to solve for the inspection mission covering a large area, like a community. To address this issue, the objective of this research is to generate a tool to automatically process the image data collected during such a mission and provide the location of each image. Towards this goal, the following tasks are performed. First, I develop a methodology to localize images and link them to locations on a structural drawing (Task 1). Second, this methodology is extended to be able to process data collected from a large scale area, and perform indoor localization for images collected on each of the indoor floors of each individual building (Task 2). Third, I develop an automated technique to render the damage condition decision of buildings by fusing the image data collected within (Task 3). The methods developed through each task have been evaluated with data collected from real world buildings. This research may also lead to automated assessment of buildings over a large scale area. </p>

Feature extractors in Visual Odometry pipelines rarely exploit depth signals, even though depth sensors and RGB-D cameras are commonly used in later stages of Visual Odometry systems. Nonetheless, depth sensors from RGB-D cameras function even with no external light and can provide feature extractors with additional structural information otherwise invisible in RGB images. Deep Learning feature extractors, which have recently been shown to outperform their classical counterparts, still only exploit RGB information. Against this background, this thesis presents a Self-Supervised Deep Learning feature extraction algorithm that employs both RGB and depth signals as input. The proposed approach builds upon the existing deep learning feature extractors, adapting the architecture and training procedure to introduce the depth signal. The developed RGB-D system is compared with an RGB-only feature extractor in a qualitative study on keypoints’ location and a quantitative evaluation on pose estimation. The qualitative evaluation demonstrates that the proposed system exploits information from both RGB and depth domains, and it robustly adapts to the degradation of either of the two input signals. The pose estimation results indicate that the RGB-D system performs comparably to the RGB-only one in normal and low-light conditions. Thanks to the usage of depth information, the RGB-D feature extractor can still operate, showing only limited performance degradation, even in completely dark environments, where RGB methods fail due to a lack of input information. The combined qualitative and quantitative results suggest that the proposed system extracts features based on both RGB and depth input domains and can autonomously transition from normal brightness to a no-light environment, by exploiting depth signal to compensate for the degraded RGB information. / Detektering av nyckelpunkter för Visuell Odometri (VO) utnyttjar sällan information om djup i bilder, även om avståndssensorer och RGB-D-kameror ofta används i senare skeden av VO pipelinen. RGB-D-kamerors avståndsestimering fungerar även utan externt ljus. De kan förse nyckelpunktsdetektorer med ytterligare strukturell information som är svårt att extrahera enbart från RGB-bilder. Detektering av nyckelpunkter, med hjälp av Deep Learning metoder, har nyligen visat sig överträffa sina klassiska motsvarigheter som fortfarande endast utnyttjar bildinformation. Denna avhandling presenterar en algoritm för självövervakande nyckelpunktsdetektering med djupinlärning, som använder både RGB-bilder och avståndsinformation som indata. Det föreslagna tillvägagångssättet bygger på en befintlig arkitektur, som har anpassats för att också kunna hantera informationen om djupet i bilder. Den utvecklade RGB-D nyckelpunktsdetektorn har jämförts med en detektor som enbart baseras på RGB-bilder. Det har både gjorts en kvalitativ utvärdering av nyckelpunkternas läge och en kvantitativ utvärdering av detektorns förmåga på VO-tillämpningar, dvs estimering av position och orientering. Den kvalitativa utvärderingen av nyckelpunkterna visar att det föreslagna systemet kan utnyttja både information från bild- och djupdomänen. Den visar även att detektorn är robust mot försämringar av båda bilderna och djupinformationen. Evalueringen visar att den utvecklade RGB-D-metoden och en standardetektor uppnår jämförbara resultat under normala och svaga ljusförhållanden. Dock, tack vare användningen av tillgänglig djupinformation kan RGB-D-metoden fortfarande fungera i helt mörka förhållanden, med endast begränsad försämring av prestanda. I dessa scenarion misslyckas RGB-metoder på grund av brist på användbar bildinformation. De kombinerade kvalitativa och kvantitativa resultaten tyder på att det föreslagna systemet extraherar egenskaper som baseras på både bild- och djupinmatningsområden och kan självständigt övergå mellan normala och ljusfattiga förhållanden genom att utnyttja djup för att kompensera för den försämrade bildinformationen.

Feature extraction is an essential part of the Visual Odometry problem. In recent years, with the rise of Neural Networks, the problem has shifted from a more classical to a deep learning approach. This thesis presents a fine-tuned feature extraction network trained on pose estimation as a proxy task. The architecture aims at integrating inertial information coming from IMU sensor data in the deep local feature extraction paradigm. Specifically, visual features and inertial features are extracted using Neural Networks. These features are then fused together and further processed to regress the pose of a moving agent. The visual feature extraction network is effectively fine-tuned and is used stand-alone for inference. The approach is validated via a qualitative analysis on the keypoints extracted and also in a more quantitative way. Quantitatively, the feature extraction network is used to perform Visual Odometry on the Kitti dataset where the ATE for various sequences is reported. As a comparison, the proposed method, the proposed without IMU and the original pre-trained feature extraction network are used to extract features for the Visual Odometry task. Their ATE results and relative trajectories show that in sequences with great change in orientation the proposed system outperforms the original one, while on mostly straight sequences the original system performs slightly better. / Feature extraktion är en viktig del av visuell odometri (VO). Under de senaste åren har framväxten av neurala nätverk gjort att tillvägagångsättet skiftat från klassiska metoder till Deep Learning metoder. Denna rapport presenterar ett kalibrerat feature extraheringsnätverk som är tränat med posesuppskattning som en proxyuppgift. Arkitekturen syftar till att integrera tröghetsinformation som kommer från sensordata i feature extraheringsnätverket. Specifikt extraheras visuella features och tröghetsfeatures med hjälp av neurala nätverk. Dessa features slås ihop och bearbetas ytterligare för att estimera position och riktning av en rörlig kamera. Metoden har undersökts genom en kvalitativ analys av featurepunkternas läge men även på ett mer kvantitativt sätt där VO-estimering på olika bildsekvenser från KITTI-datasetet har jämförts. Resultaten visar att i sekvenser med stora riktningsförändringar överträffar det föreslagna systemet det ursprungliga, medan originalsystemet presterar något bättre på sekvenser som är mestadels raka.

Visual Odometry (VO) is the process of estimating the relative motion of a vehicle by using solely image data gathered from the camera. In underwater environments, VO becomes extremely challenging but valuable since ordinary sensors for on-road localization are usually unpractical in these hostile environments. For years, VO methods have been purely based on Computer Vision (CV) principles. However, the recent advances in Deep Learning (DL) have ushered in a new era for VO approaches. These novel methods have achieved impressive performance with state-of-the-art results on urban datasets. Nevertheless, little effort has been made to push learning-based research towards natural environments, such as underwater. Consequently, this work aims to bridge the research gap by evaluating the effectiveness of the learning-based approach in the navigation of Autonomous Underwater Vehicles (AUVs). We compare two learning-based methods with a traditional feature-based method on the Underwater Caves dataset, a very challenging dataset collected in the unstructured environment of an underwater cave complex. Extensive experiments are thus conducted training the models on this dataset. Moreover, we investigate different aspects and propose several improvements, such as sub-sampling the video clips to emphasize the camera motion between consecutive frames, or training exclusively on images with relevant content discarding those with dark borders and representing solely sandy bottoms. Finally, during the training, we also leverage underwater images from other datasets, hence acquired from different cameras. However, the best improvement is obtained by penalizing rotations around the x-axis of the camera coordinate system. The three methods are evaluated on test sequences that cover different lighting conditions. In the most favorable environments, although learning-based methods are not up to par with the feature-based method, the results show great potential. Furthermore, in extreme lighting conditions, where the feature-based baseline sharply fails to bootstrap, one of the two learning-based methods produces instead qualitatively good trajectory results, revealing the power of the learning-based approach in this peculiar context. / Visuell Odometri (VO) används för att uppskatta den relativa rörelsen för ett fordon med hjälp av enbart bilddata från en eller flera kameror. I undervattensmiljöer blir VO extremt utmanande men värdefullt eftersom vanliga sensorer för lokalisering vanligtvis är opraktiska i dessa svåra miljöer. I åratal har VO-metoder enbart baserats på klassisk datorseende. De senaste framstegen inom djupinlärning har dock inlett en ny era för VO-metoder. Dessa nya metoder har uppnått imponerande prestanda på dataset urbana miljöer. Trots detta har ganska lite gjorts för att driva den inlärningsbaserad forskningen mot naturliga miljöer, till exempel under vattnet. Följaktligen syftar detta arbete till att överbrygga forskningsgapet genom att utvärdera effektiviteten hos det inlärningsbaserade tillvägagångssättet vid navigering av autonoma undervattensfordon (AUV). Vi jämför två inlärningsbaserade metoder med en traditionell nyckelpunktsbaserad metod som referens. Vi gör jämförelsen på Underwater Caves-datasetet, ett mycket utmanande dataset som samlats in i den ostrukturerade miljön i ett undervattensgrottkomplex. Omfattande experiment utförs för att träna modellerna på detta dataset. Vi undersöker också olika aspekter och föreslår flera förbättringar, till exempel, att delsampla videoklippen för att betona kamerarörelsen mellan på varandra följande bildrutor, eller att träna på en delmängd av datasetet bestående uteslutande på bilder med relevant innehåll för att förbättra skattningen av rörelsen. Under träningen utnyttjar vi också undervattensbilder från andra datamängder, och därmed från olika kameror. Den bästa förbättringen uppnås dock genom att straffa skattningar av stora rotationer runt kamerakoordinatsystemets x-axel. De tre metoderna utvärderas på testsekvenser som täcker olika ljusförhållanden. I de mest gynnsamma miljöerna visar resultaten stor potential, även om de inlärningsbaserade metoder inte är i nivå med den traditionella referensmetoden. Vid extrema ljusförhållanden, där referensmetoden misslyckas att ens initialisera, ger en av de två inlärningsbaserade metoderna istället kvalitativt bra resultat, vilket demonstrerar kraften i det inlärningsbaserade tillvägagångssättet i detta specifika sammanhang.

No description available.

Intelligent vehicles require perception systems with high performances. Usually, perception system consists of multiple sensors, such as cameras, 2D/3D lidars or radars. The works presented in this Ph.D thesis concern several topics on cameras and lidar based perception for understanding dynamic scenes in urban environments. The works are composed of four parts.In the first part, a stereo vision based visual odometry is proposed by comparing several different approaches of image feature detection and feature points association. After a comprehensive comparison, a suitable feature detector and a feature points association approach is selected to achieve better performance of stereo visual odometry. In the second part, independent moving objects are detected and segmented by the results of visual odometry and U-disparity image. Then, spatial features are extracted by a kernel-PCA method and classifiers are trained based on these spatial features to recognize different types of common moving objects e.g. pedestrians, vehicles and cyclists. In the third part, an extrinsic calibration method between a 2D lidar and a stereoscopic system is proposed. This method solves the problem of extrinsic calibration by placing a common calibration chessboard in front of the stereoscopic system and 2D lidar, and by considering the geometric relationship between the cameras of the stereoscopic system. This calibration method integrates also sensor noise models and Mahalanobis distance optimization for more robustness. At last, dynamic occupancy grid mapping is proposed by 3D reconstruction of the environment, obtained from stereovision and Lidar data separately and then conjointly. An improved occupancy grid map is obtained by estimating the pitch angle between ground plane and the stereoscopic system. The moving object detection and recognition results (from the first and second parts) are incorporated into the occupancy grid map to augment the semantic meanings. All the proposed and developed methods are tested and evaluated with simulation and real data acquired by the experimental platform "intelligent vehicle SetCar" of IRTES-SET laboratory.

Dans ce travail, nous proposons une représentation efficace de l’environnement adaptée à la problématique de la navigation autonome. Cette représentation topométrique est constituée d’un graphe de sphères de vision augmentées d’informations de profondeur. Localement la sphère de vision augmentée constitue une représentation égocentrée complète de l’environnement proche. Le graphe de sphères permet de couvrir un environnement de grande taille et d’en assurer la représentation. Les "poses" à 6 degrés de liberté calculées entre sphères sont facilement exploitables par des tâches de navigation en temps réel. Dans cette thèse, les problématiques suivantes ont été considérées : Comment intégrer des informations géométriques et photométriques dans une approche d’odométrie visuelle robuste ; comment déterminer le nombre et le placement des sphères augmentées pour représenter un environnement de façon complète ; comment modéliser les incertitudes pour fusionner les observations dans le but d’augmenter la précision de la représentation ; comment utiliser des cartes de saillances pour augmenter la précision et la stabilité du processus d’odométrie visuelle. / Our aim is concentrated around building ego-centric topometric maps represented as a graph of keyframe nodes which can be efficiently used by autonomous agents. The keyframe nodes which combines a spherical image and a depth map (augmented visual sphere) synthesises information collected in a local area of space by an embedded acquisition system. The representation of the global environment consists of a collection of augmented visual spheres that provide the necessary coverage of an operational area. A "pose" graph that links these spheres together in six degrees of freedom, also defines the domain potentially exploitable for navigation tasks in real time. As part of this research, an approach to map-based representation has been proposed by considering the following issues : how to robustly apply visual odometry by making the most of both photometric and ; geometric information available from our augmented spherical database ; how to determine the quantity and optimal placement of these augmented spheres to cover an environment completely ; how tomodel sensor uncertainties and update the dense infomation of the augmented spheres ; how to compactly represent the information contained in the augmented sphere to ensure robustness, accuracy and stability along an explored trajectory by making use of saliency maps.

Les robots et véhicules autonomes représentent le futur des modes de déplacements et de production. Les enjeux de l’avenir reposent sur la robustesse de leurs perceptions et flexibilité face aux environnements changeant et situations inattendues. Les capteurs stéréoscopiques sont des capteurs passifs qui permettent d'obtenir à la fois image et information 3D de la scène à la manière de la vision humaine. Dans ces travaux nous avons développé un système de localisation, par odométrie visuelle permettant de déterminer la position dans l'espace du capteur de façon efficace et performante en tirant partie de la carte de profondeur dense mais également associé à un système de SLAM, rendant la localisation robuste aux perturbations et aux décalages potentiels. Nous avons également développé plusieurs solutions de cartographie et interprétation d’obstacles, à la fois pour le véhicule aérien et terrestre. Ces travaux sont en partie intégrés dans des produits commerciaux. / Autonomous vehicles and robots represent the future of transportation and production industries. The challenge ahead will come from the robustness of perception and flexibility from unexpected situations and changing environments. Stereoscopic cameras are passive sensors that provide color images and depth information of the scene by correlating 2 images like the human vision. In this work, we developed a localization system, by visual odometry that can determine efficiently the position in space of the sensor by exploiting the dense depth map. It is also combined with a SLAM system that enables robust localization against disturbances and potentials drifts. Additionally, we developed a few mapping and obstacles detections solutions, both for aerial and terrestrial vehicles. These algorithms are now partly integrated into commercial products.