• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 233
  • 44
  • 44
  • 34
  • 17
  • 13
  • 12
  • 9
  • 6
  • 6
  • 5
  • 1
  • Tagged with
  • 482
  • 110
  • 104
  • 102
  • 94
  • 92
  • 87
  • 78
  • 60
  • 55
  • 50
  • 48
  • 47
  • 46
  • 44
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
311

Fault-tolerant mapping and localization for Quadrotor UAV

Gilson, Maximillian Andrew January 2019 (has links)
No description available.
312

ROS-based implementation of a model car with a LiDAR and camera setup

Nises, Marcus January 2023 (has links)
The aim of this project is to implement a Radio Controlled (RC) car with a Light Detection and Ranging (LiDAR) sensor and a stereoscopic camera setup based on the Robot Operating System (ROS) to conduct Simultaneous Localization and Mapping (SLAM). The LiDAR sensor used is a 2D LiDAR, RPlidar A1, and the stereoscopic camera setup is made of two monocular cameras, Raspberry Pi Camera v2. The sensors were mounted on the RC car and connected using two Raspberry Pi microcomputers.  The 2D LiDAR sensor was used for two-dimensional mapping and the stereo vision from the camera setup for three-dimensional mapping. RC car movement information, odometry, necessary for SLAM was derived using either the LiDAR data or the data from the stereoscopic camera setup. Two means of SLAM were implemented both separately and together for mapping an office space. The SLAM algorithms adopted the Real Time Appearance Based Mapping (RTAB-map) package in the open-source ROS.    The results of the mapping indicated that the RPlidar A1 was able to provide a precise mapping, but showed difficulty when mapping in large circular patterns as the odometry drift resulted in the mismatch of the current mapping with the earlier mapping of the same positions and secondly in localization when turning quickly. The camera setup derived more information about surrounding and showed more robust odometry. However, the setup performed poorly for the mapping of visual loop closures, i.e., the current mapping did not match the earlier mapping of earlier visited positions.
313

Kartläggning av källor till utsläpp av mikroplaster från verksamheter inom Käppalaförbundets upptagningsområde / Mapping of sources that give emissions of microplastics from activities within the Käppala Association´s WWTP catchment area

Jeppsson, Frida January 2017 (has links)
Mikroplast har på senare tid blivit allt mer uppmärksammat och varje dag kommer nya artiklar om mikroplasts förekomst eller verkan. Mikroplaster är små fragment, fibrer eller granuler av plast som vanligtvis definieras som plastpartiklar mindre än 5 mm och större än 100 nm i diameter. Förekomst av mikroplast är ett stort miljöproblem då de visat sig ge skadliga effekter på vattenlevande organismer. Organismerna förväxlar mikroplaster med plankton och får på så sätt i sig mikroplast i stället för föda. Det finns betydligt färre studier gjorda på hur marklevande organismer påverkas av mikroplast, men mikroplast misstänks även kunna innebära problem när slam sprids på åkermark. Svenska kustvatten tar emot mikroplast från både land- och havsbaserade källor. Däribland har avloppsreningsverk pekats ut som spridningsväg av mikroplast till miljön. Hushåll anses i sin tur stå för en del av mikroplastutsläppen till avloppsreningsverken. Utifrån bristfällig information gällande vilka mängder av mikroplast som tillförs avloppsreningsverken från verksamheter och industrier, önskade Käppalaförbundet en kartläggning av vilka verksamheter inom deras upptagningsområde som kan vara källor till utsläpp av mikroplaster till spillvattennätet. Denna studie inkluderar även en diskussion om lämplig analysmetod för att kvantifiera mängderna mikroplast. Käppalaförbundet är ett avloppsreningsverk lokaliserat på Lidingö som renar vatten från 500 000 anslutna personer från elva medlemskommuner, industrier och verksamheter norr och öster om Stockholm. Målet med examensarbetet var att öka kunskapen om vilka verksamheter som bidrar med ett utsläpp av mikroplaster till spillvattennätet. Metoden för att identifiera källorna var litteraturstudier och databasen EnvoMap, vilken innehåller information om verksamheter kopplade till Käppalaverket. Intervjuer har gjorts med verksamheter och miljökontor i respektive kommun i syfte att ta reda på om verksamheterna har processvattenanslutning till Käppalaverket och vad de har för utsläpp. Verksamheter som undersöktes var tvätterier, badanläggningar, fordonstvättar, tillverkning av skönhetsprodukter samt verksamheter med plast som råvara i produktionen. En uppskattning om hur mycket mikroplaster som når Käppalaverket varje år gjordes. Tvätteriers mikroplastutsläpp har kunnat kvantifieras. De står för en förhållandevis liten del av utsläppet mikroplast till i avloppsnätet. Det saknas data för att kunna kvantifiera mängderna mikroplast från badanläggningar och fordonstvätt, men båda verksamheterna är potentiella källor till utsläpp av mikroplast i Käppalaförbundets upptagnings-område. Denna studie uppskattar att inget utsläpp av mikroplaster sker från plastindustrier. Med största sannolikhet är mängderna mikroplast från tillverkningsprocessen av skönhetsprodukter obetydliga på grund av att ytterst små mängder når spillvattennätet. Analysmetoden som rekommenderas för att analysera mikroplaster är FT-IR-bildbehandling med Focal Plane Array, då metoden tillåter kvantifiering av massa, partikelantal och information om vilka typer av polymerer mikroplasten innehåller. En hel del kunskapsluckor har identifierats under arbetets gång. Det saknas till exempel data för att kvantifiera mängderna från identifierade potentiella verksamheter och fenomen som ”fulspolningar”. ”Fulspolningar” innebär att föremål och partiklar som inte hör hemma i avloppet ändå hamnar där. Examenarbetet bör ses som en första studie och behöver följas upp med fler analyser som undersöker om det sker mikroplastutsläpp från dessa källor. En fortsatt inventering av andra verksamheter behövs också. Sjukhus och företag som blästrar med plastkulor är exempel på verksamheter som inte rymts inom det här arbetet. Sammanfattningsvis går det att konstatera att trots ständig publicering av nya data om mikroplast så är informationen på många plan bristfällig. Vilka mängder mikroplast som härrör från olika källor är svåra att kvantifiera och de uppskattningar som gjorts i arbetet innefattar ett stort mått av osäkerhet. / In recent years, microplastics have been more frequently recognized and new articles about its presence and effects are published every day. Microplastics are small fragments, fibers or granules of plastics that usually are defined as particles smaller than 5 mm and bigger than 100 nm in diameter. The presence of microplastics have been recognized as a major environmental threat, because microplastics have proven to cause damage to aquatic organisms. These organisms ingest the microplastics by mistake, instead of plankton, while feeding. Significantly fewer studies have been carried out to analyze how terrestrial organisms have been affected by microplastics but it has been suspected that microplastics may serve as a threat when mud is spread on arable soil. Swedish coastal waters receive microplastics from sources originating both from the ocean and terrestrial origins. Sewage plants serve as one of several different sources from which microplastics are being spread. The spread of microplastics through sewage plants is very much due to the significant emission levels coming from the vast number of households. Due to insufficient information regarding the different industries, services and facilities and the volumes of microplastics that they disperse, Käppalaförbundet asked for a mapping of which activities within its catchment area that may represent sources of the spreading of microplastics to the wastewater network. A study of that nature should also include a discussion about reasonable methods of analytics for quantify the amounts of microplastics. Käppalaförbundet is a sewage plant located at Lidingö, which purifies water from 502 000 people from 11 member counties, industries and businesses North and East of Stockholm. The objective of this project was to increase the awareness regarding which activities and industries that cause the emission of microplastics to the wastewater network. The methods to identify the sources were literature studies and the EnvoMap database, which contains activities connected to the Käppalaverket. In addition, interviews with businesses and offices with environmental responsibilities have been conducted in each counties. The purpose is to gain information about the water processes, and if there are any connection to Käppalaverket and their emissions. Businesses that were investigated was laundromats, swimming facilities, car washes, manufacturing cosmetic products and businesses that uses plastics as their primary product. Part of the research included an estimate regarding the amount of microplastics that reach the Käppalaverket each year. Laundromats emission of microplastics have been quantified. They only make up a small portion of the total emission of microplastics related to the sewage network. Lack of data have made it difficult to quantify the amount of microplastics coming from swimming facilities and car washes but both facilities are potential sources for emission of microplastics in the catchment area of Käppalaförbundet. This study estimates that there is no emission of microplastics that originates from plastic industries. The amounts of microplastics from cosmetic production are most likely insignificant due to the fact that extremely small amounts reach the wastewater network. The recommended method to analyze microplastics is FTIR-image processing with Focal Plane Array. As this method allows quantification of weight, numbers of particles and information about which types of polymers the microplastics contain. Throughout the project, several knowledge-gaps have been identified. For example, data that may quantify the different amounts of emissions coming from pre-identified sources as well as the amount of incorrect draining procedures are not available. The amount of incorrect draining procedures relates to waste that do not belong in the drain but nevertheless end up in the system. This project should be viewed as an initial study and needs further analysis that investigates whether microplastic emissions from these sources occur. In addition, continued check-ups are needed to determine the inventory associated with other facilities. Hospitals and businesses in the plastic bullet industry are examples of some facilities that have not been covered in this project. In summary, it can be established that regardless of that new data on microplastics is constantly being published, it remains clear that the information is very much inadequate. What amounts of microplastics that originate from the different sources are difficult to quantify and the estimations that have been presented in this report contain high levels of uncertainty.
314

Robustness of State-of-the-Art Visual Odometry and SLAM Systems / Robusthet hos moderna Visual Odometry och SLAM system

Mannila, Cassandra January 2023 (has links)
Visual(-Inertial) Odometry (VIO) and Simultaneous Localization and Mapping (SLAM) are hot topics in Computer Vision today. These technologies have various applications, including robotics, autonomous driving, and virtual reality. They may also be valuable in studying human behavior and navigation through head-mounted visual systems. A complication to SLAM and VIO systems could potentially be visual degeneration such as motion blur. This thesis attempts to evaluate the robustness to motion blur of two open-source state-of-the-art VIO and SLAM systems, namely Delayed Marginalization Visual-Inertial Odometry (DM-VIO) and ORB-SLAM3. There are no real-world benchmark datasets with varying amounts of motion blur today. Instead, a semi-synthetic dataset was created with a dynamic trajectory-based motion blurring technique on an existing dataset, TUM VI. The systems were evaluated in two sensor configurations, Monocular and Monocular-Inertial. The systems are evaluated using the Root Mean Square (RMS) of the Absolute Trajectory Error (ATE).  Based on the findings, the visual input highly influences DM-VIO, and performance decreases substantially as motion blur increases, regardless of the sensor configuration. In the Monocular setup, the performance decline significantly going from centimeter precision to decimeter. The performance is slightly improved using the Monocular-Inertial configuration. ORB-SLAM3 is unaffected by motion blur performing on centimeter precision, and there is no significant difference between the sensor configurations. Nevertheless, a stochastic behavior can be noted in ORB-SLAM3 that can cause some sequences to deviate from this. In total, ORB-SLAM3 outperforms DM-VIO on the all sequences in the semi-synthetic datasets created for this thesis. The code used in this thesis is available at GitHub https://github.com/cmannila along with forked repositories of DM-VIO and ORB-SLAM3 / Visual(-Inertial) Odometry (VIO) och Simultaneous Localization and Mapping (SLAM) är av stort intresse inom datorseende (Computer Vision). Dessa system har en variation av tillämpningar såsom robotik, själv-körande bilar och VR (Virtual Reality). En ytterligare potentiell tillämpning är att integrera SLAM/VIO i huvudmonterade system, såsom glasögon, för att kunna studera beteenden och navigering hos bäraren. En komplikation till SLAM och VIO skulle kunna vara en visuell degration i det visuella systemet såsom rörelseoskärpa. Detta examensarbete försöker utvärdera robustheten mot rörelseoskärpa i två tillgängliga state-of-the-art system, DM-VIO (Delayed Marginalization Visual-Inertial Odometry) och ORB-SLAM3. Idag finns det inga tillgängliga dataset som innehåller specifikt varierande mängder rörelseoskärpa. Således, skapades ett semisyntetiskt dataset baserat på ett redan existerande, vid namn TUM VI. Detta gjordes med en dynamisk rendering av rörelseoskärpa enligt en känd rörelsebana erhållen från datasetet. Med denna teknik kunde olika mängder exponeringstid simuleras.  DM-VIO och ORB-SLAM3 utvärderades med två sensor konfigurationer, Monocular (en kamera) och Monokulär-Inertial (en kamera med Inertial Measurement Unit). Det objektiva mått som användes för att jämföra systemen var Root Mean Square av Absolute Trajectory Error i meter. Resultaten i detta arbete visar på att DM-VIO är i hög-grad beroende av den visuella signalen som används, och prestandan minskar avsevärt när rörelseoskärpan ökar, oavsett sensorkonfiguration. När enbart en kamera (Monocular) används minskar prestandan från centimeterprecision till diameter. ORB-SLAM3 påverkas inte av rörelseoskärpa och presterar med centimeterprecision för alla sekvenser. Det kan heller inte påvisas någon signifikant skillnad mellan sensorkonfigurationerna. Trots detta kan ett stokastiskt beteende i ORB-SLAM3 noteras, detta kan ha orsakat vissa sekvenser att bete sig avvikande. I helhet, ORB-SLAM3 överträffar DM-VIO på alla sekvenser i det semisyntetiska datasetet som skapats för detta arbete. Koden som använts i detta arbete finns tillgängligt på GitHub https://github.com/cmannila tillsammans med forkade repository för DM-VIO och ORB-SLAM3.
315

An Ethnographic Study of The Moth Detroit StorySLAM

Janssen, Catherine Jo 15 August 2012 (has links) (PDF)
The Moth Detroit StorySLAM is one of many storytelling events staged in urban bar environments. Unlike the increasingly aged audiences attending the National Storytelling Festival and similar story festivals, the Detroit StorySLAM consistently yields at capacity crowds of college students and young professionals. Participants were informally interviewed during the September, October, and November slams of 2010 and the January 2011 slam. In addition to conducting these interviews, the researcher was a participant observer—throwing her name into the hat and being twice called to the stage. Data are presented as a thick description organized according to Richard Bauman's 6 situational factors of the performance event. Until now questions about the nature and meaning of storytelling have been largely considered from the storyteller's perspective. By redirecting those questions to the listeners, this study reveals the ethos of hundreds of story enthusiasts—an undisputed admiration for the revelation of authentic, individual truths.
316

MonoDepth-vSLAM: A Visual EKF-SLAM using Optical Flow and Monocular Depth Estimation

Dey, Rohit 04 October 2021 (has links)
No description available.
317

Ego-Motion Estimation of Drones / Positionsestimering för drönare

Ay, Emre January 2017 (has links)
To remove the dependency on external structure for drone positioning in GPS-denied environments, it is desirable to estimate the ego-motion of drones on-board. Visual positioning systems have been studied for quite some time and the literature on the area is diligent. The aim of this project is to investigate the currently available methods and implement a visual odometry system for drones which is capable of giving continuous estimates with a lightweight solution. In that manner, the state of the art systems are investigated and a visual odometry system is implemented based on the design decisions. The resulting system is shown to give acceptable estimates. / För att avlägsna behovet av extern infrastruktur så som GPS, som dessutominte är tillgänglig i många miljöer, är det önskvärt att uppskatta en drönares rörelse med sensor ombord. Visuella positioneringssystem har studerats under lång tid och litteraturen på området är ymnig. Syftet med detta projekt är att undersöka de för närvarande tillgängliga metodernaoch designa ett visuellt baserat positioneringssystem för drönare. Det resulterande systemet utvärderas och visas ge acceptabla positionsuppskattningar.
318

Combining dense short range sensors and sparse long range sensors for mapping

Lin, Ismael January 2018 (has links)
Mapping is one of the main components of autonomous robots, and consist in the construction of a model of their environment based on the information gathered by different sensors over time. Those maps will have different attributes depending on the type of sensor used for the reconstruction. In this thesis we focus on RGBD cameras and LiDARs. The acquired data with cameras is dense, but the range is short and the construction of large scale and consistent maps is more challenging. LiDARs are the exact opposite, they give sparse data but can measure long ranges accurately and therefore support large scale mapping better. The thesis presents a method that uses both types of sensors with the purpose of combine their strengths and reduce their weaknesses. The evaluation of the system is done in an indoor environment, and with an autonomous robot. The result of the thesis shows a map that is robust in large environments and has dense information of the surroundings. / Kartläggning är en av huvudkomponenterna för autonoma robotar, och består av att bygga en modell av miljön utifrån informationen som samlats in av olika sensorer över tid. Dessa kartor kommer att ha olika attribut beroende på vilken typ av sensor som används för rekonstruktionen. I denna avhandling är fokus på RGBD-kameror och LiDARs. Datan från kameror är kompakt men kan bara mäta korta sträckor och det är utmanande att konstruera storskaliga och konsistenta kartor. LiDARs är exakt motsatta, de ger gles data men kan mäta långa avstånd noggrant och stödjer därför storskalig kartering bättre. Avhandlingen presenterar en metod som använder båda typerna av sensorer i syfte att kombinera deras styrkor och minska svagheterna. Utvärderingen av systemet sker i en inomhusmiljö och med en autonom robot. Resultatet av avhandlingen visar en karta som är robust i stora miljöer och har tät information om omgivningen.
319

Object registration in semi-cluttered and partial-occluded scenes for augmented reality

Gao, Q.H., Wan, Tao Ruan, Tang, W., Chen, L. 26 November 2018 (has links)
Yes / This paper proposes a stable and accurate object registration pipeline for markerless augmented reality applications. We present two novel algorithms for object recognition and matching to improve the registration accuracy from model to scene transformation via point cloud fusion. Whilst the first algorithm effectively deals with simple scenes with few object occlusions, the second algorithm handles cluttered scenes with partial occlusions for robust real-time object recognition and matching. The computational framework includes a locally supported Gaussian weight function to enable repeatable detection of 3D descriptors. We apply a bilateral filtering and outlier removal to preserve edges of point cloud and remove some interference points in order to increase matching accuracy. Extensive experiments have been carried to compare the proposed algorithms with four most used methods. Results show improved performance of the algorithms in terms of computational speed, camera tracking and object matching errors in semi-cluttered and partial-occluded scenes. / Shanxi Natural Science and Technology Foundation of China, grant number 2016JZ026 and grant number 2016KW-043).
320

Event-Based Visual SLAM : An Explorative Approach

Rideg, Johan January 2023 (has links)
Simultaneous Localization And Mapping (SLAM) is an important topic within the field of roboticsaiming to localize an agent in a unknown or partially known environment while simultaneouslymapping the environment. The ability to perform robust SLAM is especially important inhazardous environments such as natural disasters, firefighting and space exploration wherehuman exploration may be too dangerous or impractical. In recent years, neuromorphiccameras have been made commercially available. This new type of sensor does not outputconventional frames but instead an asynchronous signal of events at a microsecond resolutionand is capable of capturing details in complex lightning scenarios where a standard camerawould be either under- or overexposed, making neuromorphic cameras a promising solution insituations where standard cameras struggle. This thesis explores a set of different approachesto virtual frames, a frame-based representation of events, in the context of SLAM.UltimateSLAM, a project fusing events, gray scale and IMU data, is investigated using virtualframes of fixed and varying frame rate both with and without motion compensation. Theresulting trajectories are compared to the trajectories produced when using gray scale framesand the number of detected and tracked features are compared. We also use a traditional visualSLAM project, ORB-SLAM, to investigate the Gaussian weighted virtual frames and gray scaleframes reconstructed from the event stream using a recurrent network model. While virtualframes can be used for SLAM, the event camera is not a plug and play sensor and requires agood choice of parameters when constructing virtual frames, relying on pre-existing knowledgeof the scene.

Page generated in 0.0732 seconds