A laser-triangulating range camera uses a laser plane to light an object. If the position of the laser relative to the camera as well as certrain properties of the camera is known, it is possible to calculate the coordinates for all points along the profile of the object. If either the object or the camera and laser has a known motion, it is possible to combine several measurements to get a three-dimensional view of the object. Camera calibration is the process of finding the properties of the camera and enough information about the setup so that the desired coordinates can be calculated. Several methods for camera calibration exist, but this thesis proposes a new method that has the advantages that the objects needed are relatively inexpensive and that only objects in the laser plane need to be observed. Each part of the method is given a thorough description. Several mathematical derivations have also been added as appendices for completeness. The proposed method is tested using both synthetic and real data. The results show that the method is suitable even when high accuracy is needed. A few suggestions are also made about how the method can be improved further.

Detta examensarbete undersöker forensisk längdmätning i bild, t ex längduppskattning av människor i bilder rörande brottsmål. Problemen identifieras och några av dagens befintliga längdmätningsmetoder diskuteras. Den metod som bäst uppfyller de i arbetet ställda kraven, d v s snabb handläggning, minimal systeminformation, minimalt arbete på plats och exakthet, har valts ut, anpassats och utvärderats. Metoden bygger på att hitta s k gränspunkter och grundplanets gränslinje i bilden och utifrån en i världen känd referenslängd beräkna den sökta längden. Den bakomliggande teorin presenteras och metoden beskrivs i detalj. Funktioner, algoritmer och ett användargränssnitt har implementerats i beräkningsprogrammet MatLab. Tester har utförts för att validera metodens noggrannhet och parameterberoende. Metoden visar sig ge mycket bra resultat då rätt förutsättningar ges, men har konstaterats vara känslig för variation på gränslinjen. En rad förbättringsförslag presenteras för att utveckla metoden och stabilisera resultatet. Examensarbetet omfattar 20 högskolepoäng och utgör ett obligatoriskt moment i utbildningsprogrammet civilingenjör i datateknik som ges av Linköpings universitet. Arbetet är utfört vid och på uppdrag av Statens kriminaltekniska laboratorium (SKL) i Linköping.

No description available.

This master's thesis focuses on 3D reconstruction of vehicles passing in front of a traffic surveillance camera. Calibration process of surveillance camera is first introduced and the relation of automatic calibration with 3D information about observed traffic is described. Furthermore, Structure from Motion, SLAM, and optical flow algorithms are presented. A set of experiments with feature matching and the Structure from Motion algorithm is carried out to examine results on images of passing vehicles. Afterwards, the Structure from Motion pipeline is modified. Instead of using SIFT features, DeepMatching algorithm is utilized to obtain quasi-dense point correspondences for the subsequent reconstruction phase. Afterwards, reconstructed models are refined by applying additional constraints specific to the vehicle reconstruction task. The resultant models are then evaluated. Lastly, observations and acquired information about the process of vehicle reconstruction are utilized to form proposals for prospective design of an entirely custom pipeline that would be specialized for 3D reconstruction of passing vehicles.

Master’s thesis deals with object pose estimation using monocular camera. As an object is considered every rigid, shape fixed entity with strong edges, ideally textureless. Object position in this work is represented by transformation matrix, which describes object translation and rotation towards world coordinate system. First chapter is dedicated to explanation of theory of geometric transformations and intrinsic and extrinsic parameters of camera. This chapter also describes detection algorithm Chamfer Matching, which is used in this work. Second chapter describes all development tools used in this work. Third, fourth and fifth chapter are dedicated to practical realization of this works goal and achieved results. Last chapter describes created application, that realizes known object pose estimation in scene.

This thesis deals with the issue of creating applications of augmented reality. There are described types of augmented reality, problems associated with developing of applications of this kind. Also there is description of method for detection of moving objects from the record of stationary camera. The thesis deals with camera calibration using knowledge of scene geometry. Scene editor for scene geometry estimation is included in this work. Augmented reality is represented by physical simulations, where object from virtual reality interacts with detected objects and with objects defined in scene editor.

V rámci této dizertační práce se zaměřuji na Inteligentní dopravní systémy a Počítačové vidění - především automatické měření rychlosti a rozpoznání automobilů podle typů.  Rozpoznání automobilů podle typů je úkol, ve kterém system má predikovat přesný typ (např. Škoda Octavia combi mk2) pro daný obrázek automobilu. Publikoval jsem dva články, které popisují navržený přístup k tomuto problému a tvoří jádro této dizertace. Prezentovaná metoda je založena na 3D obalových kvádrech postavených okolo automobilů, které jsou následně využity pro rozbalení obrázku automobilu do roviny a tudíž normalizaci vstupu neuronové sítě, která dělá následné rozpoznání. Přístup byl dále rozpracován v druhé publikaci, kde je navržena metoda pro určení tohoto 3D obalového kvádru z jediného obrázku - tudíž není nutné mít zkalibrovanou kameru. Experimentální výsledky ukazují, že navržená metoda zlepšuje úspěšnost rozpoznání o 12 procentních bodů - chyba rozpoznání je redukována o 50 procent.Při měření rychlosti má systém za úkol odhadnout rychlost projíždějících aut z videa. Cílem je také, ať měření probíhá plně automaticky bez jakékoli manuální kalibrace. Jelikož neexistoval žádný dataset, který by obsahoval velké množství průjezdů s přesně změřenou rychlostí, tak jsme nejprve takovýto dataset pořídili. Dále jsem navrhnul metodu pro plně automatickou kalibraci dopravní dohledové kamery což umožňuje měřit rychlost automobilů pozorovaných touto kamerou. Metoda je založena na odhadu kalibrace pomocí detekovaných úběžníků scény a následného zarovnání 3D modelů několika běžných typů automobilů. Experimentální výsledky ukazují, že navržená metoda dosahuje průměrné chyby měření rychlosti 1,10 km/h.

This thesis attempts to solve the problem of estimating the extrinsic camera parameters (pitch and roll) from a wide-angle view image. The first contributionis a data generation pipeline capable of producing wide-angle distorted images with rotation and line segment annotations. This pipeline was used to produce four datasets with distortion and rotation in the range −5◦ to 5◦. The second contribution is two neural networks aiming to estimate the roll and pitch angles, one where line segments are used, and one where ResNet and DenseNet features are used. The roll and pitch angles are predicted both directly and with vanishing points as an intermediate representation in both networks. The line segment network managed to extract line segments from distorted images, and predict the roll and pitch angles with a mean error of 3.70◦ over all datasets. The network with features from ResNet and DenseNet performed the best with a mean angle error of 1.02◦ over all datasets.

Mini Unmanned Aerial Vehicles (mUAVs) have the potential to be a great asset to Wilderness Search and Rescue groups by providing a bird's eye view of the search area. These vehicles can carry a variety of sensors to better understand the world below. This paper proposes using both Infrared (IR) and Visible Spectrum cameras on a mUAV for Wilderness Search and Rescue. It details a method for combining the color and heat information from these two cameras into a single fused display to reduce needed screen space for remote field use. To align the video frames for fusion, a method for simultaneously pre-calibrating the intrinsic and extrinsic parameters of the cameras and their mount using a single multi-spectral calibration rig is also presented. A user study conducted to validate the proposed image fusion methods showed no reduction in performance when detecting objects of interest in the single-screen fused display compared to a side-by-side display. Furthermore, the users' increased performance on a simultaneous auditory task showed that increased performance on a simultaneous auditory task showed that their cognitive load was reduced when using the fused display.

Kontroll av trafik på och kring flygfält är ett krav för att få industrin och dess relaterade tjänster att upnå den säkerhet och effektivitet som krävs i dagens samhälle. Detta har traditionellt gjorts med bemannade kontrolltorn med full utsikt över fältet. Dessa torn är dock kostsamma både i konstruktion, drift och bemanning. Flygtrafik kontroll på distans har varit i utveckling under de senaste åren. Dessa projekt har som mål att sänka kostnader och låta avlägsna flygplatser med lite eller säsongsbaserad trafik att ändå ha tillgång till flygkontrollanter vid behov året om. Sådan teknologi kräver att kamera och positionsbestämning arbetar tillsammans med ett användargränssnitt som presenterar all relevant information på ett effektivt och intuitivt sätt. Denna rapport täcker designval och teknologier använda i utvecklingen av ett gränssnitt som använder augumented reality för att binda renderade element till ett objekt i bild igenom att utnyttja dess GPS koordinater. Projektet har som mål att visa ett produktkoncept som realistiskt sett skulle kunna utvecklas till en kommersiell produkt. Den färdiga applikationen använder ett set av tidsstämplade GPS koordinater från fordon i trafik på ett flygfält samt video av området. Applikationen använder kamerakalibrering för att bestämma kamerans position och orientering för att sedan omvandla GPS position till skärmposition så att man kan binda grafiska element till GPS koordinaterna vilket i detta fall är fordonen i drift. Projektet utnyttjar OpenGL samt fritt tillgängliga bibliotek för att hantera uppspelning av videofil, avkodning av bildformat och projektion av koordinater inom applikationen. Resultatet visar ett troligt produktkoncept som kan utnyttjas inom framtida produkter och system samt hur ett sådant systems användargränssnitt kan se ut, då projektet använder välkända kalibreringsmetoder och bibliotek som används inom industrin. / Air- and ground traffic control of any airport or airfield is a vital task necessary to ensure the safety and reliability of the services it provides and the efficiency of the infrastructure. Traditionally done through manned towers with an outlook over the field where operators can guide the traffic into safe takeoffs and landings. This traditional air-traffic control tower is, however, costly to build, maintain and staff. The remotecontrolled tower has been in development for some time now, meant to reduce cost and provide operators to any field utilizing the technology when need arise, even in remote locations with season dependent usage. However, with such technology one needs a camera, geographic locators, and information interfaces to all work together. This report covers the design and technologies used to develop an Augmented Reality interface that anchors its position based on a geographic locator using the GPS system. Its objective is to showcase or conceptualize a product that could realistically be developed further into a commercially viable system. Used within the application is a subset of timestamped GPS data of moving vehicles and a recorded video of the same area. Using Camera Calibration algorithms to find the location of the camera and line up the position of calibration points and their viewed position in the video one can later track the vehicles and attach AR-interfaces over them. All of which is rendered using OpenGL and freely available libraries for video playback and more. The result showcases a viable conceptualization of what future products might look like using current graphical guidelines and well-known calibration methods using a graphics library that is well used within the industry and multiple application or game engines.