<p>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.</p><p>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.</p><p>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.</p>

A new open source 3D reconstruction and evaluation pipeline is described, with a thorough description of the algorithms employed. A new evaluation framework is introduced, which is easy to use for comparison of state-of-the-art multiview reconstruction algorithms. The evaluation framework also includes tools for creating data sets which have ground truth. The source code is available under the GPL; a first for a complete end-to-end reconstruction system.

A new open source 3D reconstruction and evaluation pipeline is described, with a thorough description of the algorithms employed. A new evaluation framework is introduced, which is easy to use for comparison of state-of-the-art multiview reconstruction algorithms. The evaluation framework also includes tools for creating data sets which have ground truth. The source code is available under the GPL; a first for a complete end-to-end reconstruction system.

There has always been a desire to apply technology to human endeavors to increase a person's capabilities and reduce the numbers or skill level required of the people involved, or replace the people altogether. Three fundamental areas are investigated where technology can enable the reduction or removal of humans in complex tasks. The fi rst area of research is the rapid calibration of multiple camera systems when cameras share an overlapping fi eld of view allowing for 3D computer vision applications. A simple method for the rapid calibration of such systems is introduced. The second area of research is the autonomous exploration of hallways or other urbancanyon environments in the absence of a global positions system (GPS) using only an inertial motion unit (IMU) and a monocular camera. Desired paths that generate accurate vehicle state estimates for simple ground vehicles are identi fied and the bene fits of integrated estimation and control are investigated. It is demonstrated that considering estimation accuracy is essential to produce efficient guidance and control. The Schmidt-Kalman filter is applied to the vision-aided inertial navigation system in a novel manner, reducing the state vector size signi ficantly. The final area of research is a decentralized swarm based approach to source localization using a high fidelity environment model to directly provide vehicle updates. The approach is an extension of a standard quadratic model that provides linear updates. The new approach leverages information from the higher-order terms of the environment model showing dramatic improvement over the standard method.

<p>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.</p><p>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.</p><p>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.</p>

Many smooth, highly specular coatings such as automotive paints are subjected to considerable performance demands as the customer expectations for appearance of coatings are continually increasing. Therefore it is vital to develop robust methods to monitor surface quality online. An automated visual assessment of specular coated surface that would not only provide a cost effective and reliable solution to the industries but also facilitate the implementation of a real-time feedback loop. The scope of this thesis is a subset of the inspection technology that facilitates real-time close loop control of the surface quality and concentrates on one common surface defect the seed defect. This machine vision system design utilizes surface reflectance models as a rational basis. Using a single high-contrast image the height of the seed defect is computed; the result is obtained rapidly and is reasonably accurate approximation of the actual height.

Performance improvement of a 3-D configuration reconstruction algorithm using a passive secondary target has been focused in this study. In earlier studies, a theoretical development of the 3-D configuration reconstruction algorithm was achieved and it was implemented by a computer program on a system consisting of an optical bench and a digital imaging system. The passive secondary target used was a circle with two internal spots. In order to use this reconstruction algorithm in autonomous systems, an automatic target recognition algorithm has been developed in this study. Starting from a pre-captured and stored 8-bit gray-level image, the algorithm automatically detects the elliptical image of a circular target and determines its contour in the scene. It was shown that the algorithm can also be used for partially captured elliptical images. Another improvement achieved in this study is the determination of internal camera parameters of the vision system.

To make three dimensional measurements using a stereo camera system, the intrinsic and extrinsic calibration of the system should be obtained. Furthermore, to allow zooming, intrinsic parameters should be re-estimated using only scene constraints. In this study both manual and autocalibration algorithms are implemented and tested. The implemented manual calibration system is used to calculate the parameters of the calibration with the help of a planar calibration object. The method is tested on different internal calibration settings and results of 3D measurements using the obtained calibration is presented. Two autocalibration methods have been implemented. The first one requires a general motion while the second method requires a pure rotation of the cameras. The autocalibration methods require point matches between images. To achieve a fully automated process, robust algorithms for point matching have been implemented. For the case of general motion the fundamental matrix relation is used in the matching algorithm. When there is only rotation between views, the homography relation is used. The results of variations on the autocalibration methods are also presented. The result of the manual calibration has been found to be very reliable. The results of the first autocalibration method are not accurate enough but it has been shown that the calibration from rotating cameras performs precise enough if rotation between images is sufficiently large.

Cette thèse porte sur la fonction de détection d'obstacles dans le domaine ferroviaire à partir de la vision par ordinateur. Il s'agit d'assurer une perception de l'environnement situé à l'avant du train afin de détecter et d'évaluer les distances des obstacles situés sur la voie.Nous avons donc proposé un module détection de rails à partir des images à niveaux de gris, pour déterminer une zone libre d'obstacles à l'avant du train. Cette détection est basée dans l'algorithme de RANSAC et une estimation de la voie par un polynôme de degré 2. Elle s'est montrée robuste à notre base de données et a permis de détecter les rails à des distances supérieures à la distance d'arrêt. Aussi, un algorithme d'étalonnage des caméras installées dans le train a été proposé à partir de la morphologie de la voie.Comme support de la reconnaissance de rails, nous présentons un module de détection et classification des appareils de voie basé dans le descripteur HOG extrait des images IPM (Inverse Perspective Mapping). Un classifieur SVM (Support Vector Machines) binaire a été utilisé pour la détection et un SVM multi-classe pour différencier les appareils de voie existants sur la ligne.Après avoir élaboré le module de détection des rails, nous avons implémenté un détecteur de trains. À partir d'un échantillon des images de trains de la ligne en question et des images négatives comme des voitures ou des bus, nous avons créé une base de données d'obstacles pour trouver un descripteur robuste qui arrive à décrire la forme des trains et permet à un classifieur SVM de discriminer les images et détecter les trains. Par la suite, ce classifieur est utilisé par le système global pour déterminer la présence d'un train au-delà de la détection de la voie. À la distance maximale de détection, un rectangle de la taille d'un train est extrait de l'image pour vérifier la présence d'un train. Ces rectangles font l'objet d'une classification au moyen de descripteurs globaux de type HOG et une structure SVM binaire.Cette étude permettra non seulement de déboucher sur des applications concrètes, mais surtout d'évaluer la maturité des technologies de traitements d'images pour réaliser des fonctions sûres appliquées aux systèmes ferroviaires. / This thesis deals with obstacle detection in a railway setting using computer vision. The main task is to provide perception of the environment in front ofthe train using an optical sensor to detect and evaluate distances to obstacles along the track path.We present a module for detecting rails from grayscale images to determine an obstacle-free zone in front of the train. This detection is based on the RANSACalgorithm and fitting the track to a second degree polynomial. The method has shown itself robust to our dataset and allows detecting the rails at distancesgreater than the emergency stopping distance. In addition, a method for calibrating the cameras installed on the train is proposed based on the morphology ofthe track.To supplement rail detection, we present a new module for detecting and classifying junctions based on the HOG descriptor extracted from InversePerspective Mapping (IPM) images. A Support Vector Machines (SVM) binary classifier was used for detection and a multi-class SVM for distinguishing ofjunctions along the rails.In the sequel, a train detector was implemented. Using a set of images of trains found on the studied line and negative images such as cars or buses, we havecreated a database of obstacles to find a robust descriptor which is able to model the form of trains and allows a SVM classifier to distinguish images anddetect trains. Next this classifier is used by the overall system to determine the presence of a train in addition to detecting rails. At the maximum detectiondistance, a train-sized rectangle is extracted from the image in order to confirm the presence of a train. These rectangles are classified by means of HOG-typeglobal descriptors and a binary SVM structure.In addition to its applications to concrete problems, this study permits to evaluate the maturity of image processing technologies forfail-safe railway systems.

abstract: There is a growing interest for improved high-accuracy camera calibration methods due to the increasing demand for 3D visual media in commercial markets. Camera calibration is used widely in the fields of computer vision, robotics and 3D reconstruction. Camera calibration is the first step for extracting 3D data from a 2D image. It plays a crucial role in computer vision and 3D reconstruction due to the fact that the accuracy of the reconstruction and 3D coordinate determination relies on the accuracy of the camera calibration to a great extent. This thesis presents a novel camera calibration method using a circular calibration pattern. The disadvantages and issues with existing state-of-the-art methods are discussed and are overcome in this work. The implemented system consists of techniques of local adaptive segmentation, ellipse fitting, projection and optimization. Simulation results are presented to illustrate the performance of the proposed scheme. These results show that the proposed method reduces the error as compared to the state-of-the-art for high-resolution images, and that the proposed scheme is more robust to blur in the imaged calibration pattern. / Dissertation/Thesis / M.S. Electrical Engineering 2012