Filtyp
Many computer vision applications require robust estimation of the underlying geometry, in terms of camera motion and 3D structure of the scene. These robust methods often rely on running minimal solvers in a RANSAC framework. In this paper we show how we can make polynomial solvers based on the action matrix method faster, by careful selection of the monomial bases. These monomial bases have trad
To estimate the 6-DoF extrinsic pose of a pinhole camera with partially unknown intrinsic parameters is a critical sub-problem in structure-from-motion and camera localization. In most of existing camera pose estimation solvers, the principal point is assumed to be in the image center. Unfortunately, this assumption is not always true, especially for asymmetrically cropped images. In this paper, w
This paper introduces the first minimal solvers that jointly solve for affine-rectification and radial lens distortion from coplanar repeated patterns. Even with imagery from moderately distorted lenses, plane rectification using the pinhole camera model is inaccurate or invalid. The proposed solvers incorporate lens distortion into the camera model and extend accurate rectification to wide-angle
The problem of graph matching under node and pairwise constraints is fundamental in areas as diverse as combinatorial optimization, machine learning or computer vision, where representing both the relations between nodes and their neighborhood structure is essential. We present an end-to-end model that makes it possible to learn all parameters of the graph matching process, including the unary and
We introduce new, fine-grained action and emotion recognition tasks defined on non-staged videos, recorded during robot-assisted therapy sessions of children with autism. The tasks present several challenges: a large dataset with long videos, a large number of highly variable actions, children that are only partially visible, have different ages and may show unpredictable behaviour, as well as non
We propose drl-RPN, a deep reinforcement learning-based visual recognition model consisting of a sequential region proposal network (RPN) and an object detector. In contrast to typical RPNs, where candidate object regions (RoIs) are selected greedily via class-agnostic NMS, drl-RPN optimizes an objective closer to the final detection task. This is achieved by replacing the greedy RoI selection pro
In this paper we explore the role of duality principles within the problem of rotation averaging, a fundamental task in a wide range of computer vision applications. In its conventional form, rotation averaging is stated as a minimization over multiple rotation constraints. As these constraints are non-convex, this problem is generally considered challenging to solve globally. We show how to circu
The problem of fitting models to measured data has been studied extensively, not least in the field of computer vision. A central problem in this field is the difficulty in reliably find corresponding structures and points in different images, resulting in outlier data. This thesis presents theoretical results improving the understanding of the connection between model parameter estimation and pos
In this thesis some research questions regarding durability and quality of roads has been investigated. The questions are analyzed from an image analysis point of view and aims to be a complement to existing methods for analyzing asphalt. One important factor for the durability of the asphalt layer on roads is the affinity between the stones in the asphalt and the binder that holds the stones tog
Recent work on geometric vision problems has exploited convexity properties in order to obtain globally optimal solutions. In this paper we give an overview of these developments and show the tight connections between different types of convexity and optimality conditions for a large class of multiview geometry problems. We also show how the convexity properties are closely linked to different typ
In this paper, we study minimal problems related to dual microphone rig self-calibration using TOA measurements from sound sources with unknown positions. We consider the problems with varying setups as (i) if the internal distances between the microphone nodes are known a priori or not. (ii) if the microphone rigs lies in an affine space with different dimension than the sound sources. Solving th
Energies with high-order non-submodular interactions have been shown to be very useful in vision due to their high modeling power. Optimization of such energies, however, is generally NP-hard. A naive approach that works for small problem instances is exhaustive search, that is, enumera- tion of all possible labelings of the underlying graph. We propose a general minimization approach for large gr
Fast algorithms for unequally spaced discrete Laplace transforms are presented. The algorithms are approximate up to a prescribed choice of computational precision, and they employ modified versions of algorithms for unequally spaced fast Fourier transforms using Gaussians. Various configurations of sums with equally and unequally spaced points can be dealt with. In contrast to previously presente
In experimental design and 3D reconstruction it is desirable to minimize the number of observations required to reach a prescribed estimation accuracy. Many approaches in the literature attempt to find the next best view from which to measure, and iterate this procedure. This paper discusses a continuous optimization method for finding a whole set of future imaging locations which minimize the rec
In this paper, we describe a novel approach to create 3D miniatures of persons using a Kinect sensor and a 3D color printer. To achieve this, we acquire color and depth images while the person is rotating on a swivel chair. We represent the model with a signed distance function which is updated and visualized as the images are captured for immediate feedback. Our approach automatically fills small
We introduce a multi-region model for simultaneous segmentation of medical images. In contrast to many other models, geometric constraints such as inclusion and exclusion between the regions are enforced, which makes it possible to correctly segment different regions even if the intensity distributions are identical. We efficiently optimize the model using a combination of graph cuts and Lagrangia
The estimation of three-dimensional position information from two-dimensional images in computer vision systems can be formulated as a state estimation problem for a nonlinear perspective dynamic system. The multi-output state estimation problem has been treated by several authors using methods for nonlinear observer design. This paper shows that a perspective system can be transformed to two obse
This thesis concerns ego-motion and pose estimation of a single camera under the assumptions of planar motion and constant internal camera parameters. Planar motion is common for cameras mounted onto mobile robots, particularly in indoor scenarios, as they remain at a constant height above the ground plane. In Paper A, a parametrisation of the camera motion and pose is presented, along with an ite
Dynamic vegetation models are useful tools for analysing terrestrial ecosystem processes and their interactions with climate through variations in carbon and water exchange. Long-term changes in structure and composition (vegetation dynamics) caused by altered competitive strength between plant functional types (PFTs) are attracting increasing attention as controls on ecosystem functioning and pot
