In this paper we propose a new approach to real-time view-based pose recognition and interpolation. Pose recognition is particularly useful for identifying camera views in databases, video sequences, video streams, and live recordings. All of these applications require a fast pose recognition process, in many cases video real-time. It should further be possible to extend the database with new material, i.e., to update the recognition system online. The method that we propose is based on P-channels, a special kind of information representation which combines advantages of histograms and local linear models. Our approach is motivated by its similarity to information representation in biological systems but its main advantage is its robustness against common distortions such as clutter and occlusion. The recognition algorithm consists of three steps: (1) low-level image features for color and local orientation are extracted in each point of the image; (2) these features are encoded into P-channels by combining similar features within local image regions; (3) the query P-channels are compared to a set of prototype P-channels in a database using a least-squares approach. The algorithm is applied in two scene registration experiments with fisheye camera data, one for pose interpolation from synthetic images and one for finding the nearest view in a set of real images. The method compares favorable to SIFT-based methods, in particular concerning interpolation. The method can be used for initializing pose-tracking systems, either when starting the tracking or when the tracking has failed and the system needs to re-initialize. Due to its real-time performance, the method can also be embedded directly into the tracking system, allowing a sensor fusion unit choosing dynamically between the frame-by-frame tracking and the pose recognition.

Estimating the position of a 3-dimensional world point given its 2-dimensional projections in a set of images is a key component in numerous computer vision systems. There are several methods dealing with this problem, ranging from sub-optimal, linear least square triangulation in two views, to finding the world point that minimized the L2-reprojection error in three views. This leads to the statistically optimal estimate under the assumption of Gaussian noise. In this paper we present a solution to the optimal triangulation in three views. The standard approach for solving the three-view triangulation problem is to find a closed-form solution. In contrast to this, we propose a new method based on an iterative scheme. The method is rigorously tested on both synthetic and real image data with corresponding ground truth, on a midrange desktop PC and a Raspberry Pi, a low-end mobile platform. We are able to improve the precision achieved by the closed-form solvers and reach a speed-up of two orders of magnitude compared to the current state-of-the-art solver. In numbers, this amounts to around 300K triangulations per second on the PC and 30K triangulations per second on Raspberry Pi.

This paper presents an autonomous robotic system that incorporates novel Computer Vision, Machine Learning and Data Mining algorithms in order to learn to navigate and discover important visual entities. This is achieved within a Learning from Demonstration (LfD) framework, where policies are derived from example state-to-action mappings. For autonomous navigation, a mapping is learnt from holistic image features (GIST) onto control parameters using Random Forest regression. Additionally, visual entities (road signs e.g. STOP sign) that are strongly associated to autonomously discovered modes of action (e.g. stopping behaviour) are discovered through a novel Percept-Action Mining methodology. The resulting sign detector is learnt without any supervision (no image labeling or bounding box annotations are used). The complete system is demonstrated on a fully autonomous robotic platform, featuring a single camera mounted on a standard remote control car. The robot carries a PC laptop, that performs all the processing on board and in real-time.

The majority of consumer quality cameras sold today have CMOS sensors with rolling shutters. In a rolling shutter camera, images are read out row by row, and thus each row is exposed during a different time interval. A rolling-shutter exposure causes geometric image distortions when either the camera or the scene is moving, and this causes state-of-the-art structure and motion algorithms to fail. We demonstrate a novel method for solving the structure and motion problem for rolling-shutter video. The method relies on exploiting the continuity of the camera motion, both between frames, and across a frame. We demonstrate the effectiveness of our method by controlled experiments on real video sequences. We show, both visually and quantitatively, that our method outperforms standard structure and motion, and is more accurate and efficient than a two-step approach, doing image rectification and structure and motion.

This paper describes a system that efficiently uses the KLT tracker together with a calibrated 5-point solver for structure-from-motion (SfM). Our system uses a GPU to perform tracking, and the CPU for SfM.

In this setup, it is advantageous to run the tracker both forwards and backwards in time, to detect incorrectly tracked points. We introduce a modification to the point selection inside the RANSAC step of the 5-point solver, and demonstrate how this speeds up the algorithm. Our evaluations are done using both real camera sequences, and data from a state-of-the art rendering engine with associated ground-truth.

Good data sets for evaluation of computer visionalgorithms are important for the continuedprogress of the field. There exist good evaluationsets for many applications, but there are othersfor which good evaluation sets are harder to comeby. One such example is feature tracking, wherethere is an obvious difficulty in the collection ofdata. Good evaluation data is important both forcomparisons of different algorithms, and to detectweaknesses in a specific method.All image data is a result of light interactingwith its environment. These interactions are sowell modelled in rendering software that sometimesnot even the sharpest human eye can tell the differencebetween reality and simulation. In this paperwe thus propose to use a high quality renderingsystem to create evaluation data for sparse pointcorrespondence trackers.

The GPU is the main processing unit on a graphics card. A modern GPU typically provides more than ten times the computational power of an ordinary PC processor. This is a result of the high demands for speed and image quality in computer games. This paper investigates the possibility of exploiting this computational power for tracking points in image sequences. Tracking points is used in many computer vision tasks, such as tracking moving objects, structure from motion, face tracking etc. The algorithm was successfully implemented on the GPU and a large speed up was achieved.

Digital camera equipped cell phones were introduced in Japan in 2001, they quickly became popular and by 2003 outsold the entire stand-alone digital camera market. In 2010 sales passed one billion units and the market is still growing. Another trend is the rising popularity of smartphones which has led to a rapid development of the processing power on a phone, and many units sold today bear close resemblance to a personal computer. The combination of a powerful processor and a camera which is easily carried in your pocket, opens up a large eld of interesting computer vision applications.

The core contribution of this thesis is the development of methods that allow an imaging device such as the cell phone camera to estimates its own motion and to capture the observed scene structure. One of the main focuses of this thesis is real-time performance, where a real-time constraint does not only result in shorter processing times, but also allows for user interaction.

In computer vision, structure from motion refers to the process of estimating camera motion and 3D structure by exploring the motion in the image plane caused by the moving camera. This thesis presents several methods for estimating camera motion. Given the assumption that a set of images has known camera poses associated to them, we train a system to solve the camera pose very fast for a new image. For the cases where no a priory information is available a fast minimal case solver is developed. The solver uses ve points in two camera views to estimate the cameras relative position and orientation. This type of minimal case solver is usually used within a RANSAC framework. In order to increase accuracy and performance a renement to the random sampling strategy of RANSAC is proposed. It is shown that the new scheme doubles the performance for the ve point solver used on video data. For larger systems of cameras a new Bundle Adjustment method is developed which are able to handle video from cell phones.

Demands for reduction in size, power consumption and price has led to a redesign of the image sensor. As a consequence the sensors have changed from a global shutter to a rolling shutter, where a rolling shutter image is acquired row by row. Classical structure from motion methods are modeled on the assumption of a global shutter and a rolling shutter can severely degrade their performance. One of the main contributions of this thesis is a new Bundle Adjustment method for cameras with a rolling shutter. The method accurately models the camera motion during image exposure with an interpolation scheme for both position and orientation.

The developed methods are not restricted to cellphones only, but is rather applicable to any type of mobile platform that is equipped with cameras, such as a autonomous car or a robot. The domestic robot comes in many  avors, everything from vacuum cleaners to service and pet robots. A robot equipped with a camera that is capable of estimating its own motion while sensing its environment, like the human eye, can provide an eective means of navigation for the robot. Many of the presented methods are well suited of robots, where low latency and real-time constraints are crucial in order to allow them to interact with their environment.

Enligt de dokumentatörer som deltog i samtalen hade de allra flesta egna erfarenheter av hemtentor. En hemtentamen definierades som att studenten utförde sin examination i hemmet med tillgång till olika typer av källmateri-al, som kurs- och annan litteratur samt med hjälp av tidskrifter och journaler via internet. Ett vanligt förhållande tycktes vara att en tentamen var begrän-sad till 1-2 veckor, vilket skiljde sig från lärarprogrammets terminsvisa tentor. I de allra flesta fall offentliggjordes hemtentan ett visst klockslag via nätet, ofta med hjälp av lärplattformar som It’s Learning. Oavsett den tid som stu-denterna hade till förfogande betonades vikten av att sätta tydliga tidsramar och att man som lärare följde efterlevnaden av dessa ramar.