We present a synchronized multisensory dataset for accurate and robust indoor localization: the Lund University Vision, Radio, and Audio (LuViRA) Dataset. The dataset includes color images, corresponding depth maps, inertial measurement unit (IMU) readings, channel response between a 5G massive multiple-input and multiple-output (MIMO) testbed and user equipment, audio recorded by 12 microphones, and accurate six degrees of freedom (6DOF) pose ground truth of 0.5 mm. We synchronize these sensors to ensure that all data is recorded simultaneously. A camera, speaker, and transmit antenna are placed on top of a slowly moving service robot, and 89 trajectories are recorded. Each trajectory includes 20 to 50 seconds of recorded sensor data and ground truth labels. Data from different sensors can be used separately or jointly to perform localization tasks, and data from the motion capture (mocap) system is used to verify the results obtained by the localization algorithms. The main aim of this dataset is to enable research on sensor fusion with the most commonly used sensors for localization tasks. Moreover, the full dataset or some parts of it can also be used for other research areas such as channel estimation, image classification, etc. Our dataset is available at: https://github.com/ilaydayaman/LuViRA_Dataset

Monocular depth estimation is a highly challenging problem that is often addressed with deep neural networks. While these use recognition of high level image features to predict reasonably looking depth maps, the result often has poor metric accuracy. Moreover, the standard feed forward architecture does not allow modification of the prediction based on cues other than the image.In this paper we relax the monocular depth estimation task by proposing a network that allows us to complement image features with a set of auxiliary variables. These allow disambiguation when image features are not enough to accurately pinpoint the exact depth map and can be thought of as a low dimensional parameterization of the surfaces that are reasonable monocular predictions. By searching the parameterization we can combine monocular estimation with traditional photoconsistency or geometry based methods to achieve both visually appealing and metrically accurate surface estimations. Since we relax the problem we are able to work with smaller networks than current architectures. In addition we design a self-supervised training scheme, eliminating the need for ground truth image depth-map pairs. Our experimental evaluation shows that our method generates more accurate depth maps and generalizes better than competing state-of-the-art approaches.

This work presents an on-chip memory subsystem envisioned for real-time applications performing Oriented FAST and Rotated Brief (ORB) feature extraction for Simultaneous Localization and Mapping (SLAM) systems. For autonomous navigation of battery-powered devices, feature-based SLAM is a computationally frugal alternative to direct methods. This paper thoroughly analyses ORB multiple memory access patterns, exploring possible systematic parallelism and hardware-biased algorithmic enhancements, alleviating requirements on bandwidth and reducing redundant accesses. Enabling those, a suitable multi-bank parallel memory featuring run-time reconfigurable address generation, image allotment, and close-to-memory data-shuffling is proposed. As case study, a 30 Frames-Per-Second (FPS) VGA-resolution ORB-capable 8-bank memory is evaluated using 22 FDX technology, running at 909 MHz, with a negligible area overhead of 0.3%, reducing operand accesses between 54 - 160× relative to Sudoku-like and scalar memories.

In this paper we present a novel algorithm for onboard radial distortion correction for unmanned aerial vehicles (UAVs) equipped with an inertial measurement unit (IMU), that runs in real-time. This approach makes calibration procedures redundant, thus allowing for exchange of optics extemporaneously. By utilizing the IMU data, the cameras can be aligned with the gravity direction. This allows us to work with fewer degrees of freedom, and opens up for further intrinsic calibration. We propose a fast and robust minimal solver for simultaneously estimating the focal length, radial distortion profile and motion parameters from homographies. The proposed solver is tested on both synthetic and real data, and perform better or on par with state-of-the-art methods relying on pre-calibration procedures. Code available at: https://github.com/marcusvaltonen/HomLib.1

With the development of cheap image sensors, the amount of available image data have increased enormously, and the possibility of using crowdsourced collection methods has emerged. This calls for development of ways to handle all these data. In this paper, we present new tools that will enable efficient, flexible and robust map merging. Assuming that separate optimisations have been performed for the individual maps, we show how only relevant data can be stored in a low memory footprint representation. We use these representations to perform map merging so that the algorithm is invariant to the merging order and independent of the choice of coordinate system. The result is a robust algorithm that can be applied to several maps simultaneously. The result of a merge can also be represented with the same type of low-memory footprint format, which enables further merging and updating of the map in a hierarchical way. Furthermore, the method can perform loop closing and also detect changes in the scene between the capture of the different image sequences. Using both simulated and real data - from both a hand held mobile phone and from a drone - we verify the performance of the proposed method.

In this paper we consider a collection of relative pose problems which arise naturally in applications for visual indoor UAV navigation. We focus on cases where additional information from an onboard IMU is available and thus provides a partial extrinsic calibration through the gravitational vector. The solvers are designed for a partially calibrated camera, for a variety of realistic indoor scenarios, which makes it possible to navigate using images of the ground floor. Current state-of-the-art solvers use more general assumptions, such as using arbitrary planar structures; however, these solvers do not yield adequate reconstructions for real scenes, nor do they perform fast enough to be incorporated in real-time systems. We show that the proposed solvers enjoy better numerical stability, are faster, and require fewer point correspondences, compared to state-of-the-art solvers. These properties are vital components for robust navigation in real-time systems, and we demonstrate on both synthetic and real data that our method outperforms other methods, and yields superior motion estimation.

In this paper we present results from a outdoor-to-indoor MIMO measurement campaign where we study the effect of repeaters on singular values, spatial richness, capacity, and delay spread distributions. We present results from different repeater scenarios such as, e.g. different outdoor/indoor repeater deployments with single/dual polarized antennas. The measurements show that repeaters significantly enhance the received SNR while they increase the delay spread and decrease the spatial richness of the MIMO channel. However, the main conclusion is that a significant increase in channel capacity is attained when deploying repeaters mostly thanks to their ability to provide spatial multiplexing over the high-quality eigenmodes they may provide. The number of such eigenmodes is limited by the number of repeaters, deployment, and their antennas.