arXiv subjects

Davide Scaramuzza

Publications and source records attributed to Davide Scaramuzza.

At least 199 records · Page 11Linked to original sources

arXiv2020

Augmenting Visual Place Recognition with Structural Cues

In this paper, we propose to augment image-based place recognition with structural cues. Specifically, these structural cues are obtained using structure-from-motion, such that no additional sensors are needed for place recognition. This is achieved by augmenting the 2D convolutional neural network (CNN) typically used for image-based place recognition with a 3D CNN that takes as input a voxel grid derived from the structure-from-motion point cloud. We evaluate different methods for fusing the 2D and 3D features and obtain best performance with global average pooling and simple concatenation. On the Oxford RobotCar dataset, the resulting descriptor exhibits superior recognition performance compared to descriptors extracted from only one of the input modalities, including state-of-the-art image-based descriptors. Especially at low descriptor dimensionalities, we outperform state-of-the-art descriptors by up to 90%.

cs.CV↗

arXiv2020

Tightly-coupled Fusion of Global Positional Measurements in Optimization-based Visual-Inertial Odometry

Motivated by the goal of achieving robust, drift-free pose estimation in long-term autonomous navigation, in this work we propose a methodology to fuse global positional information with visual and inertial measurements in a tightly-coupled nonlinear-optimization-based estimator. Differently from previous works, which are loosely-coupled, the use of a tightly-coupled approach allows exploiting the correlations amongst all the measurements. A sliding window of the most recent system states is estimated by minimizing a cost function that includes visual re-projection errors, relative inertial errors, and global positional residuals. We use IMU preintegration to formulate the inertial residuals and leverage the outcome of such algorithm to efficiently compute the global position residuals. The experimental results show that the proposed method achieves accurate and globally consistent estimates, with negligible increase of the optimization computational cost. Our method consistently outperforms the loosely-coupled fusion approach. The mean position error is reduced up to 50% with respect to the loosely-coupled approach in outdoor Unmanned Aerial Vehicle (UAV) flights, where the global position information is given by noisy GPS measurements. To the best of our knowledge, this is the first work where global positional measurements are tightly fused in an optimization-based visual-inertial odometry algorithm, leveraging the IMU preintegration method to define the global positional factors.

cs.RO↗

arXiv2020

Deep Drone Acrobatics

Performing acrobatic maneuvers with quadrotors is extremely challenging. Acrobatic flight requires high thrust and extreme angular accelerations that push the platform to its physical limits. Professional drone pilots often measure their level of mastery by flying such maneuvers in competitions. In this paper, we propose to learn a sensorimotor policy that enables an autonomous quadrotor to fly extreme acrobatic maneuvers with only onboard sensing and computation. We train the policy entirely in simulation by leveraging demonstrations from an optimal controller that has access to privileged information. We use appropriate abstractions of the visual input to enable transfer to a real quadrotor. We show that the resulting policy can be directly deployed in the physical world without any fine-tuning on real data. Our methodology has several favorable properties: it does not require a human expert to provide demonstrations, it cannot harm the physical system during training, and it can be used to learn maneuvers that are challenging even for the best human pilots. Our approach enables a physical quadrotor to fly maneuvers such as the Power Loop, the Barrel Roll, and the Matty Flip, during which it incurs accelerations of up to 3g.

cs.RO↗

arXiv2020

Video to Events: Recycling Video Datasets for Event Cameras

Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous "events" instead of intensity frames. They offer significant advantages with respect to conventional cameras: high dynamic range (HDR), high temporal resolution, and no motion blur. Recently, novel learning approaches operating on event data have achieved impressive results. Yet, these methods require a large amount of event data for training, which is hardly available due the novelty of event sensors in computer vision research. In this paper, we present a method that addresses these needs by converting any existing video dataset recorded with conventional cameras to synthetic event data. This unlocks the use of a virtually unlimited number of existing video datasets for training networks designed for real event data. We evaluate our method on two relevant vision tasks, i.e., object recognition and semantic segmentation, and show that models trained on synthetic events have several benefits: (i) they generalize well to real event data, even in scenarios where standard-camera images are blurry or overexposed, by inheriting the outstanding properties of event cameras; (ii) they can be used for fine-tuning on real data to improve over state-of-the-art for both classification and semantic segmentation.

cs.CV↗

arXiv2020

Towards Low-Latency High-Bandwidth Control of Quadrotors using Event Cameras

Event cameras are a promising candidate to enable high speed vision-based control due to their low sensor latency and high temporal resolution. However, purely event-based feedback has yet to be used in the control of drones. In this work, a first step towards implementing low-latency high-bandwidth control of quadrotors using event cameras is taken. In particular, this paper addresses the problem of one-dimensional attitude tracking using a dualcopter platform equipped with an event camera. The event-based state estimation consists of a modified Hough transform algorithm combined with a Kalman filter that outputs the roll angle and angular velocity of the dualcopter relative to a horizon marked by a black-and-white disk. The estimated state is processed by a proportional-derivative attitude control law that computes the rotor thrusts required to track the desired attitude. The proposed attitude tracking scheme shows promising results of event-camera-driven closed loop control: the state estimator performs with an update rate of 1 kHz and a latency determined to be 12 ms, enabling attitude tracking at speeds of over 1600 deg/s.

cs.RO↗

arXiv2020

AirSim Drone Racing Lab

Autonomous drone racing is a challenging research problem at the intersection of computer vision, planning, state estimation, and control. We introduce AirSim Drone Racing Lab, a simulation framework for enabling fast prototyping of algorithms for autonomy and enabling machine learning research in this domain, with the goal of reducing the time, money, and risks associated with field robotics. Our framework enables generation of racing tracks in multiple photo-realistic environments, orchestration of drone races, comes with a suite of gate assets, allows for multiple sensor modalities (monocular, depth, neuromorphic events, optical flow), different camera models, and benchmarking of planning, control, computer vision, and learning-based algorithms. We used our framework to host a simulation based drone racing competition at NeurIPS 2019. The competition binaries are available at our github repository.

cs.RO↗

arXiv2020

Event-Based Angular Velocity Regression with Spiking Networks

Spiking Neural Networks (SNNs) are bio-inspired networks that process information conveyed as temporal spikes rather than numeric values. A spiking neuron of an SNN only produces a spike whenever a significant number of spikes occur within a short period of time. Due to their spike-based computational model, SNNs can process output from event-based, asynchronous sensors without any pre-processing at extremely lower power unlike standard artificial neural networks. This is possible due to specialized neuromorphic hardware that implements the highly-parallelizable concept of SNNs in silicon. Yet, SNNs have not enjoyed the same rise of popularity as artificial neural networks. This not only stems from the fact that their input format is rather unconventional but also due to the challenges in training spiking networks. Despite their temporal nature and recent algorithmic advances, they have been mostly evaluated on classification problems. We propose, for the first time, a temporal regression problem of numerical values given events from an event camera. We specifically investigate the prediction of the 3-DOF angular velocity of a rotating event camera with an SNN. The difficulty of this problem arises from the prediction of angular velocities continuously in time directly from irregular, asynchronous event-based input. Directly utilising the output of event cameras without any pre-processing ensures that we inherit all the benefits that they provide over conventional cameras. That is high-temporal resolution, high-dynamic range and no motion blur. To assess the performance of SNNs on this task, we introduce a synthetic event camera dataset generated from real-world panoramic images and show that we can successfully train an SNN to perform angular velocity regression.

cs.NE↗

arXiv2020

Voxel Map for Visual SLAM

In modern visual SLAM systems, it is a standard practice to retrieve potential candidate map points from overlapping keyframes for further feature matching or direct tracking. In this work, we argue that keyframes are not the optimal choice for this task, due to several inherent limitations, such as weak geometric reasoning and poor scalability. We propose a voxel-map representation to efficiently retrieve map points for visual SLAM. In particular, we organize the map points in a regular voxel grid. Visible points from a camera pose are queried by sampling the camera frustum in a raycasting manner, which can be done in constant time using an efficient voxel hashing method. Compared with keyframes, the retrieved points using our method are geometrically guaranteed to fall in the camera field-of-view, and occluded points can be identified and removed to a certain extend. This method also naturally scales up to large scenes and complicated multicamera configurations. Experimental results show that our voxel map representation is as efficient as a keyframe map with 5 keyframes and provides significantly higher localization accuracy (average 46% improvement in RMSE) on the EuRoC dataset. The proposed voxel-map representation is a general approach to a fundamental functionality in visual SLAM and widely applicable.

cs.RO↗

arXiv2020

Redesigning SLAM for Arbitrary Multi-Camera Systems

Adding more cameras to SLAM systems improves robustness and accuracy but complicates the design of the visual front-end significantly. Thus, most systems in the literature are tailored for specific camera configurations. In this work, we aim at an adaptive SLAM system that works for arbitrary multi-camera setups. To this end, we revisit several common building blocks in visual SLAM. In particular, we propose an adaptive initialization scheme, a sensor-agnostic, information-theoretic keyframe selection algorithm, and a scalable voxel-based map. These techniques make little assumption about the actual camera setups and prefer theoretically grounded methods over heuristics. We adapt a state-of-the-art visual-inertial odometry with these modifications, and experimental results show that the modified pipeline can adapt to a wide range of camera setups (e.g., 2 to 6 cameras in one experiment) without the need of sensor-specific modifications or tuning.

cs.RO↗

arXiv2020

EVDodgeNet: Deep Dynamic Obstacle Dodging with Event Cameras

Dynamic obstacle avoidance on quadrotors requires low latency. A class of sensors that are particularly suitable for such scenarios are event cameras. In this paper, we present a deep learning -- based solution for dodging multiple dynamic obstacles on a quadrotor with a single event camera and on-board computation. Our approach uses a series of shallow neural networks for estimating both the ego-motion and the motion of independently moving objects. The networks are trained in simulation and directly transfer to the real world without any fine-tuning or retraining. We successfully evaluate and demonstrate the proposed approach in many real-world experiments with obstacles of different shapes and sizes, achieving an overall success rate of 70% including objects of unknown shape and a low light testing scenario. To our knowledge, this is the first deep learning -- based solution to the problem of dynamic obstacle avoidance using event cameras on a quadrotor. Finally, we also extend our work to the pursuit task by merely reversing the control policy, proving that our navigation stack can cater to different scenarios.

cs.RO↗

arXiv2020

A General Framework for Uncertainty Estimation in Deep Learning

Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics. Current approaches for uncertainty estimation of neural networks require changes to the network and optimization process, typically ignore prior knowledge about the data, and tend to make over-simplifying assumptions which underestimate uncertainty. To address these limitations, we propose a novel framework for uncertainty estimation. Based on Bayesian belief networks and Monte-Carlo sampling, our framework not only fully models the different sources of prediction uncertainty, but also incorporates prior data information, e.g. sensor noise. We show theoretically that this gives us the ability to capture uncertainty better than existing methods. In addition, our framework has several desirable properties: (i) it is agnostic to the network architecture and task; (ii) it does not require changes in the optimization process; (iii) it can be applied to already trained architectures. We thoroughly validate the proposed framework through extensive experiments on both computer vision and control tasks, where we outperform previous methods by up to 23% in accuracy.

cs.CV↗

arXiv2020

Registration made easy -- standalone orthopedic navigation with HoloLens

In surgical navigation, finding correspondence between preoperative plan and intraoperative anatomy, the so-called registration task, is imperative. One promising approach is to intraoperatively digitize anatomy and register it with the preoperative plan. State-of-the-art commercial navigation systems implement such approaches for pedicle screw placement in spinal fusion surgery. Although these systems improve surgical accuracy, they are not gold standard in clinical practice. Besides economical reasons, this may be due to their difficult integration into clinical workflows and unintuitive navigation feedback. Augmented Reality has the potential to overcome these limitations. Consequently, we propose a surgical navigation approach comprising intraoperative surface digitization for registration and intuitive holographic navigation for pedicle screw placement that runs entirely on the Microsoft HoloLens. Preliminary results from phantom experiments suggest that the method may meet clinical accuracy requirements.

cs.CV↗

arXiv2019

Deep Drone Racing: From Simulation to Reality with Domain Randomization

Dynamically changing environments, unreliable state estimation, and operation under severe resource constraints are fundamental challenges that limit the deployment of small autonomous drones. We address these challenges in the context of autonomous, vision-based drone racing in dynamic environments. A racing drone must traverse a track with possibly moving gates at high speed. We enable this functionality by combining the performance of a state-of-the-art planning and control system with the perceptual awareness of a convolutional neural network (CNN). The resulting modular system is both platform- and domain-independent: it is trained in simulation and deployed on a physical quadrotor without any fine-tuning. The abundance of simulated data, generated via domain randomization, makes our system robust to changes of illumination and gate appearance. To the best of our knowledge, our approach is the first to demonstrate zero-shot sim-to-real transfer on the task of agile drone flight. We extensively test the precision and robustness of our system, both in simulation and on a physical platform, and show significant improvements over the state of the art.

cs.RO↗

arXiv2019

Exploration Without Global Consistency Using Local Volume Consolidation

In exploration, the goal is to build a map of an unknown environment. Most state-of-the-art approaches use map representations that require drift-free state estimates to function properly. Real-world state estimators, however, exhibit drift. In this paper, we present a 2D map representation for exploration that is robust to drift. Rather than a global map, it uses local metric volumes connected by relative pose estimates. This pose-graph does not need to be globally consistent. Overlaps between the volumes are resolved locally, rather than on the faulty estimate of space. We demonstrate our representation with a frontier-based exploration approach, evaluate it under different conditions and compare it with a commonly-used grid-based representation. We show that, at the cost of longer exploration time, using the proposed representation allows full coverage of space even for very large drift in the state estimate, contrary to the grid-based representation. The system is validated in a real world experiment and we discuss its extension to 3D.

cs.RO↗

arXiv2019

Event-Based Motion Segmentation by Motion Compensation

In contrast to traditional cameras, whose pixels have a common exposure time, event-based cameras are novel bio-inspired sensors whose pixels work independently and asynchronously output intensity changes (called "events"), with microsecond resolution. Since events are caused by the apparent motion of objects, event-based cameras sample visual information based on the scene dynamics and are, therefore, a more natural fit than traditional cameras to acquire motion, especially at high speeds, where traditional cameras suffer from motion blur. However, distinguishing between events caused by different moving objects and by the camera's ego-motion is a challenging task. We present the first per-event segmentation method for splitting a scene into independently moving objects. Our method jointly estimates the event-object associations (i.e., segmentation) and the motion parameters of the objects (or the background) by maximization of an objective function, which builds upon recent results on event-based motion-compensation. We provide a thorough evaluation of our method on a public dataset, outperforming the state-of-the-art by as much as 10%. We also show the first quantitative evaluation of a segmentation algorithm for event cameras, yielding around 90% accuracy at 4 pixels relative displacement.

cs.CV↗

arXiv2019

End-to-End Learning of Representations for Asynchronous Event-Based Data

Event cameras are vision sensors that record asynchronous streams of per-pixel brightness changes, referred to as "events". They have appealing advantages over frame-based cameras for computer vision, including high temporal resolution, high dynamic range, and no motion blur. Due to the sparse, non-uniform spatiotemporal layout of the event signal, pattern recognition algorithms typically aggregate events into a grid-based representation and subsequently process it by a standard vision pipeline, e.g., Convolutional Neural Network (CNN). In this work, we introduce a general framework to convert event streams into grid-based representations through a sequence of differentiable operations. Our framework comes with two main advantages: (i) allows learning the input event representation together with the task dedicated network in an end to end manner, and (ii) lays out a taxonomy that unifies the majority of extant event representations in the literature and identifies novel ones. Empirically, we show that our approach to learning the event representation end-to-end yields an improvement of approximately 12% on optical flow estimation and object recognition over state-of-the-art methods.

cs.CV↗

arXiv2019

SIPs: Succinct Interest Points from Unsupervised Inlierness Probability Learning

A wide range of computer vision algorithms rely on identifying sparse interest points in images and establishing correspondences between them. However, only a subset of the initially identified interest points results in true correspondences (inliers). In this paper, we seek a detector that finds the minimum number of points that are likely to result in an application-dependent "sufficient" number of inliers k. To quantify this goal, we introduce the "k-succinctness" metric. Extracting a minimum number of interest points is attractive for many applications, because it can reduce computational load, memory, and data transmission. Alongside succinctness, we introduce an unsupervised training methodology for interest point detectors that is based on predicting the probability of a given pixel being an inlier. In comparison to previous learned detectors, our method requires the least amount of data pre-processing. Our detector and other state-of-the-art detectors are extensively evaluated with respect to succinctness on popular public datasets covering both indoor and outdoor scenes, and both wide and narrow baselines. In certain cases, our detector is able to obtain an equivalent amount of inliers with as little as 60% of the amount of points of other detectors. The code and trained networks are provided at https://github.com/uzh-rpg/sips2_open .

cs.CV↗

arXiv2019

Matching Features without Descriptors: Implicitly Matched Interest Points

The extraction and matching of interest points is a prerequisite for many geometric computer vision problems. Traditionally, matching has been achieved by assigning descriptors to interest points and matching points that have similar descriptors. In this paper, we propose a method by which interest points are instead already implicitly matched at detection time. With this, descriptors do not need to be calculated, stored, communicated, or matched any more. This is achieved by a convolutional neural network with multiple output channels and can be thought of as a collection of a variety of detectors, each specialized to specific visual features. This paper describes how to design and train such a network in a way that results in successful relative pose estimation performance despite the limitation on interest point count. While the overall matching score is slightly lower than with traditional methods, the approach is descriptor free and thus enables localization systems with a significantly smaller memory footprint and multi-agent localization systems with lower bandwidth requirements. The network also outputs the confidence for a specific interest point resulting in a valid match. We evaluate performance relative to state-of-the-art alternatives.

cs.CV↗