We present a challenging dataset, the TartanAir, for robot navigation task and more. The data is collected in photo-realistic simulation environments in the presence of various light conditions, weather and moving objects. By collecting data in simulation, we are able to obtain multi-modal sensor data and precise ground truth labels, including the stereo RGB image, depth image, segmentation, optical flow, camera poses, and LiDAR point cloud. We set up a large number of environments with various styles and scenes, covering challenging viewpoints and diverse motion patterns, which are difficult to achieve by using physical data collection platforms.
Accurate registration of 2D imagery with point clouds is a key technology for image-LiDAR point cloud fusion, camera to laser scanner calibration and camera localization. Despite continuous improvements, automatic registration of 2D and 3D data without using additional textured information still faces great challenges. In this paper, we propose a new 2D-3D registration method to estimate 2D-3D line feature correspondences and the camera pose in untextured point clouds of structured environments. Specifically, we first use geometric constraints between vanishing points and 3D parallel lines to compute all feasible camera rotations. Then, we utilize a hypothesis testing strategy to estimate the 2D-3D line correspondences and the translation vector. By checking the consistency with computed correspondences, the best rotation matrix can be found. Finally, the camera pose is further refined using non-linear optimization with all the 2D-3D line correspondences. The experimental results demonstrate the effectiveness of the proposed method on the synthetic and real dataset (outdoors and indoors) with repeated structures and rapid depth changes.
This work presents dense stereo reconstruction using high-resolution images for infrastructure inspections. The state-of-the-art stereo reconstruction methods, both learning and non-learning ones, consume too much computational resource on high-resolution data. Recent learning-based methods achieve top ranks on most benchmarks. However, they suffer from the generalization issue due to lack of task-specific training data. We propose to use a less resource demanding non-learning method, guided by a learning-based model, to handle high-resolution images and achieve accurate stereo reconstruction. The deep-learning model produces an initial disparity prediction with uncertainty for each pixel of the down-sampled stereo image pair. The uncertainty serves as a self-measurement of its generalization ability and the per-pixel searching range around the initially predicted disparity. The downstream process performs a modified version of the Semi-Global Block Matching method with the up-sampled per-pixel searching range. The proposed deep-learning assisted method is evaluated on the Middlebury dataset and high-resolution stereo images collected by our customized binocular stereo camera. The combination of learning and non-learning methods achieves better performance on 12 out of 15 cases of the Middlebury dataset. In our infrastructure inspection experiments, the average 3D reconstruction error is less than 0.004m.
Although Structure-from-Motion (SfM) as a maturing technique has been widely used in many applications, state-of-the-art SfM algorithms are still not robust enough in certain situations. For example, images for inspection purposes are often taken in close distance to obtain detailed textures, which will result in less overlap between images and thus decrease the accuracy of estimated motion. In this paper, we propose a LiDAR-enhanced SfM pipeline that jointly processes data from a rotating LiDAR and a stereo camera pair to estimate sensor motions. We show that incorporating LiDAR helps to effectively reject falsely matched images and significantly improve the model consistency in large-scale environments. Experiments are conducted in different environments to test the performance of the proposed pipeline and comparison results with the state-of-the-art SfM algorithms are reported.
Aerial cinematography is revolutionizing industries that require live and dynamic camera viewpoints such as entertainment, sports, and security. However, safely piloting a drone while filming a moving target in the presence of obstacles is immensely taxing, often requiring multiple expert human operators. Hence, there is demand for an autonomous cinematographer that can reason about both geometry and scene context in real-time. Existing approaches do not address all aspects of this problem; they either require high-precision motion-capture systems or GPS tags to localize targets, rely on prior maps of the environment, plan for short time horizons, or only follow artistic guidelines specified before flight. In this work, we address the problem in its entirety and propose a complete system for real-time aerial cinematography that for the first time combines: (1) vision-based target estimation; (2) 3D signed-distance mapping for occlusion estimation; (3) efficient trajectory optimization for long time-horizon camera motion; and (4) learning-based artistic shot selection. We extensively evaluate our system both in simulation and in field experiments by filming dynamic targets moving through unstructured environments. Our results indicate that our system can operate reliably in the real world without restrictive assumptions. We also provide in-depth analysis and discussions for each module, with the hope that our design tradeoffs can generalize to other related applications. Videos of the complete system can be found at: https://youtu.be/ookhHnqmlaU.
Stereo cameras are a popular choice for obstacle avoidance for outdoor lighweight, low-cost robotics applications. However, they are unable to sense thin and reflective objects well. Currently, many algorithms are tuned to perform well on indoor scenes like the Middlebury dataset. When navigating outdoors, reflective objects, like windows and glass, and thin obstacles, like wires, are not well handled by most stereo disparity algorithms. Reflections, repeating patterns and objects parallel to the cameras' baseline causes mismatches between image pairs which leads to bad disparity estimates. Thin obstacles are difficult for many sliding window based disparity methods to detect because they do not take up large portions of the pixels in the sliding window. We use a trinocular camera setup and micropolarizer camera capable of detecting reflective objects to overcome these issues. We present a hierarchical disparity algorithm that reduces noise, separately identify wires using semantic object triangulation in three images, and use information about the polarization of light to estimate the disparity of reflective objects. We evaluate our approach on outdoor data that we collected. Our method contained an average of 9.27% of bad pixels compared to a typical stereo algorithm's 18.4% of bad pixels in scenes containing reflective objects. Our trinocular and semantic wire disparity methods detected 53% of wire pixels, whereas a typical two camera stereo algorithm detected 5%.
Machines are a long way from robustly solving open-world perception-control tasks, such as first-person view (FPV) drone racing. While recent advances in Machine Learning, especially Reinforcement and Imitation Learning show promise, they are constrained by the need of large amounts of difficult to collect real-world data for learning robust behaviors in diverse scenarios. In this work we propose to learn rich representations and policies by leveraging unsupervised data, such as video footage from an FPV drone, together with easy to generate simulated labeled data. Our approach takes a cross-modal perspective, where separate modalities correspond to the raw camera sensor data and the system states relevant to the task, such as the relative pose gates to the UAV. We fuse both data modalities into a novel factored architecture that learns a joint low-dimensional representation via Variational Auto Encoders. Such joint representations allow us to leverage rich labeled information from simulations together with the diversity of possible experiences via the unsupervised real-world data. We present experiments in simulation that provide insights into the rich latent spaces learned with our proposed representations, and also show that the use of our cross-modal architecture improves control policy performance in over 5X in comparison with end-to-end learning or purely unsupervised feature extractors. Finally, we present real-life results for drone navigation, showing that the learned representations and policies can generalize across simulation and reality.
We present a dataset of several fault types in control surfaces of a fixed-wing Unmanned Aerial Vehicle (UAV) for use in Fault Detection and Isolation (FDI) and Anomaly Detection (AD) research. Currently, the dataset includes processed data for 47 autonomous flights with scenarios for eight different types of control surface (actuator and engine) faults, with a total of 66 minutes of flight in normal conditions and 13 minutes of post-fault flight time. It additionally includes many hours of raw data of fully-autonomous, autopilot-assisted and manual flights with tens of fault scenarios. The ground truth of the time and type of faults is provided in each scenario to enable evaluation of the methods using the dataset. We have also provided the helper tools in several programming languages to load and work with the data and to help the evaluation of a detection method using the dataset. A set of metrics is proposed to help to compare different methods using the dataset. Most of the current fault detection methods are evaluated in simulation and as far as we know, this dataset is the only one providing the real flight data with faults in such capacity. We hope it will help advance the state-of-the-art in Anomaly Detection or FDI research for Autonomous Aerial Vehicles and mobile robots to enhance the safety of autonomous and remote flight operations further. The dataset and the provided tools can be accessed from http://theairlab.org/alfa-dataset.
Fusing data from LiDAR and camera is conceptually attractive because of their complementary properties. For instance, camera images are higher resolution and have colors, while LiDAR data provide more accurate range measurements and have a wider Field Of View (FOV). However, the sensor fusion problem remains challenging since it is difficult to find reliable correlations between data of very different characteristics (geometry vs. texture, sparse vs. dense). This paper proposes an offline LiDAR-camera fusion method to build dense, accurate 3D models. Specifically, our method jointly solves a bundle adjustment (BA) problem and a cloud registration problem to compute camera poses and the sensor extrinsic calibration. In experiments, we show that our method can achieve an averaged accuracy of 2.7mm and resolution of 70 points per square cm by comparing to the ground truth data from a survey scanner. Furthermore, the extrinsic calibration result is discussed and shown to outperform the state-of-the-art method.
The recent increase in the use of aerial vehicles raises concerns about the safety and reliability of autonomous operations. There is a growing need for methods to monitor the status of these aircraft and report any faults and anomalies to the safety pilot or to the autopilot to deal with the emergency situation. In this paper, we present a real-time approach using the Recursive Least Squares method to detect anomalies in the behavior of an aircraft. The method models the relationship between correlated input-output pairs online and uses the model to detect the anomalies. The result is an easy-to-deploy anomaly detection method that does not assume a specific aircraft model and can detect many types of faults and anomalies in a wide range of autonomous aircraft. The experiments on this method show a precision of $88.23\%$, recall of $88.23\%$ and $86.36\%$ accuracy for over 22 flight tests. The other contribution is providing a new fault detection open dataset for autonomous aircraft, which contains complete data and the ground truth for 22 fixed-wing flights with eight different types of mid-flight actuator failures to help future fault detection research for aircraft.