This paper considers outdoor terrain mapping using RGB images obtained from an aerial vehicle. While feature-based localization and mapping techniques deliver real-time vehicle odometry and sparse keypoint depth reconstruction, a dense model of the environment geometry and semantics (vegetation, buildings, etc.) is usually recovered offline with significant computation and storage. This paper develops a joint 2D-3D learning approach to reconstruct a local metric-semantic mesh at each camera keyframe maintained by a visual odometry algorithm. Given the estimated camera trajectory, the local meshes can be assembled into a global environment model to capture the terrain topology and semantics during online operation. A local mesh is reconstructed using an initialization and refinement stage. In the initialization stage, we estimate the mesh vertex elevation by solving a least squares problem relating the vertex barycentric coordinates to the sparse keypoint depth measurements. In the refinement stage, we associate 2D image and semantic features with the 3D mesh vertices using camera projection and apply graph convolution to refine the mesh vertex spatial coordinates and semantic features based on joint 2D and 3D supervision. Quantitative and qualitative evaluation using real aerial images show the potential of our method to support environmental monitoring and surveillance applications.
We introduce EDS, a direct monocular visual odometry using events and frames. Our algorithm leverages the event generation model to track the camera motion in the blind time between frames. The method formulates a direct probabilistic approach of observed brightness increments. Per-pixel brightness increments are predicted using a sparse number of selected 3D points and are compared to the events via the brightness increment error to estimate camera motion. The method recovers a semi-dense 3D map using photometric bundle adjustment. EDS is the first method to perform 6-DOF VO using events and frames with a direct approach. By design, it overcomes the problem of changing appearance in indirect methods. We also show that, for a target error performance, EDS can work at lower frame rates than state-of-the-art frame-based VO solutions. This opens the door to low-power motion-tracking applications where frames are sparingly triggered "on demand" and our method tracks the motion in between. We release code and datasets to the public.
Monocular visual odometry (VO) is an important task in robotics and computer vision. Thus far, how to build accurate and robust monocular VO systems that can work well in diverse scenarios remains largely unsolved. In this paper, we propose a framework to exploit monocular depth estimation for improving VO. The core of our framework is a monocular depth estimation module with a strong generalization capability for diverse scenes. It consists of two separate working modes to assist the localization and mapping. With a single monocular image input, the depth estimation module predicts a relative depth to help the localization module on improving the accuracy. With a sparse depth map and an RGB image input, the depth estimation module can generate accurate scale-consistent depth for dense mapping. Compared with current learning-based VO methods, our method demonstrates a stronger generalization ability to diverse scenes. More significantly, our framework is able to boost the performances of existing geometry-based VO methods by a large margin.
Visual odometry is the process of estimating the position and orientation of a camera by analyzing the images associated to it. This paper develops a quick and accurate approach to visual odometry of a moving RGB-D camera navigating on a static environment. The proposed algorithm uses SURF (Speeded Up Robust Features) as feature extractor, RANSAC (Random Sample Consensus) to filter the results and Minimum Mean Square to estimate the rigid transformation of six parameters between successive video frames. Data from a Kinect camera were used in the tests. The results show that this approach is feasible and promising, surpassing in performance the algorithms ICP (Interactive Closest Point) and SfM (Structure from Motion) in tests using a publicly available dataset.
Existing vision based supervised approaches to lateral vehicle control are capable of directly mapping RGB images to the appropriate steering commands. However, they are prone to suffering from inadequate robustness in real world scenarios due to a lack of failure cases in the training data. In this paper, a framework for training a more robust and scalable model for lateral vehicle control is proposed. The framework only requires an unlabeled sequence of RGB images. The trained model takes a point cloud as input and predicts the lateral offset to a subsequent frame from which the steering angle is inferred. The frame poses are in turn obtained from visual odometry. The point cloud is conceived by projecting dense depth maps into 3D. An arbitrary number of additional trajectories from this point cloud can be generated during training. This is to increase the robustness of the model. Online experiments show that the performance of our method is superior to that of the supervised model.
Onboard localization capabilities for planetary rovers to date have used relative navigation, by integrating combinations of wheel odometry, visual odometry, and inertial measurements during each drive to track position relative to the start of each drive. At the end of each drive, a ground-in-the-loop (GITL) interaction is used to get a position update from human operators in a more global reference frame, by matching images or local maps from onboard the rover to orbital reconnaissance images or maps of a large region around the rover's current position. Autonomous rover drives are limited in distance so that accumulated relative navigation error does not risk the possibility of the rover driving into hazards known from orbital images. However, several rover mission concepts have recently been studied that require much longer drives between GITL cycles, particularly for the Moon. These concepts require greater autonomy to minimize GITL cycles to enable such large range; onboard global localization is a key element of such autonomy. Multiple techniques have been studied in the past for onboard rover global localization, but a satisfactory solution has not yet emerged. For the Moon, the ubiquitous craters offer a new possibility, which involves mapping craters from orbit, then recognizing crater landmarks with cameras and-or a lidar onboard the rover. This approach is applicable everywhere on the Moon, does not require high resolution stereo imaging from orbit as some other approaches do, and has potential to enable position knowledge with order of 5 to 10 m accuracy at all times. This paper describes our technical approach to crater-based lunar rover localization and presents initial results on crater detection using 3D point cloud data from onboard lidar or stereo cameras, as well as using shading cues in monocular onboard imagery.
Unsupervised learning for monocular camera motion and 3D scene understanding has gained popularity over traditional methods, relying on epipolar geometry or non-linear optimization. Notably, deep learning can overcome many issues of monocular vision, such as perceptual aliasing, low-textured areas, scale-drift, and degenerate motions. Also, concerning supervised learning, we can fully leverage video streams data without the need for depth or motion labels. However, in this work, we note that rotational motion can limit the accuracy of the unsupervised pose networks more than the translational component. Therefore, we present RAUM-VO, an approach based on a model-free epipolar constraint for frame-to-frame motion estimation (F2F) to adjust the rotation during training and online inference. To this end, we match 2D keypoints between consecutive frames using pre-trained deep networks, Superpoint and Superglue, while training a network for depth and pose estimation using an unsupervised training protocol. Then, we adjust the predicted rotation with the motion estimated by F2F using the 2D matches and initializing the solver with the pose network prediction. Ultimately, RAUM-VO shows a considerable accuracy improvement compared to other unsupervised pose networks on the KITTI dataset while reducing the complexity of other hybrid or traditional approaches and achieving comparable state-of-the-art results.
Monocular visual odometry (VO) has attracted extensive research attention by providing real-time vehicle motion from cost-effective camera images. However, state-of-the-art optimization-based monocular VO methods suffer from the scale inconsistency problem for long-term predictions. Deep learning has recently been introduced to address this issue by leveraging stereo sequences or ground-truth motions in the training dataset. However, it comes at an additional cost for data collection, and such training data may not be available in all datasets. In this work, we propose VRVO, a novel framework for retrieving the absolute scale from virtual data that can be easily obtained from modern simulation environments, whereas in the real domain no stereo or ground-truth data are required in either the training or inference phases. Specifically, we first train a scale-aware disparity network using both monocular real images and stereo virtual data. The virtual-to-real domain gap is bridged by using an adversarial training strategy to map images from both domains into a shared feature space. The resulting scale-consistent disparities are then integrated with a direct VO system by constructing a virtual stereo objective that ensures the scale consistency over long trajectories. Additionally, to address the suboptimality issue caused by the separate optimization backend and the learning process, we further propose a mutual reinforcement pipeline that allows bidirectional information flow between learning and optimization, which boosts the robustness and accuracy of each other. We demonstrate the effectiveness of our framework on the KITTI and vKITTI2 datasets.
This paper proposes a high-precision self-supervised monocular VO, which is specifically designed for navigation in foggy weather. A cycled generative adversarial network is designed to obtain high-quality self-supervised loss via forcing the forward and backward half-cycle to output consistent estimation. Moreover, gradient-based loss and perceptual loss are introduced to eliminate the interference of complex photometric change on self-supervised loss in foggy weather. To solve the ill-posed problem of depth estimation, a self-supervised multi-task learning aided depth estimation module is designed based on the strong correlation between the depth estimation and transmission map calculation of hazy images in foggy weather. The experimental results on the synthetic foggy KITTI dataset show that the proposed self-supervised monocular VO performs better in depth and pose estimation than other state-of-the-art monocular VO in the literature, indicating the designed method is more suitable for foggy weather.
Event cameras open up new possibilities for robotic perception due to their low latency and high dynamic range. On the other hand, developing effective event-based vision algorithms that fully exploit the beneficial properties of event cameras remains work in progress. In this paper, we focus on event-based visual odometry (VO). While existing event-driven VO pipelines have adopted continuous-time representations to asynchronously process event data, they either assume a known map, restrict the camera to planar trajectories, or integrate other sensors into the system. Towards map-free event-only monocular VO in SE(3), we propose an asynchronous structure-from-motion optimisation back-end. Our formulation is underpinned by a principled joint optimisation problem involving non-parametric Gaussian Process motion modelling and incremental maximum a posteriori inference. A high-performance incremental computation engine is employed to reason about the camera trajectory with every incoming event. We demonstrate the robustness of our asynchronous back-end in comparison to frame-based methods which depend on accurate temporal accumulation of measurements.
In this paper, we present a complete pipeline for 3D semantic mapping solely based on a stereo camera system. The pipeline comprises a direct sparse visual odometry front-end as well as a back-end for global optimization including GNSS integration, and semantic 3D point cloud labeling. We propose a simple but effective temporal voting scheme which improves the quality and consistency of the 3D point labels. Qualitative and quantitative evaluations of our pipeline are performed on the KITTI-360 dataset. The results show the effectiveness of our proposed voting scheme and the capability of our pipeline for efficient large-scale 3D semantic mapping. The large-scale mapping capabilities of our pipeline is furthermore demonstrated by presenting a very large-scale semantic map covering 8000 km of roads generated from data collected by a fleet of vehicles.
The motion of planar ground vehicles is often non-holonomic, and as a result may be modelled by the 2 DoF Ackermann steering model. We analyse the feasibility of estimating such motion with a downward facing camera that exerts fronto-parallel motion with respect to the ground plane. This turns the motion estimation into a simple image registration problem in which we only have to identify a 2-parameter planar homography. However, one difficulty that arises from this setup is that ground-plane features are indistinctive and thus hard to match between successive views. We encountered this difficulty by introducing the first globally-optimal, correspondence-less solution to plane-based Ackermann motion estimation. The solution relies on the branch-and-bound optimisation technique. Through the low-dimensional parametrisation, a derivation of tight bounds, and an efficient implementation, we demonstrate how this technique is eventually amenable to accurate real-time motion estimation. We prove its property of global optimality and analyse the impact of assuming a locally constant centre of rotation. Our results on real data finally demonstrate a significant advantage over the more traditional, correspondence-based hypothesise-and-test schemes.
Visual-inertial-odometry has attracted extensive attention in the field of autonomous driving and robotics. The size of Field of View (FoV) plays an important role in Visual-Odometry (VO) and Visual-Inertial-Odometry (VIO), as a large FoV enables to perceive a wide range of surrounding scene elements and features. However, when the field of the camera reaches the negative half plane, one cannot simply use [u,v,1]^T to represent the image feature points anymore. To tackle this issue, we propose LF-VIO, a real-time VIO framework for cameras with extremely large FoV. We leverage a three-dimensional vector with unit length to represent feature points, and design a series of algorithms to overcome this challenge. To address the scarcity of panoramic visual odometry datasets with ground-truth location and pose, we present the PALVIO dataset, collected with a Panoramic Annular Lens (PAL) system with an entire FoV of 360{\deg}x(40{\deg}-120{\deg}) and an IMU sensor. With a comprehensive variety of experiments, the proposed LF-VIO is verified on both the established PALVIO benchmark and a public fisheye camera dataset with a FoV of 360{\deg}x(0{\deg}-93.5{\deg}). LF-VIO outperforms state-of-the-art visual-inertial-odometry methods. Our dataset and code are made publicly available at https://github.com/flysoaryun/LF-VIO
We present a novel real-time visual odometry framework for a stereo setup of a depth and high-resolution event camera. Our framework balances accuracy and robustness against computational efficiency towards strong performance in challenging scenarios. We extend conventional edge-based semi-dense visual odometry towards time-surface maps obtained from event streams. Semi-dense depth maps are generated by warping the corresponding depth values of the extrinsically calibrated depth camera. The tracking module updates the camera pose through efficient, geometric semi-dense 3D-2D edge alignment. Our approach is validated on both public and self-collected datasets captured under various conditions. We show that the proposed method performs comparable to state-of-the-art RGB-D camera-based alternatives in regular conditions, and eventually outperforms in challenging conditions such as high dynamics or low illumination.
We present the Brown Pedestrian Odometry Dataset (BPOD) for benchmarking visual odometry algorithms in head-mounted pedestrian settings. This dataset was captured using synchronized global and rolling shutter stereo cameras in 12 diverse indoor and outdoor locations on Brown University's campus. Compared to existing datasets, BPOD contains more image blur and self-rotation, which are common in pedestrian odometry but rare elsewhere. Ground-truth trajectories are generated from stick-on markers placed along the pedestrian's path, and the pedestrian's position is documented using a third-person video. We evaluate the performance of representative direct, feature-based, and learning-based VO methods on BPOD. Our results show that significant development is needed to successfully capture pedestrian trajectories. The link to the dataset is here: \url{https://doi.org/10.26300/c1n7-7p93
Visual Odometry (VO) estimation is an important source of information for vehicle state estimation and autonomous driving. Recently, deep learning based approaches have begun to appear in the literature. However, in the context of driving, single sensor based approaches are often prone to failure because of degraded image quality due to environmental factors, camera placement, etc. To address this issue, we propose a deep sensor fusion framework which estimates vehicle motion using both pose and uncertainty estimations from multiple on-board cameras. We extract spatio-temporal feature representations from a set of consecutive images using a hybrid CNN - RNN model. We then utilise a Mixture Density Network (MDN) to estimate the 6-DoF pose as a mixture of distributions and a fusion module to estimate the final pose using MDN outputs from multi-cameras. We evaluate our approach on the publicly available, large scale autonomous vehicle dataset, nuScenes. The results show that the proposed fusion approach surpasses the state-of-the-art, and provides robust estimates and accurate trajectories compared to individual camera-based estimations.
Visual Odometry (VO) is used in many applications including robotics and autonomous systems. However, traditional approaches based on feature matching are computationally expensive and do not directly address failure cases, instead relying on heuristic methods to detect failure. In this work, we propose a deep learning-based VO model to efficiently estimate 6-DoF poses, as well as a confidence model for these estimates. We utilise a CNN - RNN hybrid model to learn feature representations from image sequences. We then employ a Mixture Density Network (MDN) which estimates camera motion as a mixture of Gaussians, based on the extracted spatio-temporal representations. Our model uses pose labels as a source of supervision, but derives uncertainties in an unsupervised manner. We evaluate the proposed model on the KITTI and nuScenes datasets and report extensive quantitative and qualitative results to analyse the performance of both pose and uncertainty estimation. Our experiments show that the proposed model exceeds state-of-the-art performance in addition to detecting failure cases using the predicted pose uncertainty.
Safe deployment of self-driving cars (SDC) necessitates thorough simulated and in-field testing. Most testing techniques consider virtualized SDCs within a simulation environment, whereas less effort has been directed towards assessing whether such techniques transfer to and are effective with a physical real-world vehicle. In this paper, we shed light on the problem of generalizing testing results obtained in a driving simulator to a physical platform and provide a characterization and quantification of the sim2real gap affecting SDC testing. In our empirical study, we compare SDC testing when deployed on a physical small-scale vehicle vs its digital twin. Due to the unavailability of driving quality indicators from the physical platform, we use neural rendering to estimate them through visual odometry, hence allowing full comparability with the digital twin. Then, we investigate the transferability of behavior and failure exposure between virtual and real-world environments, targeting both unintended abnormal test data and intended adversarial examples. Our study shows that, despite the usage of a faithful digital twin, there are still critical shortcomings that contribute to the reality gap between the virtual and physical world, threatening existing testing solutions that only consider virtual SDCs. On the positive side, our results present the test configurations for which physical testing can be avoided, either because their outcome does transfer between virtual and physical environments, or because the uncertainty profiles in the simulator can help predict their outcome in the real world.
We present 360-DFPE, a sequential floor plan estimation method that directly takes 360-images as input without relying on active sensors or 3D information. Our approach leverages a loosely coupled integration between a monocular visual SLAM solution and a monocular 360-room layout approach, which estimate camera poses and layout geometries, respectively. Since our task is to sequentially capture the floor plan using monocular images, the entire scene structure, room instances, and room shapes are unknown. To tackle these challenges, we first handle the scale difference between visual odometry and layout geometry via formulating an entropy minimization process, which enables us to directly align 360-layouts without knowing the entire scene in advance. Second, to sequentially identify individual rooms, we propose a novel room identification algorithm that tracks every room along the camera exploration using geometry information. Lastly, to estimate the final shape of the room, we propose a shortest path algorithm with an iterative coarse-to-fine strategy, which improves prior formulations with higher accuracy and faster run-time. Moreover, we collect a new floor plan dataset with challenging large-scale scenes, providing both point clouds and sequential 360-image information. Experimental results show that our monocular solution achieves favorable performance against the current state-of-the-art algorithms that rely on active sensors and require the entire scene reconstruction data in advance.
Visual odometry aims to track the incremental motion of an object using the information captured by visual sensors. In this work, we study the point cloud odometry problem, where only the point cloud scans obtained by the LiDAR (Light Detection And Ranging) are used to estimate object's motion trajectory. A lightweight point cloud odometry solution is proposed and named the green point cloud odometry (GreenPCO) method. GreenPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans. It consists of three steps. First, a geometry-aware point sampling scheme is used to select discriminant points from the large point cloud. Second, the view is partitioned into four regions surrounding the object, and the PointHop++ method is used to extract point features. Third, point correspondences are established to estimate object motion between two consecutive scans. Experiments on the KITTI dataset are conducted to demonstrate the effectiveness of the GreenPCO method. It is observed that GreenPCO outperforms benchmarking deep learning methods in accuracy while it has a significantly smaller model size and less training time.