In this work we present a monocular visual odometry (VO) algorithm which leverages geometry-based methods and deep learning. Most existing VO/SLAM systems with superior performance are based on geometry and have to be carefully designed for different application scenarios. Moreover, most monocular systems suffer from scale-drift issue.Some recent deep learning works learn VO in an end-to-end manner but the performance of these deep systems is still not comparable to geometry-based methods. In this work, we revisit the basics of VO and explore the right way for integrating deep learning with epipolar geometry and Perspective-n-Point (PnP) method. Specifically, we train two convolutional neural networks (CNNs) for estimating single-view depths and two-view optical flows as intermediate outputs. With the deep predictions, we design a simple but robust frame-to-frame VO algorithm (DF-VO) which outperforms pure deep learning-based and geometry-based methods. More importantly, our system does not suffer from the scale-drift issue being aided by a scale consistent single-view depth CNN. Extensive experiments on KITTI dataset shows the robustness of our system and a detailed ablation study shows the effect of different factors in our system.
Semantically interpreting the traffic scene is crucial for autonomous transportation and robotics systems. However, state-of-the-art semantic segmentation pipelines are dominantly designed to work with pinhole cameras and train with narrow Field-of-View (FoV) images. In this sense, the perception capacity is severely limited to offer higher-level confidence for upstream navigation tasks. In this paper, we propose a network adaptation framework to achieve Panoramic Annular Semantic Segmentation (PASS), which allows to re-use conventional pinhole-view image datasets, enabling modern segmentation networks to comfortably adapt to panoramic images. Specifically, we adapt our proposed SwaftNet to enhance the sensitivity to details by implementing attention-based lateral connections between the detail-critical encoder layers and the context-critical decoder layers. We benchmark the performance of efficient segmenters on panoramic segmentation with our extended PASS dataset, demonstrating that the proposed real-time SwaftNet outperforms state-of-the-art efficient networks. Furthermore, we assess real-world performance when deploying the Detail-Sensitive PASS (DS-PASS) system on a mobile robot and an instrumented vehicle, as well as the benefit of panoramic semantics for visual odometry, showing the robustness and potential to support diverse navigational applications.
We present a method for decomposing the 3D scene flow observed from a moving stereo rig into stationary scene elements and dynamic object motion. Our unsupervised learning framework jointly reasons about the camera motion, optical flow, and 3D motion of moving objects. Three cooperating networks predict stereo matching, camera motion, and residual flow, which represents the flow component due to object motion and not from camera motion. Based on rigid projective geometry, the estimated stereo depth is used to guide the camera motion estimation, and the depth and camera motion are used to guide the residual flow estimation. We also explicitly estimate the 3D scene flow of dynamic objects based on the residual flow and scene depth. Experiments on the KITTI dataset demonstrate the effectiveness of our approach and show that our method outperforms other state-of-the-art algorithms on the optical flow and visual odometry tasks.
Place recognition is a core component of Simultaneous Localization and Mapping (SLAM) algorithms. Particularly in visual SLAM systems, previously-visited places are recognized by measuring the appearance similarity between images representing these locations. However, such approaches are sensitive to visual appearance change and also can be computationally expensive. In this paper, we propose an alternative approach adapting LiDAR descriptors for 3D points obtained from stereo-visual odometry for place recognition. 3D points are potentially more reliable than 2D visual cues (e.g., 2D features) against environmental changes (e.g., variable illumination) and this may benefit visual SLAM systems in long-term deployment scenarios. Stereo-visual odometry generates 3D points with an absolute scale, which enables us to use LiDAR descriptors for place recognition with high computational efficiency. Through extensive evaluations on standard benchmark datasets, we demonstrate the accuracy, efficiency, and robustness of using 3D points for place recognition over 2D methods.
Visual odometry shows excellent performance in a wide range of environments. However, in visually-denied scenarios (e.g. heavy smoke or darkness), pose estimates degrade or even fail. Thermal cameras are commonly used for perception and inspection when the environment has low visibility. However, their use in odometry estimation is hampered by the lack of robust visual features. In part, this is as a result of the sensor measuring the ambient temperature profile rather than scene appearance and geometry. To overcome this issue, we propose a Deep Neural Network model for thermal-inertial odometry (DeepTIO) by incorporating a visual hallucination network to provide the thermal network with complementary information. The hallucination network is taught to predict fake visual features from thermal images by using Huber loss. We also employ selective fusion to attentively fuse the features from three different modalities, i.e thermal, hallucination, and inertial features. Extensive experiments are performed in hand-held and mobile robot data in benign and smoke-filled environments, showing the efficacy of the proposed model.
This paper proposes a novel approach to stereo visual odometry without stereo matching. It is particularly robust in scenes of repetitive high-frequency textures. Referred to as DSVO (Direct Stereo Visual Odometry), it operates directly on pixel intensities, without any explicit feature matching, and is thus efficient and more accurate than the state-of-the-art stereo-matching-based methods. It applies a semi-direct monocular visual odometry running on one camera of the stereo pair, tracking the camera pose and mapping the environment simultaneously; the other camera is used to optimize the scale of monocular visual odometry. We evaluate DSVO in a number of challenging scenes to evaluate its performance and present comparisons with the state-of-the-art stereo visual odometry algorithms.
Recent work has shown that CNN-based depth and ego-motion estimators can be learned using unlabelled monocular videos. However, the performance is limited by unidentified moving objects that violate the underlying static scene assumption in geometric image reconstruction. More significantly, due to lack of proper constraints, networks output scale-inconsistent results over different samples, i.e., the ego-motion network cannot provide full camera trajectories over a long video sequence because of the per-frame scale ambiguity. This paper tackles these challenges by proposing a geometry consistency loss for scale-consistent predictions and an induced self-discovered mask for handling moving objects and occlusions. Since we do not leverage multi-task learning like recent works, our framework is much simpler and more efficient. Comprehensive evaluation results demonstrate that our depth estimator achieves the state-of-the-art performance on the KITTI dataset. Moreover, we show that our ego-motion network is able to predict a globally scale-consistent camera trajectory for long video sequences, and the resulting visual odometry accuracy is competitive with the recent model that is trained using stereo videos. To the best of our knowledge, this is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a long video sequence.
Glacial science could benefit tremendously from autonomous robots, but previous glacial robots have had perception issues in these colorless and featureless environments, specifically with visual feature extraction. This translates to failures in visual odometry and visual navigation. Glaciologists use near-infrared imagery to reveal the underlying heterogeneous spatial structure of snow and ice, and we theorize that this hidden near-infrared structure could produce more and higher quality features than available in visible light. We took a custom camera rig to Igloo Cave at Mt. St. Helens to test our theory. The camera rig contains two identical machine vision cameras, one which was outfitted with multiple filters to see only near-infrared light. We extracted features from short video clips taken inside Igloo Cave at Mt. St. Helens, using three popular feature extractors (FAST, SIFT, and SURF). We quantified the number of features and their quality for visual navigation by comparing the resulting orientation estimates to ground truth. Our main contribution is the use of NIR longpass filters to improve the quantity and quality of visual features in icy terrain, irrespective of the feature extractor used.
Multi-spectral sensors consisting of a standard (visible-light) camera and a long-wave infrared camera can simultaneously provide both visible and thermal images. Since thermal images are independent from environmental illumination, they can help to overcome certain limitations of standard cameras under complicated illumination conditions. However, due to the difference in the information source of the two types of cameras, their images usually share very low texture similarity. Hence, traditional texture-based feature matching methods cannot be directly applied to obtain stereo correspondences. To tackle this problem, a multi-spectral visual odometry method without explicit stereo matching is proposed in this paper. Bundle adjustment of multi-view stereo is performed on the visible and the thermal images using direct image alignment. Scale drift can be avoided by additional temporal observations of map points with the fixed-baseline stereo. Experimental results indicate that the proposed method can provide accurate visual odometry results with recovered metric scale. Moreover, the proposed method can also provide a metric 3D reconstruction in semi-dense density with multi-spectral information, which is not available from existing multi-spectral methods.
We propose a self-supervised learning framework for visual odometry (VO) that incorporates correlation of consecutive frames and takes advantage of adversarial learning. Previous methods tackle self-supervised VO as a local structure from motion (SfM) problem that recovers depth from single image and relative poses from image pairs by minimizing photometric loss between warped and captured images. As single-view depth estimation is an ill-posed problem, and photometric loss is incapable of discriminating distortion artifacts of warped images, the estimated depth is vague and pose is inaccurate. In contrast to previous methods, our framework learns a compact representation of frame-to-frame correlation, which is updated by incorporating sequential information. The updated representation is used for depth estimation. Besides, we tackle VO as a self-supervised image generation task and take advantage of Generative Adversarial Networks (GAN). The generator learns to estimate depth and pose to generate a warped target image. The discriminator evaluates the quality of generated image with high-level structural perception that overcomes the problem of pixel-wise loss in previous methods. Experiments on KITTI and Cityscapes datasets show that our method obtains more accurate depth with details preserved and predicted pose outperforms state-of-the-art self-supervised methods significantly.
This draft summarizes some basics about geometric computer vision needed to implement efficient computer vision algorithms for applications that use measurements from at least one digital camera mounted on a moving platform with a special focus on automotive applications processing image streams taken from cameras mounted on a car. Our intention is twofold: On the one hand, we would like to introduce well-known basic geometric relations in a compact way that can also be found in lecture books about geometric computer vision like [1, 2]. On the other hand, we would like to share some experience about subtleties that should be taken into account in order to set up quite simple but robust and fast vision algorithms that are able to run in real time. We added a conglomeration of literature, we found to be relevant when implementing basic algorithms like optical flow, visual odometry and structure from motion. The reader should get some feeling about how the estimates of these algorithms are interrelated, which parts of the algorithms are critical in terms of robustness and what kind of additional assumptions can be useful to constrain the solution space of the underlying usually non-convex optimization problems.
We propose to leverage the local information in image sequences to support global camera relocalization. In contrast to previous methods that regress global poses from single images, we exploit the spatial-temporal consistency in sequential images to alleviate uncertainty due to visual ambiguities by incorporating a visual odometry (VO) component. Specifically, we introduce two effective steps called content-augmented pose estimation and motion-based refinement. The content-augmentation step focuses on alleviating the uncertainty of pose estimation by augmenting the observation based on the co-visibility in local maps built by the VO stream. Besides, the motion-based refinement is formulated as a pose graph, where the camera poses are further optimized by adopting relative poses provided by the VO component as additional motion constraints. Thus, the global consistency can be guaranteed. Experiments on the public indoor 7-Scenes and outdoor Oxford RobotCar benchmark datasets demonstrate that benefited from local information inherent in the sequence, our approach outperforms state-of-the-art methods, especially in some challenging cases, e.g., insufficient texture, highly repetitive textures, similar appearances, and over-exposure.
Dynamical models estimate and predict the temporal evolution of physical systems. State Space Models (SSMs) in particular represent the system dynamics with many desirable properties, such as being able to model uncertainty in both the model and measurements, and optimal (in the Bayesian sense) recursive formulations e.g. the Kalman Filter. However, they require significant domain knowledge to derive the parametric form and considerable hand-tuning to correctly set all the parameters. Data driven techniques e.g. Recurrent Neural Networks have emerged as compelling alternatives to SSMs with wide success across a number of challenging tasks, in part due to their ability to extract relevant features from rich inputs. They however lack interpretability and robustness to unseen conditions. In this work, we present DynaNet, a hybrid deep learning and time-varying state-space model which can be trained end-to-end. Our neural Kalman dynamical model allows us to exploit the relative merits of each approach. We demonstrate state-of-the-art estimation and prediction on a number of physically challenging tasks, including visual odometry, sensor fusion for visual-inertial navigation and pendulum control. In addition we show how DynaNet can indicate failures through investigation of properties such as the rate of innovation (Kalman Gain).
Estimating depth from a single image represents an attractive alternative to more traditional approaches leveraging multiple cameras. In this field, deep learning yielded outstanding results at the cost of needing large amounts of data labeled with precise depth measurements for training. An issue softened by self-supervised approaches leveraging monocular sequences or stereo pairs in place of expensive ground truth depth annotations. This paper enables to further improve monocular depth estimation by integrating into existing self-supervised networks a geometrical prior. Specifically, we propose a sparsity-invariant autoencoder able to process the output of conventional visual odometry algorithms working in synergy with depth-from-mono networks. Experimental results on the KITTI dataset show that by exploiting the geometrical prior, our proposal: i) outperforms existing approaches in the literature and ii) couples well with both compact and complex depth-from-mono architectures, allowing for its deployment on high-end GPUs as well as on embedded devices (e.g., NVIDIA Jetson TX2).
For ego-motion estimation, the feature representation of the scenes is crucial. Previous methods indicate that both the low-level and semantic feature-based methods can achieve promising results. Therefore, the incorporation of hierarchical feature representation may benefit from both methods. From this perspective, we propose a novel direct feature odometry framework, named DFO, for depth estimation and hierarchical feature representation learning from monocular videos. By exploiting the metric distance, our framework is able to learn the hierarchical feature representation without supervision. The pose is obtained with a coarse-to-fine approach from high-level to low-level features in enlarged feature maps. The pixel-level attention mask can be self-learned to provide the prior information. In contrast to the previous methods, our proposed method calculates the camera motion with a direct method rather than regressing the ego-motion from the pose network. With this approach, the consistency of the scale factor of translation can be constrained. Additionally, the proposed method is thus compatible with the traditional SLAM pipeline. Experiments on the KITTI dataset demonstrate the effectiveness of our method.
This paper presents a novel method to distill knowledge from a deep pose regressor network for efficient Visual Odometry (VO). Standard distillation relies on "dark knowledge" for successful knowledge transfer. As this knowledge is not available in pose regression and the teacher prediction is not always accurate, we propose to emphasize the knowledge transfer only when we trust the teacher. We achieve this by using teacher loss as a confidence score which places variable relative importance on the teacher prediction. We inject this confidence score to the main training task via Attentive Imitation Loss (AIL) and when learning the intermediate representation of the teacher through Attentive Hint Training (AHT) approach. To the best of our knowledge, this is the first work which successfully distill the knowledge from a deep pose regression network. Our evaluation on the KITTI and Malaga dataset shows that we can keep the student prediction close to the teacher with up to 92.95% parameter reduction and 2.12x faster in computation time.
In the paper, we propose a robust real-time visual odometry in dynamic environments via rigid-motion model updated by scene flow. The proposed algorithm consists of spatial motion segmentation and temporal motion tracking. The spatial segmentation first generates several motion hypotheses by using a grid-based scene flow and clusters the extracted motion hypotheses, separating objects that move independently of one another. Further, we use a dual-mode motion model to consistently distinguish between the static and dynamic parts in the temporal motion tracking stage. Finally, the proposed algorithm estimates the pose of a camera by taking advantage of the region classified as static parts. In order to evaluate the performance of visual odometry under the existence of dynamic rigid objects, we use self-collected dataset containing RGB-D images and motion capture data for ground-truth. We compare our algorithm with state-of-the-art visual odometry algorithms. The validation results suggest that the proposed algorithm can estimate the pose of a camera robustly and accurately in dynamic environments.
Optical Flow (OF) and depth are commonly used for visual odometry since they provide sufficient information about camera ego-motion in a rigid scene. We reformulate the problem of ego-motion estimation as a problem of motion estimation of a 3D-scene with respect to a static camera. The entire scene motion can be represented as a combination of motions of its visible points. Using OF and depth we estimate a motion of each point in terms of 6DoF and represent results in the form of motion maps, each one addressing single degree of freedom. In this work we provide motion maps as inputs to a deep neural network that predicts 6DoF of scene motion. Through our evaluation on outdoor and indoor datasets we show that utilizing motion maps leads to accuracy improvement in comparison with naive stacking of depth and OF. Another contribution of our work is a novel network architecture that efficiently exploits motion maps and outperforms learnable RGB/RGB-D baselines.
Stereo relative pose problem lies at the core of stereo visual odometry systems that are used in many applications. In this work, we present two minimal solvers for the stereo relative pose. We specifically consider the case when a minimal set consists of three point or line features and each of them has three known projections on two stereo cameras. We validate the importance of this formulation for practical purposes in our experiments with motion estimation. We then present a complete classification of minimal cases with three point or line correspondences each having three projections, and present two new solvers that can handle all such cases. We demonstrate a considerable effect from the integration of the new solvers into a visual SLAM system.
Recently end-to-end unsupervised deep learning methods have achieved an effect beyond geometric methods for visual depth and ego-motion estimation tasks. These data-based learning methods perform more robustly and accurately in some of the challenging scenes. The encoder-decoder network has been widely used in the depth estimation and the RCNN has brought significant improvements in the ego-motion estimation. Furthermore, the latest use of Generative Adversarial Nets(GANs) in depth and ego-motion estimation has demonstrated that the estimation could be further improved by generating pictures in the game learning process. This paper proposes a novel unsupervised network system for visual depth and ego-motion estimation: Stacked Generative Adversarial Network(SGANVO). It consists of a stack of GAN layers, of which the lowest layer estimates the depth and ego-motion while the higher layers estimate the spatial features. It can also capture the temporal dynamic due to the use of a recurrent representation across the layers. See Fig.1 for details. We select the most commonly used KITTI [1] data set for evaluation. The evaluation results show that our proposed method can produce better or comparable results in depth and ego-motion estimation.