Keypoint detection and description is fundamental yet important in many vision applications. Most existing methods use detect-then-describe or detect-and-describe strategy to learn local features without considering their context information. Consequently, it is challenging for these methods to learn robust local features. In this paper, we focus on the fusion of low-level textual information and high-level semantic context information to improve the discrimitiveness of local features. Specifically, we first estimate a score map to represent the distribution of potential keypoints according to the quality of descriptors of all pixels. Then, we extract and aggregate multi-scale high-level semantic features based by the guidance of the score map. Finally, the low-level local features and high-level semantic features are fused and refined using a residual module. Experiments on the challenging local feature benchmark dataset demonstrate that our method achieves the state-of-the-art performance in the local feature challenge of the visual localization benchmark.
In this paper, we propose a monocular visual localization pipeline leveraging semantic and depth cues. We apply semantic consistency evaluation to rank the image retrieval results and a practical clustering technique to reject estimation outliers. In addition, we demonstrate a substantial performance boost achieved with a combination of multiple feature extractors. Furthermore, by using depth prediction with a deep neural network, we show that a significant amount of falsely matched keypoints are identified and eliminated. The proposed pipeline outperforms most of the existing approaches at the Long-Term Visual Localization benchmark 2020.
Visual localization plays an important role in many applications. However, due to the large appearance variations such as season and illumination changes, as well as weather and day-night variations, it's still a big challenge for robust long-term visual localization algorithms. In this paper, we present a novel visual localization method using hybrid handcrafted and learned features with dense semantic 3D map. Hybrid features help us to make full use of their strengths in different imaging conditions, and the dense semantic map provide us reliable and complete geometric and semantic information for constructing sufficient 2D-3D matching pairs with semantic consistency scores. In our pipeline, we retrieve and score each candidate database image through the semantic consistency between the dense model and the query image. Then the semantic consistency score is used as a soft constraint in the weighted RANSAC-based PnP pose solver. Experimental results on long-term visual localization benchmarks demonstrate the effectiveness of our method compared with state-of-the-arts.
Mapping and localization, preferably from a small number of observations, are fundamental tasks in robotics. We address these tasks by combining spatial structure (differentiable mapping) and end-to-end learning in a novel neural network architecture: the Differentiable Mapping Network (DMN). The DMN constructs a spatially structured view-embedding map and uses it for subsequent visual localization with a particle filter. Since the DMN architecture is end-to-end differentiable, we can jointly learn the map representation and localization using gradient descent. We apply the DMN to sparse visual localization, where a robot needs to localize in a new environment with respect to a small number of images from known viewpoints. We evaluate the DMN using simulated environments and a challenging real-world Street View dataset. We find that the DMN learns effective map representations for visual localization. The benefit of spatial structure increases with larger environments, more viewpoints for mapping, and when training data is scarce. Project website: http://sites.google.com/view/differentiable-mapping
Electric vhicles and autonomous driving dominate current research efforts in the automotive sector. The two topics go hand in hand in terms of enabling safer and more environmentally friendly driving. One fundamental building block of an autonomous vehicle is the ability to build a map of the environment and localize itself on such a map. In this paper, we make use of a stereo camera sensor in order to perceive the environment and create the map. With live Simultaneous Localization and Mapping (SLAM), there is a risk of mislocalization, since no ground truth map is used as a reference and errors accumulate over time. Therefore, we first build up and save a map of visual features of the environment at low driving speeds with our extension to the ORB-SLAM\,2 package. In a second run, we reload the map and then localize on the previously built-up map. Loading and localizing on a previously built map can improve the continuous localization accuracy for autonomous vehicles in comparison to a full SLAM. This map saving feature is missing in the original ORB-SLAM\,2 implementation. We evaluate the localization accuracy for scenes of the KITTI dataset against the built up SLAM map. Furthermore, we test the localization on data recorded with our own small scale electric model car. We show that the relative translation error of the localization stays under 1\% for a vehicle travelling at an average longitudinal speed of 36 m/s in a feature-rich environment. The localization mode contributes to a better localization accuracy and lower computational load compared to a full SLAM. The source code of our contribution to the ORB-SLAM2 will be made public at: https://github.com/TUMFTM/orbslam-map-saving-extension.
Visual Localization is one of the key enabling technologies for autonomous driving and augmented reality. High quality datasets with accurate 6 Degree-of-Freedom (DoF) reference poses are the foundation for benchmarking and improving existing methods. Traditionally, reference poses have been obtained via Structure-from-Motion (SfM). However, SfM itself relies on local features which are prone to fail when images were taken under different conditions, e.g., day/ night changes. At the same time, manually annotating feature correspondences is not scalable and potentially inaccurate. In this work, we propose a semi-automated approach to generate reference poses based on feature matching between renderings of a 3D model and real images via learned features. Given an initial pose estimate, our approach iteratively refines the pose based on feature matches against a rendering of the model from the current pose estimate. We significantly improve the nighttime reference poses of the popular Aachen Day-Night dataset, showing that state-of-the-art visual localization methods perform better (up to $47\%$) than predicted by the original reference poses. We extend the dataset with new nighttime test images, provide uncertainty estimates for our new reference poses, and introduce a new evaluation criterion. We will make our reference poses and our framework publicly available upon publication.
Visual localization is a useful alternative to standard localization techniques. It works by utilizing cameras. In a typical scenario, features are extracted from captured images and compared with geo-referenced databases. Location information is then inferred from the matching results. Conventional schemes mainly use low-level visual features. These approaches offer good accuracy but suffer from scalability issues. In order to assist localization in large urban areas, this work explores a different path by utilizing high-level semantic information. It is found that object information in a street view can facilitate localization. A novel descriptor scheme called "semantic signature" is proposed to summarize this information. A semantic signature consists of type and angle information of visible objects at a spatial location. Several metrics and protocols are proposed for signature comparison and retrieval. They illustrate different trade-offs between accuracy and complexity. Extensive simulation results confirm the potential of the proposed scheme in large-scale applications. This paper is an extended version of a conference paper in CBMI'18. A more efficient retrieval protocol is presented with additional experiment results.
Localization is a critically essential and crucial enabler of autonomous robots. While deep learning has made significant strides in many computer vision tasks, it is still yet to make a sizeable impact on improving capabilities of metric visual localization. One of the major hindrances has been the inability of existing Convolutional Neural Network (CNN)-based pose regression methods to generalize to previously unseen places. Our recently introduced CMRNet effectively addresses this limitation by enabling map independent monocular localization in LiDAR-maps. In this paper, we now take it a step further by introducing CMRNet++, which is a significantly more robust model that not only generalizes to new places effectively, but is also independent of the camera parameters. We enable this capability by combining deep learning with geometric techniques, and by moving the metric reasoning outside the learning process. In this way, the weights of the network are not tied to a specific camera. Extensive evaluations of CMRNet++ on three challenging autonomous driving datasets, i.e., KITTI, Argoverse, and Lyft5, show that CMRNet++ outperforms CMRNet as well as other baselines by a large margin. More importantly, for the first-time, we demonstrate the ability of a deep learning approach to accurately localize without any retraining or fine-tuning in a completely new environment and independent of the camera parameters.
Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under challenging conditions, they are often limited in terms of precision. In this paper, we introduce S2DNet, a novel feature matching pipeline, designed and trained to efficiently establish both robust and accurate correspondences. By leveraging a sparse-to-dense matching paradigm, we cast the correspondence learning problem as a supervised classification task to learn to output highly peaked correspondence maps. We show that S2DNet achieves state-of-the-art results on the HPatches benchmark, as well as on several long-term visual localization datasets.
Recent learning-based approaches have achieved impressive results in the field of single-shot camera localization. However, how best to fuse multiple modalities (e.g., image and depth) and to deal with degraded or missing input are less well studied. In particular, we note that previous approaches towards deep fusion do not perform significantly better than models employing a single modality. We conjecture that this is because of the naive approaches to feature space fusion through summation or concatenation which do not take into account the different strengths of each modality. To address this, we propose an end-to-end framework, termed VMLoc, to fuse different sensor inputs into a common latent space through a variational Product-of-Experts (PoE) followed by attention-based fusion. Unlike previous multimodal variational works directly adapting the objective function of vanilla variational auto-encoder, we show how camera localization can be accurately estimated through an unbiased objective function based on importance weighting. Our model is extensively evaluated on RGB-D datasets and the results prove the efficacy of our model. The source code is available at https://github.com/kaichen-z/VMLoc.
We present a visual localization framework based on novel deep attention aware features for autonomous driving that achieves centimeter level localization accuracy. Conventional approaches to the visual localization problem rely on handcrafted features or human-made objects on the road. They are known to be either prone to unstable matching caused by severe appearance or lighting changes, or too scarce to deliver constant and robust localization results in challenging scenarios. In this work, we seek to exploit the deep attention mechanism to search for salient, distinctive and stable features that are good for long-term matching in the scene through a novel end-to-end deep neural network. Furthermore, our learned feature descriptors are demonstrated to be competent to establish robust matches and therefore successfully estimate the optimal camera poses with high precision. We comprehensively validate the effectiveness of our method using a freshly collected dataset with high-quality ground truth trajectories and hardware synchronization between sensors. Results demonstrate that our method achieves a competitive localization accuracy when compared to the LiDAR-based localization solutions under various challenging circumstances, leading to a potential low-cost localization solution for autonomous driving.
Autonomous navigation emerges from both motion and local visual perception in real-world environments. However, most successful robotic motion estimation methods (e.g. VO, SLAM, SfM) and vision systems (e.g. CNN, visual place recognition-VPR) are often separately used for mapping and localization tasks. Conversely, recent reinforcement learning (RL) based methods for visual navigation rely on the quality of GPS data reception, which may not be reliable when directly using it as ground truth across multiple, month-spaced traversals in large environments. In this paper, we propose a novel motion and visual perception approach, dubbed MVP, that unifies these two sensor modalities for large-scale, target-driven navigation tasks. Our MVP-based method can learn faster, and is more accurate and robust to both extreme environmental changes and poor GPS data than corresponding vision-only navigation methods. MVP temporally incorporates compact image representations, obtained using VPR, with optimized motion estimation data, including but not limited to those from VO or optimized radar odometry (RO), to efficiently learn self-supervised navigation policies via RL. We evaluate our method on two large real-world datasets, Oxford Robotcar and Nordland Railway, over a range of weather (e.g. overcast, night, snow, sun, rain, clouds) and seasonal (e.g. winter, spring, fall, summer) conditions using the new CityLearn framework; an interactive environment for efficiently training navigation agents. Our experimental results, on traversals of the Oxford RobotCar dataset with no GPS data, show that MVP can achieve 53% and 93% navigation success rate using VO and RO, respectively, compared to 7% for a vision-only method. We additionally report a trade-off between the RL success rate and the motion estimation precision.
We consider the problem of cross-view geo-localization. The primary challenge of this task is to learn the robust feature against large viewpoint changes. Existing benchmarks can help, but are limited in the number of viewpoints. Image pairs, containing two viewpoints, e.g., satellite and ground, are usually provided, which may compromise the feature learning. Besides phone cameras and satellites, in this paper, we argue that drones could serve as the third platform to deal with the geo-localization problem. In contrast to the traditional ground-view images, drone-view images meet fewer obstacles, e.g., trees, and could provide a comprehensive view when flying around the target place. To verify the effectiveness of the drone platform, we introduce a new multi-view multi-source benchmark for drone-based geo-localization, named University-1652. University-1652 contains data from three platforms, i.e., synthetic drones, satellites and ground cameras of 1,652 university buildings around the world. To our knowledge, University-1652 is the first drone-based geo-localization dataset and enables two new tasks, i.e., drone-view target localization and drone navigation. As the name implies, drone-view target localization intends to predict the location of the target place via drone-view images. On the other hand, given a satellite-view query image, drone navigation is to drive the drone to the area of interest in the query. We use this dataset to analyze a variety of off-the-shelf CNN features and propose a strong CNN baseline on this challenging dataset. The experiments show that University-1652 helps the model to learn the viewpoint-invariant features and also has good generalization ability in the real-world scenario.
We describe a learning-based system that estimates the camera position and orientation from a single input image relative to a known environment. The system is flexible w.r.t. the amount of information available at test and at training time, catering to different applications. Input images can be RGB-D or RGB, and a 3D model of the environment can be utilized for training but is not necessary. In the minimal case, our system requires only RGB images and ground truth poses at training time, and it requires only a single RGB image at test time. The framework consists of a deep neural network and fully differentiable pose optimization. The neural network predicts so called scene coordinates, i.e. dense correspondences between the input image and 3D scene space of the environment. The pose optimization implements robust fitting of pose parameters using differentiable RANSAC (DSAC) to facilitate end-to-end training. The system, an extension of DSAC++ and referred to as DSAC*, achieves state-of-the-art accuracy an various public datasets for RGB-based re-localization, and competitive accuracy for RGB-D-based re-localization.
Combining multiple complementary techniques together has long been regarded as a way to improve performance. In visual localization, multi-sensor fusion, multi-process fusion of a single sensing modality, and even combinations of different localization techniques have been shown to result in improved performance. However, merely fusing together different localization techniques does not account for the varying performance characteristics of different localization techniques. In this paper we present a novel, hierarchical localization system that explicitly benefits from three varying characteristics of localization techniques: the distribution of their localization hypotheses, their appearance- and viewpoint-invariant properties, and the resulting differences in where in an environment each system works well and fails. We show how two techniques deployed hierarchically work better than in parallel fusion, how combining two different techniques works better than two levels of a single technique, even when the single technique has superior individual performance, and develop two and three-tier hierarchical structures that progressively improve localization performance. Finally, we develop a stacked hierarchical framework where localization hypotheses from techniques with complementary characteristics are concatenated at each layer, significantly improving retention of the correct hypothesis through to the final localization stage. Using two challenging datasets, we show the proposed system outperforming state-of-the-art techniques.
Visual place recognition algorithms trade off three key characteristics: their storage footprint, their computational requirements, and their resultant performance, often expressed in terms of recall rate. Significant prior work has investigated highly compact place representations, sub-linear computational scaling and sub-linear storage scaling techniques, but have always involved a significant compromise in one or more of these regards, and have only been demonstrated on relatively small datasets. In this paper we present a novel place recognition system which enables for the first time the combination of ultra-compact place representations, near sub-linear storage scaling and extremely lightweight compute requirements. Our approach exploits the inherently sequential nature of much spatial data in the robotics domain and inverts the typical target criteria, through intentionally coarse scalar quantization-based hashing that leads to more collisions but is resolved by sequence-based matching. For the first time, we show how effective place recognition rates can be achieved on a new very large 10 million place dataset, requiring only 8 bytes of storage per place and 37K unitary operations to achieve over 50% recall for matching a sequence of 100 frames, where a conventional state-of-the-art approach both consumes 1300 times more compute and fails catastrophically. We present analysis investigating the effectiveness of our hashing overload approach under varying sizes of quantized vector length, comparison of near miss matches with the actual match selections and characterise the effect of variance re-scaling of data on quantization.
In complex environments, low-cost and robust localization is a challenging problem. For example, in a GPSdenied environment, LiDAR can provide accurate position information, but the cost is high. In general, visual SLAM based localization methods become unreliable when the sunlight changes greatly. Therefore, inexpensive and reliable methods are required. In this paper, we propose a stereo visual localization method based on the prior LiDAR map. Different from the conventional visual localization system, we design a novel visual optimization model by matching planar information between the LiDAR map and visual image. Bundle adjustment is built by using coplanarity constraints. To solve the optimization problem, we use a graph-based optimization algorithm and a local window optimization method. Finally, we estimate a full six degrees of freedom (DOF) pose without scale drift. To validate the efficiency, the proposed method has been tested on the KITTI dataset. The results show that our method is more robust and accurate than the state-of-art ORB-SLAM2.
This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by solving a differentiable optimal transport problem, whose costs are predicted by a graph neural network. We introduce a flexible context aggregation mechanism based on attention, enabling SuperGlue to reason about the underlying 3D scene and feature assignments jointly. Compared to traditional, hand-designed heuristics, our technique learns priors over geometric transformations and regularities of the 3D world through end-to-end training from image pairs. SuperGlue outperforms other learned approaches and achieves state-of-the-art results on the task of pose estimation in challenging real-world indoor and outdoor environments. The proposed method performs matching in real-time on a modern GPU and can be readily integrated into modern SfM or SLAM systems. The code and trained weights are publicly available at https://github.com/magicleap/SuperGluePretrainedNetwork.
While visual localization or SLAM has witnessed great progress in past decades, when deploying it on a mobile robot in practice, few works have explicitly considered the kinematic (or dynamic) constraints of the real robotic system when designing state estimators. To promote the practical deployment of current state-of-the-art visual-inertial localization algorithms, in this work we propose a low-cost kinematics-constrained localization system particularly for a skid-steering mobile robot. In particular, we derive in a principle way the robot's kinematic constraints based on the instantaneous centers of rotation (ICR) model and integrate them in a tightly-coupled manner into the sliding-window bundle adjustment (BA)-based visual-inertial estimator. Because the ICR model parameters are time-varying due to, for example, track-to-terrain interaction and terrain roughness, we estimate these kinematic parameters online along with the navigation state. To this end, we perform in-depth the observability analysis and identify motion conditions under which the state/parameter estimation is viable. The proposed kinematics-constrained visual-inertial localization system has been validated extensively in different terrain scenarios.
Vision based localization is the problem of inferring the pose of the camera given a single image. One solution to this problem is to learn a deep neural network to infer the pose of a query image after learning on a dataset of images with known poses. Another more commonly used approach rely on image retrieval where the query image is compared against the database of images and its pose is inferred with the help of the retrieved images. The latter approach assumes that images taken from the same places consists of the same landmarks and, thus would have similar feature representations. These representation can be learned using full supervision to be robust to different variations in capture conditions like time of the day and weather. In this work, we introduce a framework to enhance the performance of these retrieval based localization methods by taking into account the additional information including GPS coordinates and temporal neighbourhood of the images provided by the acquisition process in addition to the descriptor similarity of pairs of images in the reference or query database which is used traditionally for localization. Our method constructs a graph based on this additional information and use it for robust retrieval by smoothing the feature representation of reference and/or query images. We show that the proposed method is able to significantly improve the localization accuracy on two large scale datasets over the baselines.