Visual place recognition is an important component of systems for camera localization and loop closure detection. It concerns the recognition of a previously visited place based on visual cues only. Although it is a widely studied problem for indoor and urban environments, the recent use of robots for automation of agricultural and gardening tasks has created new problems, due to the challenging appearance of garden-like environments. Garden scenes predominantly contain green colors, as well as repetitive patterns and textures. The lack of available data recorded in gardens and natural environments makes the improvement of visual localization algorithms difficult. In this paper we propose an extended version of the TB-Places data set, which is designed for testing algorithms for visual place recognition. It contains images with ground truth camera pose recorded in real gardens in different seasons, with varying light conditions. We constructed and released a ground truth for all possible pairs of images, indicating whether they depict the same place or not. We present the results of a benchmark analysis of methods based on convolutional neural networks for holistic image description and place recognition. We train existing networks (i.e. ResNet, DenseNet and VGG NetVLAD) as backbone of a two-way architecture with a contrastive loss function. The results that we obtained demonstrate that learning garden-tailored representations contribute to an improvement of performance, although the generalization capabilities are limited.
In this paper we present CMRNet, a realtime approach based on a Convolutional Neural Network to localize an RGB image of a scene in a map built from LiDAR data. Our network is not trained in the working area, i.e. CMRNet does not learn the map. Instead it learns to match an image to the map. We validate our approach on the KITTI dataset, processing each frame independently without any tracking procedure. CMRNet achieves 0.27m and 1.07deg median localization accuracy on the sequence 00 of the odometry dataset, starting from a rough pose estimate displaced up to 3.5m and 17deg. To the best of our knowledge this is the first CNN-based approach that learns to match images from a monocular camera to a given, preexisting 3D LiDAR-map.
We propose a novel concept to directly match feature descriptors extracted from RGB images, with feature descriptors extracted from 3D point clouds. We use this concept to localize the position and orientation (pose) of the camera of a query image in dense point clouds. We generate a dataset of matching 2D and 3D descriptors, and use it to train a proposed Descriptor-Matcher algorithm. To localize a query image in a point cloud, we extract 2D keypoints and descriptors from the query image. Then the Descriptor-Matcher is used to find the corresponding pairs 2D and 3D keypoints by matching the 2D descriptors with the pre-extracted 3D descriptors of the point cloud. This information is used in a robust pose estimation algorithm to localize the query image in the 3D point cloud. Experiments demonstrate that directly matching 2D and 3D descriptors is not only a viable idea but also achieves competitive accuracy compared to other state-of-the-art approaches for camera pose localization.
Visual localization is an attractive problem that estimates the camera localization from database images based on the query image. It is a crucial task for various applications, such as autonomous vehicles, assistive navigation and augmented reality. The challenging issues of the task lie in various appearance variations between query and database images, including illumination variations, dynamic object variations and viewpoint variations. In order to tackle those challenges, Panoramic Annular Localizer into which panoramic annular lens and robust deep image descriptors are incorporated is proposed in this paper. The panoramic annular images captured by the single camera are processed and fed into the NetVLAD network to form the active deep descriptor, and sequential matching is utilized to generate the localization result. The experiments carried on the public datasets and in the field illustrate the validation of the proposed system.
We present Neural-Guided RANSAC (NG-RANSAC), an extension to the classic RANSAC algorithm from robust optimization. NG-RANSAC uses prior information to improve model hypothesis search, increasing the chance of finding outlier-free minimal sets. Previous works use heuristic side-information like hand-crafted descriptor distance to guide hypothesis search. In contrast, we learn hypothesis search in a principled fashion that lets us optimize an arbitrary task loss during training, leading to large improvements on classic computer vision tasks. We present two further extensions to NG-RANSAC. Firstly, using the inlier count itself as training signal allows us to train neural guidance in a self-supervised fashion. Secondly, we combine neural guidance with differentiable RANSAC to build neural networks which focus on certain parts of the input data and make the output predictions as good as possible. We evaluate NG-RANSAC on a wide array of computer vision tasks, namely estimation of epipolar geometry, horizon line estimation and camera re-localization. We achieve superior or competitive results compared to state-of-the-art robust estimators, including very recent, learned ones.
In image-based camera localization systems, information about the environment is usually stored in some representation, which can be referred to as a map. Conventionally, most maps are built upon hand-crafted features. Recently, neural networks have attracted attention as a data-driven map representation, and have shown promising results in visual localization. However, these neural network maps are generally hard to interpret by human. A readable map is not only accessible to humans, but also provides a way to be verified when the ground truth pose is unavailable. To tackle this problem, we propose Generative Map, a new framework for learning human-readable neural network maps, by combining a generative model with the Kalman filter, which also allows it to incorporate additional sensor information such as stereo visual odometry. For evaluation, we use real world images from the 7-Scenes and Oxford RobotCar datasets. We demonstrate that our Generative Map can be queried with a pose of interest from the test sequence to predict an image, which closely resembles the true scene. For localization, we show that Generative Map achieves comparable performance with current regression models. Moreover, our framework is trained completely from scratch, unlike regression models which rely on large ImageNet pretrained networks.
In this paper, we propose a novel approach that learns to sequentially attend to different Convolutional Neural Networks (CNN) layers (i.e., ``what'' feature abstraction to attend to) and different spatial locations of the selected feature map (i.e., ``where'') to perform the task at hand. Specifically, at each Recurrent Neural Network (RNN) step, both a CNN layer and localized spatial region within it are selected for further processing. We demonstrate the effectiveness of this approach on two computer vision tasks: (i) image-based six degree of freedom camera pose regression and (ii) indoor scene classification. Empirically, we show that combining the ``what'' and ``where'' aspects of attention improves network performance on both tasks. We evaluate our method on standard benchmarks for camera localization (Cambridge, 7-Scenes, and TUM-LSI) and for scene classification (MIT-67 Indoor Scenes). For camera localization our approach reduces the median error by 18.8\% for position and 8.2\% for orientation (averaged over all scenes), and for scene classification it improves the mean accuracy by 3.4\% over previous methods.
Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While sparse point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of the art object detection methods provide rich information about entities present in the scene from a single image. This work incorporates a real-time deep-learned object detector to the monocular SLAM framework for representing generic objects as quadrics that permit detections to be seamlessly integrated while allowing the real-time performance. Finer reconstruction of an object, learned by a CNN network, is also incorporated and provides a shape prior for the quadric leading further refinement. To capture the dominant structure of the scene, additional planar landmarks are detected by a CNN-based plane detector and modeled as independent landmarks in the map. Extensive experiments support our proposed inclusion of semantic objects and planar structures directly in the bundle-adjustment of SLAM - Semantic SLAM - that enriches the reconstructed map semantically, while significantly improving the camera localization. The performance of our SLAM system is demonstrated in https://youtu.be/UMWXd4sHONw and https://youtu.be/QPQqVrvP0dE .
In this paper, we present a monocular Simultaneous Localization and Mapping (SLAM) algorithm using high-level object and plane landmarks. The built map is denser, more compact and semantic meaningful compared to feature point based SLAM. We first propose a high order graphical model to jointly infer the 3D object and layout planes from single images considering occlusions and semantic constraints. The extracted objects and planes are further optimized with camera poses in a unified SLAM framework. Objects and planes can provide more semantic constraints such as Manhattan plane and object supporting relationships compared to points. Experiments on various public and collected datasets including ICL NUIM and TUM Mono show that our algorithm can improve camera localization accuracy compared to state-of-the-art SLAM especially when there is no loop closure, and also generate dense maps robustly in many structured environments.
Augmented reality aims to enrich our real world by inserting 3D virtual objects. In order to accomplish this goal, it is important that virtual elements are rendered and aligned in the real scene in an accurate and visually acceptable way. The solution of this problem can be related to a pose estimation and 3D camera localization. This paper presents a survey on different approaches of 3D pose estimation in augmented reality and gives classification of key-points-based techniques. The study given in this paper may help both developers and researchers in the field of augmented reality.
Event-based vision sensors mimic the operation of biological retina and they represent a major paradigm shift from traditional cameras. Instead of providing frames of intensity measurements synchronously, at artificially chosen rates, event-based cameras provide information on brightness changes asynchronously, when they occur. Such non-redundant pieces of information are called "events". These sensors overcome some of the limitations of traditional cameras (response time, bandwidth and dynamic range) but require new methods to deal with the data they output. We tackle the problem of event-based camera localization in a known environment, without additional sensing, using a probabilistic generative event model in a Bayesian filtering framework. Our main contribution is the design of the likelihood function used in the filter to process the observed events. Based on the physical characteristics of the sensor and on empirical evidence of the Gaussian-like distribution of spiked events with respect to the brightness change, we propose to use the contrast residual as a measure of how well the estimated pose of the event-based camera and the environment explain the observed events. The filter allows for localization in the general case of six degrees-of-freedom motions.
Squared planar markers are a popular tool for fast, accurate and robust camera localization, but its use is frequently limited to a single marker, or at most, to a small set of them for which their relative pose is known beforehand. Mapping and localization from a large set of planar markers is yet a scarcely treated problem in favour of keypoint-based approaches. However, while keypoint detectors are not robust to rapid motion, large changes in viewpoint, or significant changes in appearance, fiducial markers can be robustly detected under a wider range of conditions. This paper proposes a novel method to simultaneously solve the problems of mapping and localization from a set of squared planar markers. First, a quiver of pairwise relative marker poses is created, from which an initial pose graph is obtained. The pose graph may contain small pairwise pose errors, that when propagated, leads to large errors. Thus, we distribute the rotational and translational error along the basis cycles of the graph so as to obtain a corrected pose graph. Finally, we perform a global pose optimization by minimizing the reprojection errors of the planar markers in all observed frames. The experiments conducted show that our method performs better than Structure from Motion and visual SLAM techniques.
Feature point matching for camera localization suffers from scalability problems. Even when feature descriptors associated with 3D scene points are locally unique, as coverage grows, similar or repeated features become increasingly common. As a result, the standard distance ratio-test used to identify reliable image feature points is overly restrictive and rejects many good candidate matches. We propose a simple coarse-to-fine strategy that uses conservative approximations to robust local ratio-tests that can be computed efficiently using global approximate k-nearest neighbor search. We treat these forward matches as votes in camera pose space and use them to prioritize back-matching within candidate camera pose clusters, exploiting feature co-visibility captured by clustering the 3D model camera pose graph. This approach achieves state-of-the-art camera localization results on a variety of popular benchmarks, outperforming several methods that use more complicated data structures and that make more restrictive assumptions on camera pose. We also carry out diagnostic analyses on a difficult test dataset containing globally repetitive structure that suggest our approach successfully adapts to the challenges of large-scale image localization.
This work addresses the task of camera localization in a known 3D scene given a single input RGB image. State-of-the-art approaches accomplish this in two steps: firstly, regressing for every pixel in the image its 3D scene coordinate and subsequently, using these coordinates to estimate the final 6D camera pose via RANSAC. To solve the first step, Random Forests (RFs) are typically used. On the other hand, Neural Networks (NNs) reign in many dense regression tasks, but are not test-time efficient. We ask the question: which of the two is best for camera localization? To address this, we make two method contributions: (1) a test-time efficient NN architecture which we term a ForestNet that is derived and initialized from a RF, and (2) a new fully-differentiable robust averaging technique for regression ensembles which can be trained end-to-end with a NN. Our experimental findings show that for scene coordinate regression, traditional NN architectures are superior to test-time efficient RFs and ForestNets, however, this does not translate to final 6D camera pose accuracy where RFs and ForestNets perform slightly better. To summarize, our best method, a ForestNet with a robust average, which has an equivalent fast and lightweight RF, improves over the state-of-the-art for camera localization on the 7-Scenes dataset. While this work focuses on scene coordinate regression for camera localization, our innovations may also be applied to other continuous regression tasks.
RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines have been replaced by deep learning pipelines, which can be trained in an end-to-end fashion. However, RANSAC has so far not been used as part of such deep learning pipelines, because its hypothesis selection procedure is non-differentiable. In this work, we present two different ways to overcome this limitation. The most promising approach is inspired by reinforcement learning, namely to replace the deterministic hypothesis selection by a probabilistic selection for which we can derive the expected loss w.r.t. to all learnable parameters. We call this approach DSAC, the differentiable counterpart of RANSAC. We apply DSAC to the problem of camera localization, where deep learning has so far failed to improve on traditional approaches. We demonstrate that by directly minimizing the expected loss of the output camera poses, robustly estimated by RANSAC, we achieve an increase in accuracy. In the future, any deep learning pipeline can use DSAC as a robust optimization component.
Accurate camera localization is an essential part of tracking systems. However, localization results are greatly affected by illumination. Including data collected under various lighting conditions can improve the robustness of the localization algorithm to lighting variation. However, this is very tedious and time consuming. By using synthesized images it is possible to easily accumulate a large variety of views under varying illumination and weather conditions. Despite continuously improving processing power and rendering algorithms, synthesized images do not perfectly match real images of the same scene, i.e. there exists a gap between real and synthesized images that also affects the accuracy of camera localization. To reduce the impact of this gap, we introduce "REal-to-Synthetic Transform (REST)." REST is an autoencoder-like network that converts real features to their synthetic counterpart. The converted features can then be matched against the accumulated database for robust camera localization. In our experiments REST improved feature matching accuracy under variable lighting conditions by approximately 30%. Moreover, our system outperforms state of the art CNN-based camera localization methods trained with synthetic images. We believe our method could be used to initialize local tracking and to simplify data accumulation for lighting robust localization.
Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization. In this work, we address the task of predicting the 6D camera pose from a single RGB image in a given 3D environment. With the advent of neural networks, previous works have either learned the entire camera localization process, or multiple components of a camera localization pipeline. Our key contribution is to demonstrate and explain that learning a single component of this pipeline is sufficient. This component is a fully convolutional neural network for densely regressing so-called scene coordinates, defining the correspondence between the input image and the 3D scene space. The neural network is prepended to a new end-to-end trainable pipeline. Our system is efficient, highly accurate, robust in training, and exhibits outstanding generalization capabilities. It exceeds state-of-the-art consistently on indoor and outdoor datasets. Interestingly, our approach surpasses existing techniques even without utilizing a 3D model of the scene during training, since the network is able to discover 3D scene geometry automatically, solely from single-view constraints.
Maps are a key component in image-based camera localization and visual SLAM systems: they are used to establish geometric constraints between images, correct drift in relative pose estimation, and relocalize cameras after lost tracking. The exact definitions of maps, however, are often application-specific and hand-crafted for different scenarios (e.g. 3D landmarks, lines, planes, bags of visual words). We propose to represent maps as a deep neural net called MapNet, which enables learning a data-driven map representation. Unlike prior work on learning maps, MapNet exploits cheap and ubiquitous sensory inputs like visual odometry and GPS in addition to images and fuses them together for camera localization. Geometric constraints expressed by these inputs, which have traditionally been used in bundle adjustment or pose-graph optimization, are formulated as loss terms in MapNet training and also used during inference. In addition to directly improving localization accuracy, this allows us to update the MapNet (i.e., maps) in a self-supervised manner using additional unlabeled video sequences from the scene. We also propose a novel parameterization for camera rotation which is better suited for deep-learning based camera pose regression. Experimental results on both the indoor 7-Scenes dataset and the outdoor Oxford RobotCar dataset show significant performance improvement over prior work. The MapNet project webpage is https://goo.gl/mRB3Au.
Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of the art object detection methods provide rich information about entities present in the scene from a single image. This work marries the two and proposes a method for representing generic objects as quadrics which allows object detections to be seamlessly integrated in a SLAM framework. For scene coverage, additional dominant planar structures are modeled as infinite planes. Experiments show that the proposed points-planes-quadrics representation can easily incorporate Manhattan and object affordance constraints, greatly improving camera localization and leading to semantically meaningful maps. The performance of our SLAM system is demonstrated in https://youtu.be/dR-rB9keF8M .
Recently, virtual reality, augmented reality, robotics, autonomous driving et al attract much attention of both academic and industrial community, in which image based camera localization is a key task. However, there has not been a complete review on image-based camera localization. It is urgent to map this topic to help people enter the field quickly. In this paper, an overview of image based camera localization is presented. A new and complete kind of classifications for image based camera localization is provided and the related techniques are introduced. Trends for the future development are also discussed. It will be useful to not only researchers but also engineers and other people interested.