arXiv subjects

Javier Civera

Publications and source records attributed to Javier Civera.

85 records · Page 5Linked to original sources

arXiv2020

LoCoQuad: A Low-Cost Arachnoid Quadruped Robot for Research and Education

Developing real robotic systems requires a tight integration of mechanics, electronics and software. Most of the times, existing robotic platforms are either closed or expensive or both, and in-house solutions are costly to develop and maintain. Open-source and low-cost designs are essential to facilitate the access to real robotic platforms and enable further progress in the field. LoCoQuad is an arachnoid quadruped platform that we designed targeting research and education in robotics. To meet these two ends, our platform allows for a high degree of flexibility and configurability. Our legged design has the lowest hardware cost of the state of the art, in the range of 150-165USD. We validated the robot platform by running several experiments showing over all functionalities. All the mechanical and electronic designs and all the software have been made open source and can be found at: https://github.com/TomBlackroad/LoCoQuad

cs.RO↗

arXiv2020

RGB-D Odometry and SLAM

The emergence of modern RGB-D sensors had a significant impact in many application fields, including robotics, augmented reality (AR) and 3D scanning. They are low-cost, low-power and low-size alternatives to traditional range sensors such as LiDAR. Moreover, unlike RGB cameras, RGB-D sensors provide the additional depth information that removes the need of frame-by-frame triangulation for 3D scene reconstruction. These merits have made them very popular in mobile robotics and AR, where it is of great interest to estimate ego-motion and 3D scene structure. Such spatial understanding can enable robots to navigate autonomously without collisions and allow users to insert virtual entities consistent with the image stream. In this chapter, we review common formulations of odometry and Simultaneous Localization and Mapping (known by its acronym SLAM) using RGB-D stream input. The two topics are closely related, as the former aims to track the incremental camera motion with respect to a local map of the scene, and the latter to jointly estimate the camera trajectory and the global map with consistency. In both cases, the standard approaches minimize a cost function using nonlinear optimization techniques. This chapter consists of three main parts: In the first part, we introduce the basic concept of odometry and SLAM and motivate the use of RGB-D sensors. We also give mathematical preliminaries relevant to most odometry and SLAM algorithms. In the second part, we detail the three main components of SLAM systems: camera pose tracking, scene mapping and loop closing. For each component, we describe different approaches proposed in the literature. In the final part, we provide a brief discussion on advanced research topics with the references to the state-of-the-art.

cs.CV↗

arXiv2019

Triangulation: Why Optimize?

For decades, it has been widely accepted that the gold standard for two-view triangulation is to minimize the cost based on reprojection errors. In this work, we challenge this idea. We propose a novel alternative to the classic midpoint method that leads to significantly lower 2D errors and parallax errors. It provides a numerically stable closed-form solution based solely on a pair of backprojected rays. Since our solution is rotationally invariant, it can also be applied for fisheye and omnidirectional cameras. We show that for small parallax angles, our method outperforms the state-of-the-art in terms of combined 2D, 3D and parallax accuracy, while achieving comparable speed.

cs.CV↗

arXiv2019

Closed-Form Optimal Two-View Triangulation Based on Angular Errors

In this paper, we study closed-form optimal solutions to two-view triangulation with known internal calibration and pose. By formulating the triangulation problem as $L_1$ and $L_\infty$ minimization of angular reprojection errors, we derive the exact closed-form solutions that guarantee global optimality under respective cost functions. To the best of our knowledge, we are the first to present such solutions. Since the angular error is rotationally invariant, our solutions can be applied for any type of central cameras, be it perspective, fisheye or omnidirectional. Our methods also require significantly less computation than the existing optimal methods. Experimental results on synthetic and real datasets validate our theoretical derivations.

cs.CV↗

arXiv2019

CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth

Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model. Thus, changing the camera model requires collecting an entirely new training dataset. In this work, we propose a new type of convolution that can take the camera parameters into account, thus allowing neural networks to learn calibration-aware patterns. Experiments confirm that this improves the generalization capabilities of depth prediction networks considerably, and clearly outperforms the state of the art when the train and test images are acquired with different cameras.

cs.CV↗

arXiv2019

Corners for Layout: End-to-End Layout Recovery from 360 Images

The problem of 3D layout recovery in indoor scenes has been a core research topic for over a decade. However, there are still several major challenges that remain unsolved. Among the most relevant ones, a major part of the state-of-the-art methods make implicit or explicit assumptions on the scenes -- e.g. box-shaped or Manhattan layouts. Also, current methods are computationally expensive and not suitable for real-time applications like robot navigation and AR/VR. In this work we present CFL (Corners for Layout), the first end-to-end model for 3D layout recovery on 360 images. Our experimental results show that we outperform the state of the art relaxing assumptions about the scene and at a lower cost. We also show that our model generalizes better to camera position variations than conventional approaches by using EquiConvs, a type of convolution applied directly on the sphere projection and hence invariant to the equirectangular distortions. CFL Webpage: https://cfernandezlab.github.io/CFL/

cs.CV↗

arXiv2019

The Rosario Dataset: Multisensor Data for Localization and Mapping in Agricultural Environments

In this paper we present The Rosario Dataset, a collection of sensor data for autonomous mobile robotics in agricultural scenes. The dataset is motivated by the lack of realistic sensor readings gathered by a mobile robot in such environments. It consists of 6 sequences recorded in soybean fields showing real and challenging cases: highly repetitive scenes, reflection and burned images caused by direct sunlight and rough terrain among others. The dataset was conceived in order to provide a benchmark and contribute to the agricultural SLAM/odometry and sensor fusion research. It contains synchronized readings of several sensors: wheel odometry, IMU, stereo camera and a GPS-RTK system. The dataset is publicly available in http://www.cifasis-conicet.gov.ar/robot/.

cs.RO↗

arXiv2019

Condition-Invariant Multi-View Place Recognition

Visual place recognition is particularly challenging when places suffer changes in its appearance. Such changes are indeed common, e.g., due to weather, night/day or seasons. In this paper we leverage on recent research using deep networks, and explore how they can be improved by exploiting the temporal sequence information. Specifically, we propose 3 different alternatives (Descriptor Grouping, Fusion and Recurrent Descriptors) for deep networks to use several frames of a sequence. We show that our approaches produce more compact and best performing descriptors than single- and multi-view baselines in the literature in two public databases.

cs.CV↗

arXiv2019

Loosely-Coupled Semi-Direct Monocular SLAM

We propose a novel semi-direct approach for monocular simultaneous localization and mapping (SLAM) that combines the complementary strengths of direct and feature-based methods. The proposed pipeline loosely couples direct odometry and feature-based SLAM to perform three levels of parallel optimizations: (1) photometric bundle adjustment (BA) that jointly optimizes the local structure and motion, (2) geometric BA that refines keyframe poses and associated feature map points, and (3) pose graph optimization to achieve global map consistency in the presence of loop closures. This is achieved in real-time by limiting the feature-based operations to marginalized keyframes from the direct odometry module. Exhaustive evaluation on two benchmark datasets demonstrates that our system outperforms the state-of-the-art monocular odometry and SLAM systems in terms of overall accuracy and robustness.

cs.CV↗

arXiv2018

Single-View Place Recognition under Seasonal Changes

Single-view place recognition, that we can define as finding an image that corresponds to the same place as a given query image, is a key capability for autonomous navigation and mapping. Although there has been a considerable amount of research in the topic, the high degree of image variability (with viewpoint, illumination or occlusions for example) makes it a research challenge. One of the particular challenges, that we address in this work, is weather variation. Seasonal changes can produce drastic appearance changes, that classic low-level features do not model properly. Our contributions in this paper are twofold. First we pre-process and propose a partition for the Nordland dataset, frequently used for place recognition research without consensus on the partitions. And second, we evaluate several neural network architectures such as pre-trained, siamese and triplet for this problem. Our best results outperform the state of the art of the field. A video showing our results can be found in https://youtu.be/VrlxsYZoHDM. The partitioned version of the Nordland dataset at http://webdiis.unizar.es/~jmfacil/pr-nordland/.

cs.CV↗

arXiv2018

DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes

The assumption of scene rigidity is typical in SLAM algorithms. Such a strong assumption limits the use of most visual SLAM systems in populated real-world environments, which are the target of several relevant applications like service robotics or autonomous vehicles. In this paper we present DynaSLAM, a visual SLAM system that, building over ORB-SLAM2 [1], adds the capabilities of dynamic object detection and background inpainting. DynaSLAM is robust in dynamic scenarios for monocular, stereo and RGB-D configurations. We are capable of detecting the moving objects either by multi-view geometry, deep learning or both. Having a static map of the scene allows inpainting the frame background that has been occluded by such dynamic objects. We evaluate our system in public monocular, stereo and RGB-D datasets. We study the impact of several accuracy/speed trade-offs to assess the limits of the proposed methodology. DynaSLAM outperforms the accuracy of standard visual SLAM baselines in highly dynamic scenarios. And it also estimates a map of the static parts of the scene, which is a must for long-term applications in real-world environments.

cs.CV↗

arXiv2017

RGBDTAM: A Cost-Effective and Accurate RGB-D Tracking and Mapping System

Simultaneous Localization and Mapping using RGB-D cameras has been a fertile research topic in the latest decade, due to the suitability of such sensors for indoor robotics. In this paper we propose a direct RGB-D SLAM algorithm with state-of-the-art accuracy and robustness at a los cost. Our experiments in the RGB-D TUM dataset [34] effectively show a better accuracy and robustness in CPU real time than direct RGB-D SLAM systems that make use of the GPU. The key ingredients of our approach are mainly two. Firstly, the combination of a semi-dense photometric and dense geometric error for the pose tracking (see Figure 1), which we demonstrate to be the most accurate alternative. And secondly, a model of the multi-view constraints and their errors in the mapping and tracking threads, which adds extra information over other approaches. We release the open-source implementation of our approach 1 . The reader is referred to a video with our results 2 for a more illustrative visualization of its performance.

cs.RO↗

arXiv2017

Single-View and Multi-View Depth Fusion

Dense and accurate 3D mapping from a monocular sequence is a key technology for several applications and still an open research area. This paper leverages recent results on single-view CNN-based depth estimation and fuses them with multi-view depth estimation. Both approaches present complementary strengths. Multi-view depth is highly accurate but only in high-texture areas and high-parallax cases. Single-view depth captures the local structure of mid-level regions, including texture-less areas, but the estimated depth lacks global coherence. The single and multi-view fusion we propose is challenging in several aspects. First, both depths are related by a deformation that depends on the image content. Second, the selection of multi-view points of high accuracy might be difficult for low-parallax configurations. We present contributions for both problems. Our results in the public datasets of NYUv2 and TUM shows that our algorithm outperforms the individual single and multi-view approaches. A video showing the key aspects of mapping in our Single and Multi-view depth proposal is available at https://youtu.be/ipc5HukTb4k

cs.CV↗