Pasar al contenido principal

SLAM VISUAL MEJORADO MEDIANTE APRENDIZAJE PROFUNDO

PGC2018-096367-B-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de Generación de Conocimiento y Fortalecimiento Científico y Tecnológico del Sistema de I+D+i
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D (Excelencia / Generación de Conocimiento)
Año convocatoria 2018
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE ZARAGOZA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 9
Encontrada(s) 1 página(s)

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Incremental Learning of Object Models From Natural Human-Robot Interactions

  • Azagra, Pablo
  • Civera, Javier
  • Murillo, Ana C.
In order to perform complex tasks in realistic human environments, robots need to be able to learn new concepts in the wild, incrementally, and through their interactions with humans. This article presents an end-to-end pipeline to learn object models incrementally during the human-robot interaction (HRI). The pipeline we propose consists of three parts: 1) recognizing the interaction type; 2) detecting the object that the interaction is targeting; and 3) learning incrementally the models from data recorded by the robot sensors. Our main contributions lie in the target object detection, guided by the recognized interaction, and in the incremental object learning. The novelty of our approach is the focus on natural, heterogeneous, and multimodal HRIs to incrementally learn new object models. Throughout the article, we highlight the main challenges associated with this problem, such as high degree of occlusion and clutter, domain change, low-resolution data, and interaction ambiguity. This article shows the benefits of using multiview approaches and combining visual and language features, and our experimental results outperform standard baselines.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

DefSLAM: Tracking and Mapping of Deforming Scenes from Monocular Sequences

  • Lamarca, J.
  • Parashar, S.
  • Bartoli, A.
  • Martínez Montiel, J.M.
Monocular simultaneous localization and mapping (SLAM) algorithms perform robustly when observing rigid scenes; however, they fail when the observed scene deforms, for example, in medical endoscopy applications. In this article, we present DefSLAM, the first monocular SLAM capable of operating in deforming scenes in real time. Our approach intertwines Shape-from-Template (SfT) and Non-Rigid Structure-from-Motion (NRSfM) techniques to deal with the exploratory sequences typical of SLAM. A deformation tracking thread recovers the pose of the camera and the deformation of the observed map, at frame rate, by means of SfT processing a template that models the scene shape-at-rest. A deformation mapping thread runs in parallel with the tracking to update the template, at keyframe rate, by means of an isometric NRSfM processing a batch of full perspective keyframes. In our experiments, DefSLAM processes close-up sequences of deforming scenes, both in a laboratory-controlled experiment and in medical endoscopy sequences, producing accurate 3-D models of the scene with respect to the moving camera.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Mapillary street-level sequences: A dataset for lifelong place recognition

  • Warburg, F.
  • Hauberg, S.
  • López-Antequera, M.
  • Gargallo, P.
  • Kuang, Y.
  • Civera, J.
Lifelong place recognition is an essential and challenging task in computer vision with vast applications in robust localization and efficient large-scale 3D reconstruction. Progress is currently hindered by a lack of large, diverse, publicly available datasets. We contribute with Mapillary Street-Level Sequences (SLS), a large dataset for urban and suburban place recognition from image sequences. It contains more than 1.6 million images curated from the Mapillary collaborative mapping platform. The dataset is orders of magnitude larger than current data sources, and is designed to reflect the diversities of true lifelong learning. It features images from 30 major cities across six continents, hundreds of distinct cameras, and substantially different viewpoints and capture times, spanning all seasons over a nine year period. All images are geo-located with GPS and compass, and feature high-level attributes such as road type. We propose a set of benchmark tasks designed to push state-of-the-art performance and provide baseline studies. We show that current state-of-the-art methods still have a long way to go, and that the lack of diversity in existing datasets have prevented generalization to new environments. The dataset and benchmarks are available for academic research.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Direct Sparse Mapping

  • Zubizarreta, J.
  • Aguinaga, I.
  • Martinez Montiel, J.M.
Photometric bundle adjustment (PBA) accurately estimates geometry from video. However, current PBA systems have a temporary map that cannot manage scene reobservations. We present, direct sparse mapping, a full monocular visual simultaneous localization and mapping (SLAM) based on PBA. Its persistent map handles reobservations, yielding the most accurate results up to date on EuRoC for a direct method.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Fine grained pointing recognition for natural drone guidance

  • Barbed, O.L.
  • Azagra, P.
  • Teixeira, L.
  • Chli, M.
  • Civera, J.
  • Murillo, A.C.
Human action recognition systems are typically focused on identifying different actions, rather than fine grained variations of the same action. This work explores strategies to identify different pointing directions in order to build a natural interaction system to guide autonomous systems such as drones. Commanding a drone with hand-held panels or tablets is common practice but intuitive user-drone interfaces might have significant benefits. The system proposed in this work just requires the user to provide occasional high-level navigation commands by pointing the drone towards the desired motion direction. Due to the lack of data on these settings, we present a new benchmarking video dataset to validate our framework and facilitate future research on the area. Our results show good accuracy for pointing direction recognition, while running at interactive rates and exhibiting robustness to variability in user appearance, viewpoint, camera distance and scenery.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Contribución de congreso (ConferenceOutput)

Photometric single-view dense 3D reconstruction in endoscopy

  • Martínez Batlle, V.
  • Martínez Montiel, J. M.
  • Tardos, J. D.
Visual SLAM inside the human body will open the way to computer-assisted navigation in endoscopy. However, due to space limitations, medical endoscopes only provide monocular images, leading to systems lacking true scale. In this paper, we exploit the controlled lighting in colonoscopy to achieve the first in-vivo 3D reconstruction of the human colon using photometric stereo on a calibrated monocular endoscope. Our method works in a real medical environment, providing both a suitable in-place calibration procedure and a depth estimation technique adapted to the colon's tubular geometry. We validate our method on simulated colonoscopies, obtaining a mean error of 7% on depth estimation, which is below 3 mm on average. Our qualitative results on the EndoMapper dataset show that the method is able to correctly estimate the colon shape in real human colonoscopies, paving the ground for truescale monocular SLAM in endoscopy.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

GNSS-stereo-inertial SLAM for arable farming

  • Cremona, Javier
  • Civera, Javier
  • Kofman, Ernesto
  • Pire, Taihú
The accelerating pace in the automation of agricultural tasks demands highly accurate and robust localization systems for field robots. Simultaneous Localization and Mapping (SLAM) methods inevitably accumulate drift on exploratory trajectories and primarily rely on place revisiting and loop closing to keep a bounded global localization error. Loop closure techniques are significantly challenging in agricultural fields, as the local visual appearance of different views is very similar and might change easily due to weather effects. A suitable alternative in practice is to employ global sensor positioning systems jointly with the rest of the robot sensors. In this paper we propose and implement the fusion of global navigation satellite system (GNSS), stereo views, and inertial measurements for localization purposes. Specifically, we incorporate, in a tightly coupled manner, GNSS measurements into the stereo-inertial ORB-SLAM3 pipeline. We thoroughly evaluate our implementation in the sequences of the Rosario data set, recorded by an autonomous robot in soybean fields, and our own in-house data. Our data includes measurements from a conventional GNSS, rarely included in evaluations of state-of-the-art approaches. We characterize the performance of GNSS-stereo-inertial SLAM in this application case, reporting pose error reductions between 10% and 30% compared to visual–inertial and loosely coupled GNSS-stereo-inertial baselines. In addition to such analysis, we also release the code of our implementation as open source.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Contribución de congreso (ConferenceOutput)

LightDepth: Single-view depth self-supervision from illumination decline

  • Rodríguez-Puigvert, Javier
  • Batlle, Víctor M.
  • Martínez Montiel, J.M.
  • Martinez-Cantin, Ruben
  • Fua, Pascal
  • Tardós, Juan D.
  • Civera, Javier
Single-view depth estimation can be remarkably effective if there is enough ground-truth depth data for supervised training. However, there are scenarios, especially in medicine in the case of endoscopies, where such data cannot be obtained. In such cases, multi-view self-supervision and synthetic-to-real transfer serve as alternative approaches, however, with a considerable performance reduction in comparison to supervised case. Instead, we propose a single-view self-supervised method that achieves a performance similar to the supervised case. In some medical devices, such as endoscopes, the camera and light sources are co-located at a small distance from the target surfaces. Thus, we can exploit that, for any given albedo and surface orientation, pixel brightness is inversely proportional to the square of the distance to the surface, providing a strong single-view self-supervisory signal. In our experiments, our self-supervised models deliver accuracies comparable to those of fully supervised ones, while being applicable without depth ground-truth data.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

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

  • Fernandez-Labrador, Clara
  • Facil, José M.
  • Perez-Yus, Alejandro
  • Demonceaux, Cédric
  • Civera, Javier
  • Guerrero, José J.
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 that predicts layout corners for 3D layout recovery on mathbf {{360}circ } images. Our experimental results show that we outperform the state of the art, making less assumptions on the scene than other works, and with lower cost. We also show that our model generalizes better to camera position variations than conventional approaches by using EquiConvs, a convolution applied directly on the spherical projection and hence invariant to the equirectangular distortions.