Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

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

Wearable Structured Light System in Non-Rigid Configuration

  • Paniagua, Carmen
  • López-Nicolás, Gonzalo
  • Guerrero, J.J.
Traditionally, structured light methods have been studied in rigid configurations. In these configurations the position and orientation between the light emitter and the camera are fixed and known beforehand. In this paper we break with this rigidness and present a new structured light system in non-rigid configuration. This system is composed by a wearable standard perspective camera and a simple laser emitter. Our non-rigid configuration permits free motion of the light emitter with respect to the camera. The point-based pattern emitted by the laser permits us to easily establish correspondences between the image from the camera and a virtual one generated from the light emitter. Using these correspondences, our method computes rotation and translation up to scale of the planes of the scene where the point pattern is projected and reconstructs them. This constitutes a very useful tool for navigation applications in indoor environments, which are mainly composed of planar surfaces.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Stairs detection with odometry-aided traversal from a wearable RGB-D camera

  • Perez-Yus, A.
  • Gutierrez-Gomez, D.
  • Lopez-Nicolas, G.
  • Guerrero, J. J.
Stairs are one of the most common structures present in human-made scenarios, but also one of the most dangerous for those with vision problems. In this work we propose a complete method to detect, locate and parametrise stairs with a wearable RGB-D camera. Our algorithm uses the depth data to determine if the horizontal planes in the scene are valid steps of a staircase judging their dimensions and relative positions. As a result we obtain a scaled model of the staircase with the spatial location and orientation with respect to the subject. The visual odometry is also estimated to continuously recover the current position and orientation of the user while moving. This enhances the system giving the ability to come back to previously detected features and providing location awareness of the user during the climb. Simultaneously, the detection of the staircase during the traversal is used to correct the drift of the visual odometry. A comparison of results of the stair detection with other state-of-the-art algorithms was performed using public dataset. Additional experiments have also been carried out, recording our own natural scenes with a chest-mounted RGB-D camera in indoor scenarios. The algorithm is robust enough to work in real-time and even under partial occlusions of the stair.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Exploiting line metric reconstruction from non-central circular panoramas

  • Bermudez-Cameo, J.
  • Saurer, O.
  • Lopez-Nicolas, G.
  • Guerrero, J.J.
  • Pollefeys, M.
In certain non-central imaging systems, straight lines are projected via a non-planar surface encapsulating the 4 degrees of freedom of the 3D line. Consequently the geometry of the 3D line can be recovered from a minimum of four image points. However, with classical non-central catadioptric systems there is not enough effective baseline for a practical implementation of the method. In this paper we propose a multi-camera system configuration resembling the circular panoramic model which results in a particular non-central projection allowing the stitching of a non-central panorama. From a single panorama we obtain well-conditioned 3D reconstruction of lines, which are specially interesting in texture-less scenarios. No previous information about the direction or arrangement of the lines in the scene is assumed. The proposed method is evaluated on both synthetic and real images.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Extrinsic Calibration of Multiple RGB-D Cameras From Line Observations

  • Perez-Yus, A.
  • Fernandez-Moral, E.
  • Lopez-Nicolas, G.
  • Guerrero, J.J.
  • Rives, P.
This letter presents a novel method to estimate the relative poses between RGB and depth cameras without the requirement of an overlapping field of view, thus providing flexibility to calibrate a variety of sensor configurations. This calibration problem is relevant to robotic applications that can benefit of using several cameras to increase the field of view. In our approach, we extract and match lines of the scene in the RGB and depth cameras, and impose geometric constraints to find the relative poses between the sensors. An analysis of the observability properties of the problem is presented. We have validated our method in both synthetic and real scenarios with different camera configurations, demonstrating that our approach achieves good accuracy and is very simple to apply, in contrast with previous methods based on trajectory matching using visual odometry or simultaneous localization and mapping.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Fitting line projections in non-central catadioptric cameras with revolution symmetry

  • Bermúdez-Cameo, Jesús
  • López-Nicolás, Gonzalo
  • Guerrero, José J.
Line-images in non-central cameras contain much richer information of the original 3D line than line projections in central cameras. The projection surface of a 3D line in most catadioptric non-central cameras is a ruled surface, encapsulating the complete information of the 3D line. The resulting line-image is a curve which contains the 4 degrees of freedom of the 3D line. That means a qualitative advantage with respect to the central case, although extracting this curve is quite difficult. In this paper, we focus on the analytical description of the line-images in non-central catadioptric systems with symmetry of revolution. As a direct application we present a method for automatic line-image extraction for conical and spherical calibrated catadioptric cameras. For designing this method we have analytically solved the metric distance from point to line-image for non-central catadioptric systems. We also propose a distance we call effective baseline measuring the quality of the reconstruction of a 3D line from the minimum number of rays. This measure is used to evaluate the different random attempts of a robust scheme allowing to reduce the number of trials in the process. The proposal is tested and evaluated in simulations and with both synthetic and real images.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Scaled layout recovery with wide field of view RGB-D

  • Perez-Yus, Alejandro
  • López-Nicolas, Gonzalo
  • Guerrero, José J.
In this work, we propose a method that integrates depth and fisheye cameras to obtain a wide 3D scene reconstruction with scale in one single shot. The motivation of such integration is to overcome the narrow field of view in consumer RGB-D cameras and lack of depth and scale information in fisheye cameras. The hybrid camera system we use is easy to build and calibrate, and currently consumer devices with similar configuration are already available in the market. With this system, we have a portion of the scene with shared field of view that provides simultaneously color and depth. In the rest of the color image we estimate the depth by recovering the structural information of the scene. Our method finds and ranks corners in the scene combining the extraction of lines in the color image and the depth information. These corners are used to generate plausible layout hypotheses, which have real-world scale due to the usage of depth. The wide angle camera captures more information from the environment (e.g. the ceiling), which helps to overcome severe occlusions. After an automatic evaluation of the hypotheses, we obtain a scaled 3D model expanding the original depth information with the wide scene reconstruction. We show in our experiments with real images from both home-made and commercial systems that our method achieves high success ratio in different scenarios and that our hybrid camera system outperforms the single color camera set-up while additionally providing scale in one single shot. (C) 2019 Elsevier B.V. All rights reserved.