Realtime Edge Based Visual Inertial Odometry for MAV Teleoperation in Indoor Environments

Tarrio, Juan; Pedre, Sol

doi:10.1007/s10846-017-0670-y

Cited by 13 publications

(11 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The authors extended it to utilize the IMU [14], although, currently, the extended system is not available open source. e) REBiVO: Realtime Edge Based Inertial Visual Odometry [24] is specifically designed for Micro Aerial Vehicles (MAV). In particular, it tracks the pose of a robot by fusing data from a monocular camera and an IMU.…”

Section: Related Work and Methods Evaluatedmentioning

confidence: 99%

“…e) REBiVO: Realtime Edge Based Inertial Visual Odometry [24] is specifically designed for Micro Aerial Vehicles (MAV). In particular, it tracks the pose of a robot by fusing data from a monocular camera and an IMU.…”

Section: Related Work and Methods Evaluatedmentioning

confidence: 99%

“…The overall performance of the tested packages is discussed next. LSD-SLAM [8], REBiVO [24], Dense Piecewise Planar Tracking and Mapping (DPPTAM) [34], and Monocular SVO were unable to produce any consistent results, as such, they were excluded from Table II. DSO [9] requires full photometric calibration accounting for the exposure time, lens vignetting and non-linear gamma response function for best performance. Even without photometric calibration, it worked well on areas having high intensity gradients and when subjected to large rotation.…”

Section: B Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Experimental Comparison of Open Source Visual-Inertial-Based State Estimation Algorithms in the Underwater Domain

Joshi

Vitzilaios

Rekleitis

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

A plethora of state estimation techniques have appeared in the last decade using visual data, and more recently with added inertial data. Datasets typically used for evaluation include indoor and urban environments, where supporting videos have shown impressive performance. However, such techniques have not been fully evaluated in challenging conditions, such as the marine domain. In this paper, we compare ten recent open-source packages to provide insights on their performance and guidelines on addressing current challenges. Specifically, we selected direct methods and tightly-coupled optimization techniques that fuse camera and Inertial Measurement Unit (IMU) data together. Experiments are conducted by testing all packages on datasets collected over the years with underwater robots in our laboratory. All the datasets are made available online.

show abstract

Section: Related Work and Methods Evaluatedmentioning

confidence: 99%

Section: Related Work and Methods Evaluatedmentioning

confidence: 99%

Section: B Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Experimental Comparison of Open Source Visual-Inertial-Based State Estimation Algorithms in the Underwater Domain

Joshi

Vitzilaios

Rekleitis

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…Este factor se puede calcular si se conoce la profundidad de dicho punto. En la literatura se han propuesto varias aproximaciones para estimar este factor de escala: En (Tarrio, 2017) utilizan una cámara como sensor principal y una unidad de medición inercial para determinar la escala.…”

Section: Sinunclassified

Estimación de la ubicación relativa de una cámara utilizando un sistema de visión monocular

Martínez-Díaz¹

2019

JOIE

View full text Add to dashboard Cite

Objective: Estimate the location of a camera with respect to objects in the real world, using monocular vision. Methodology: In this paper we introduce a method to calculate the relative location of the camera with respect to a group of points located in the three-dimensional space. The method requires only three fixed reference points of which the real distance between each pair of points must be known. With this information it is possible to estimate the relative location of the camera when it is moved, using successive images that contain the same points. Contribution: In recent years, processing power of computers has grown considerably and, with this, the interest of the scientific community in visual odometry has also increased. For this purpose, in many cases, it is convenient to use a single camera (monocular system). Unfortunately, a monocular system allows to estimate the location of the camera with respect to some object in the real world only up to a scale factor. The main contribution of this work is the estimation of the location of the camera in real world coordinates with respect to a reference object.

show abstract

“…This scale factor must be obtained by using any bootstrap method. In the literature, several approaches have been proposed to estimate this scale factor: in reference [18], the authors use a camera as the main sensor and an inertial measurement unit (IMU) to determine the scale. In [19], the depth is estimated by using a convolutional neural network, this estimation is refined, and the error is reduced by training the network with consecutive images.…”

Section: Introductionmentioning

confidence: 99%

3D Distance Measurement from a Camera to a Mobile Vehicle, Using Monocular Vision

Martínez-Díaz

2021

Journal of Sensors

View full text Add to dashboard Cite

Estimation of distance from objects in real-world scenes is an important topic in several applications such as navigation of autonomous robots, simultaneous localization and mapping (SLAM), and augmented reality (AR). Even though there is a technology for this purpose, in some cases, this technology has some disadvantages. For example, GPS systems are susceptible to interference, especially in places surrounded by buildings, under bridges or indoors; alternatively, RGBD sensors can be used, but they are expensive, and their operational range is limited. Monocular vision is a low-cost suitable alternative that can be used indoor and outdoor. However, monocular odometry is challenging because the object location can be known up a scale factor. Moreover, when objects are moving, it is necessary to estimate the location from consecutive images accumulating error. This paper introduces a new method to compute the distance from a single image of the desired object, with known dimensions, captured with a monocular calibrated vision system. This method is less restrictive than other proposals in the state-of-the-art literature. For the detection of interest points, a Region-based Convolutional Neural Network combined with a corner detector were used. The proposed method was tested on a standard dataset and images acquired by a low-cost and low-resolution webcam, under noncontrolled conditions. The system was tested and compared with a calibrated stereo vision system. Results showed the similar performance of both systems, but the monocular system accomplished the task in less time.

show abstract

Realtime Edge Based Visual Inertial Odometry for MAV Teleoperation in Indoor Environments

Cited by 13 publications

References 34 publications

Experimental Comparison of Open Source Visual-Inertial-Based State Estimation Algorithms in the Underwater Domain

Experimental Comparison of Open Source Visual-Inertial-Based State Estimation Algorithms in the Underwater Domain

Estimación de la ubicación relativa de una cámara utilizando un sistema de visión monocular

3D Distance Measurement from a Camera to a Mobile Vehicle, Using Monocular Vision

Contact Info

Product

Resources

About