Real Time Localization and 3D Reconstruction

Mouragnon, E.; Lhuillier, Maxime; Dhome, Michel; Dekeyser, Fabien; Sayd, Patrick

doi:10.1109/cvpr.2006.236

Cited by 329 publications

(266 citation statements)

References 12 publications

Supporting

Mentioning

261

Contrasting

Unclassified

Order By: Relevance

“…Recently, approaches that may be qualified as hybrids between bundle adjustment and simultaneous localization and mapping (SLAM) [107] were proposed, by Mouragnon et al [356,358] and Engels et al [129]. SLAM, mostly used in robotics, solves in principle exactly the same problem as structure-from-motion: estimating camera motion and scene structure.…”

Section: Bundle Adjustmentmentioning

confidence: 99%

Camera Models and Fundamental Concepts Used in Geometric Computer Vision

Sturm

2010

FNT in Computer Graphics and Vision

157

122

View full text Add to dashboard Cite

A printed and bound version is available at a special discount price of US35 from Now Publishers. This can be obtained by entering the promotional code CGV006023 on https://www.nowpublishers.com/bookorder.aspx?doi=0600000023&product=CGVInternational audienceThis survey is mainly motivated by the increased availability and use of panoramic image acquisition devices, in computer vision and various of its applications. Different technologies and different computational models thereof exist and algorithms and theoretical studies for geometric computer vision ("structure-from-motion") are often re-developed without highlighting common underlying principles. One of the goals of this survey is to give an overview of image acquisition methods used in computer vision and especially, of the vast number of camera models that have been proposed and investigated over the years, where we try to point out similarities between different models. Results on epipolar and multi-view geometry for different camera models are reviewed as well as various calibration and self-calibration approaches, with an emphasis on non-perspective cameras. We finally describe what we consider are fundamental building blocks for geometric computer vision or structure-from-motion: epipolar geometry, pose and motion estimation, 3D scene modeling, and bundle adjustment. The main goal here is to highlight the main principles of these, which are independent of specific camera models

show abstract

Section: Bundle Adjustmentmentioning

confidence: 99%

Camera Models and Fundamental Concepts Used in Geometric Computer Vision

Sturm

2010

FNT in Computer Graphics and Vision

157

122

View full text Add to dashboard Cite

show abstract

“…The solution is carried out taking advantage of the sparse nature of the Jacobian matrix of the error measure vector as described in [8]. Although these systems increase the final accuracy in the position estimation, their results are similar to those not using bundle adjustment (About 5% accuracy for [7] and errors in the order of meters for [6]). Reaching similar accuracy in monocular systems involves the use of very high resolution images as in [9] (2-3% with 5 768 × 1024 images) or a previously known 3D model of the environment to recover the real scale as in [10].…”

Section: Introductionmentioning

confidence: 61%

“…The system was tested in outdoor scenarios on different runs under 150 m. with a precision in the estimation of the travelled distance of 2-5%. In order to maintain consistency in long sequences of images, [6] and [7] introduce a local bundle adjustment. This local bundle adjustment tries to estimate the extrinsic parameter for the last cameras and the 3D points positions taking into account the 2D re-projections in the (with ≥ ) last frames.…”

Section: Introductionmentioning

confidence: 99%

Visual odometry and map fusion for GPS navigation assistance

Parra

Sotelo

Llorca

et al. 2011

2011 IEEE International Symposium on Industrial Electronics

View full text Add to dashboard Cite

Abstract-This paper describes a new approach for improving the estimation of the global position of a vehicle in complex urban environments by means of visual odometry and map fusion. The visual odometry system is based on the compensation of the heterodasticity in the 3D input data using a weighted nonlinear least squares based system. RANdom SAmple Consensus (RANSAC) based on Mahalanobis distance is used for outlier removal. The motion trajectory information is used to keep track of the vehicle position in a digital map during GPS outages. The final goal is the autonomous vehicle outdoor navigation in large-scale environments and the improvement of current vehicle navigation systems based only on standard GPS. This research is oriented to the development of traffic collective systems aiming vehicle-infrastructure cooperation to improve dynamic traffic management. We provide examples of estimated vehicle trajectories and map fusion using the proposed method and discuss the key issues for further improvement.

show abstract

“…There are many methods [8]- [10] for simultaneous localization and map building (SLAM). SLAM methods simultaneously estimate sensor egomotion and build an environmental map.…”

Section: Egomotion Estimationmentioning

confidence: 99%

Real-Time Estimation of Fast Egomotion with Feature Classification Using Compound Omnidirectional Vision Sensor

Ngo

Kojima

Nagahara

et al. 2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYFor fast egomotion of a camera, computing feature correspondence and motion parameters by global search becomes highly timeconsuming. Therefore, the complexity of the estimation needs to be reduced for real-time applications. In this paper, we propose a compound omnidirectional vision sensor and an algorithm for estimating its fast egomotion. The proposed sensor has both multi-baselines and a large field of view (FOV). Our method uses the multi-baseline stereo vision capability to classify feature points as near or far features. After the classification, we can estimate the camera rotation and translation separately by using random sample consensus (RANSAC) to reduce the computational complexity. The large FOV also improves the robustness since the translation and rotation are clearly distinguished. To date, there has been no work on combining multi-baseline stereo with large FOV characteristics for estimation, even though these characteristics are individually are important in improving egomotion estimation. Experiments showed that the proposed method is robust and produces reasonable accuracy in real time for fast motion of the sensor.

show abstract

Real Time Localization and 3D Reconstruction

Cited by 329 publications

References 12 publications

Camera Models and Fundamental Concepts Used in Geometric Computer Vision

Camera Models and Fundamental Concepts Used in Geometric Computer Vision

Visual odometry and map fusion for GPS navigation assistance

Real-Time Estimation of Fast Egomotion with Feature Classification Using Compound Omnidirectional Vision Sensor

Contact Info

Product

Resources

About