An Effective Rigidity Constraint for Improving RANSAC in Homography Estimation

Monnin, David; Bieber, Etienne; Schmitt, Gwenaël; Schneider, Armin

doi:10.1007/978-3-642-17691-3_19

Cited by 13 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Homography estimation and refinement: estimates the homography matrix that will bring points from a target image I to the frame F coordinate system by also filtering out geometrically incorrect matches [46]; 5.…”

mentioning

confidence: 99%

A Mixed Reality Application for the On-Site Assessment of Building Renovation: Development and Testing

et al. 2022

View full text Add to dashboard Cite

This paper contributes to a sustainable construction design management approach to increase the successful renovation rate of existing residential building stock. Indeed, coupling BIM with mixed reality can speed up and improve the quality of the renovation design processes, because it can display virtual models of alternative design scenarios superimposed over the existing physical facility. To this purpose, a sample of technicians was enrolled to test the reliability of this technology. A prototype was developed that enables cooperation among stakeholders and the implementation of an efficient workflow. The volunteers carried out real-life tests in a building demonstrator in Caceres (Spain) and filled in two questionnaires with their feedback. The results showed that an MR-based platform can involve interested stakeholders in the assessment of renovation design projects, that speeds up the decision-making process and increases the quality of those projects. Moreover, technicians can master the technology quickly, provided that it is included in the current renovation workflow and some technology gaps are covered. However, the main limitations of this study are that these findings are valid for building renovation design only, and the tests were performed in a controlled, yet full scale, experimental environment. Finally, this paper deals with a few open technical issues, such as the efficient alignment of holograms, transformation of BIM models into a format suitable for mixed reality applications and sharing feedbacks in an on-line repository to foster collaboration.

show abstract

mentioning

confidence: 99%

A Mixed Reality Application for the On-Site Assessment of Building Renovation: Development and Testing

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Therefore, homography is anticipated to reflect a mapping from one picture plane to the next related to a rigid body transformation. Hence, it is expected that a rigid body keeps its shape during the acquisition of pictures and the transformation occurs only on the projected image surface if a change in camera view [21].…”

Section: Homography Estimationmentioning

confidence: 99%

Pose estimation algorithm for mobile augmented reality based on inertial sensor fusion

Alam

Morshidi

Gunawan

et al. 2022

IJECE

View full text Add to dashboard Cite

<span>Augmented reality (AR) applications have become increasingly ubiquitous as it integrates virtual information such as images, 3D objects, video, and more to the real world, which further enhances the real environment. Many researchers have investigated the augmentation of the 3D object on the digital screen. However, certain loopholes exist in the existing system while estimating the object’s pose, making it inaccurate for mobile augmented reality (MAR) applications. Objects augmented in the current system have much jitter due to frame illumination changes, affecting the accuracy of vision-based pose estimation. This paper proposes to estimate the pose of an object by blending both vision-based techniques and micro electrical mechanical system (MEMS) sensor (gyroscope) to minimize the jitter problem in MAR. The algorithm used for feature detection and description is oriented FAST rotated BRIEF (ORB), whereas to evaluate the homography for pose estimation, <a name="_Hlk100294718"></a>random sample consensus (RANSAC) is used. Furthermore, gyroscope sensor data is incorporated with the vision-based pose estimation. We evaluated the performance of augmenting the 3D object using the techniques, vision-based, and incorporating the sensor data using the video data. After extensive experiments, the validity of the proposed method was superior to the existing vision-based pose estimation algorithms.</span>

show abstract

“…Each RANSAC sample is tested for folding. 24 If the test is passed, then the standard Direct Linear Transformation algorithm is used to estimate the homography from four correspondences. 7 The validity of the model is tested by the symmetric projection error.…”

Section: System Overviewmentioning

confidence: 99%

Parallax beam: a vision-based motion estimation method robust to nearly planar scenes

et al. 2019

Self Cite

View full text Add to dashboard Cite

In computer vision, the epipolar geometry embeds the geometrical relationship between two views of a scene. This geometry is degenerated for planar scenes as they do not provide enough constraints to estimate it without ambiguity. Nearly planar scenes can provide the necessary constraints to resolve the ambiguity. But classic estimators such as the 5-point or 8-point algorithm combined with a random sampling strategy are likely to fail in this case because a large part of the scene is planar and it requires lots of trials to get a non-degenerated sample. However, the planar part can be associated with a homographic model and several links exist between the epipolar geometry and homographies. The epipolar geometry can indeed be recovered from at least two homographies or one homgraphy and two non-coplanar points. The latter fits a wider variety of scenes, as it is unsure to be able to find a second homography in the non-coplanar points. This method is called plane-and-parallax. The equivalence between the parallax and the epipolar lines allows to recover the epipole as their common intersection and so the epipolar geometry. Robust implementations of the method are rarely given and we encounter several limitations in our implementation. Noisy image features and outliers make the lines not to be concurrent in a common point. Also, off-plane features are unequally influenced by the noise level. We noticed that the bigger the parallax, the lesser the noise influence. We therefore propose a new model for the parallax, that takes into account the noise on the features location to cope with the previous limitations. We call our method the parallax beam. The method is validated on the KITTI vision benchmark and n synthetic scenes with strong planar degeneracy. The results show that the parallax beam improves the estimation of the camera motion in scene with planar degeneracy and remains usable when there is not any particular planar structure in the scene.

show abstract

An Effective Rigidity Constraint for Improving RANSAC in Homography Estimation

Cited by 13 publications

References 2 publications

A Mixed Reality Application for the On-Site Assessment of Building Renovation: Development and Testing

A Mixed Reality Application for the On-Site Assessment of Building Renovation: Development and Testing

Pose estimation algorithm for mobile augmented reality based on inertial sensor fusion

Parallax beam: a vision-based motion estimation method robust to nearly planar scenes

Contact Info

Product

Resources

About