Prior Knowledge About Camera Motion for Outlier Removal in Feature Matching

  title={Prior Knowledge About Camera Motion for Outlier Removal in Feature Matching},
  author={Elisavet (Ellie) Konstantina Stathopoulou and Ronny H{\"a}nsch and O. Hellwich},
The search of corresponding points in between images of the same scene is a well known problem in many computer vision applications. In particular most structure from motion techniques depend heavily on the correct estimation of corresponding image points. Most commonly used approaches make neither assumptions about the 3D scene nor about the relative positions of the cameras and model both as completely unknown. This general model results in a brute force comparison of all keypoints in one… 


Path-based constraints for accurate scene reconstruction from aerial video
This paper discusses the constraints imposed by the path of a moving camera in multi-view sequential scene reconstruction scenarios such as in aerial video, which allow for an efficient detection and
A new evaluation criterion for point correspondences in stereo images
A new criterion to evaluate point correspondences within a stereo setup is presented, to determine the most probable epipolar geometry that explains the point correspondence in the two views and it is shown that using Lagrange multipliers, this constrained minimization problem can be reduced to solving a set of three linear equations.
Accurate, Dense, and Robust Multiview Stereopsis
A novel algorithm for multiview stereopsis that outputs a dense set of small rectangular patches covering the surfaces visible in the images, which outperforms all others submitted so far for four out of the six data sets.
On benchmarking camera calibration and multi-view stereo for high resolution imagery
The discussion on whether image based 3D modelling techniques can possibly be used to replace LIDAR systems for outdoor 3D data acquisition and two main issues have to be addressed: camera calibration and dense multi-view stereo.
Motion Estimation from Image and Inertial Measurements
This paper presents two algorithms for estimating sensor motion from image and inertial measurements, and presents a batch method, which produces estimates of the sensor motion, scene structure, and other unknowns using measurements from the entire observation sequence simultaneously.
Scalable Visual Navigation for Micro Aerial Vehicles using Geometric Prior Knowledge
A scalable framework for visual navigation of micro aerial vehicles based on a monocular camera as the main exteroceptive sensor of the MAV, and a distributed SLAM system capable of generating dense volumetric reconstructions in real-time, thus enabling fast collision avoidance and user interaction.
In the wild image retrieval and clustering for 3D cultural heritage landmarks reconstruction
Evaluation on a dataset of about 31,000 cultural heritage images being retrieved from internet collections with many outliers indicate the robustness and cost effectiveness of the proposed method towards a reliable and just-in-time 3D reconstruction than existing state-of-the-art techniques.
On the Probabilistic Epipolar Geometry
A point–probability-density relation can be understood as a probabilistic form of the epipolar constraint; it also approaches the true point–line relation as the number of training correspondences tends to infinity.
Fast k nearest neighbor search using GPU
A CUDA implementation of the ldquobrute forcerdquo kNN search and it is shown a speed increase on synthetic and real data by up to one or two orders of magnitude depending on the data, with a quasi-linear behavior with respect to the data size in a given, practical range.
Geometrically Constrained Structure from Motion: Points on Planes
The experimental results indicate that the quality of the reconstruction can be significantly improved by the judicious use of geometric constraints, and the approaches studied include hallucinating extra point matches in planar regions, computing fundamental matrices directly from homographies, and applying coplanarity and other geometric constraints as part of the final bundle adjustment stage.