RepMatch: Robust Feature Matching and Pose for Reconstructing Modern Cities

Lin, Wen Yan; Liu, Siying; Jiang, Nan; Minh, N.; Tan, Ping; Lu, Jiangbo

doi:10.1007/978-3-319-46448-0_34

Cited by 32 publications

(27 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, some urban scenes with repetitive structures still cause alignment issues [36], which may limit the application of our method. Therefore, we use a more robust feature matching method RepMatch [37], and a more robust RANSAC solution USAC [38] for estimating a global homography, to generalize our proposed method in urban scenes. Non-planar scenes may cause outlier removal issues [17], but fortunately, [39] justifies that a simple RANSAC-driven homography still works reasonably well even for such cases.…”

Section: A Results Comparisonsmentioning

confidence: 99%

Quasi-Homography Warps in Image Stitching

Wang

2018

IEEE Trans. Multimedia

100

View full text Add to dashboard Cite

The naturalness of warps is gaining extensive attentions in image stitching. Recent warps such as SPHP and AANAP, use global similarity warps to mitigate projective distortion (which enlarges regions), however, they necessarily bring in perspective distortion (which generates inconsistencies). In this paper, we propose a novel quasi-homography warp, which effectively balances the perspective distortion against the projective distortion in the non-overlapping region to create a more natural-looking panorama. Our approach formulates the warp as the solution of a bivariate system, where perspective distortion and projective distortion are characterized as slope preservation and scale linearization respectively. Because our proposed warp only relies on a global homography, thus it is totally parameter-free. A comprehensive experiment shows that a quasi-homography warp outperforms some state-of-the-art warps in urban scenes, including homography, AutoStitch and SPHP. A user study demonstrates that it wins most users' favor, comparing to homography and SPHP.

show abstract

Section: A Results Comparisonsmentioning

confidence: 99%

Quasi-Homography Warps in Image Stitching

Wang

2018

IEEE Trans. Multimedia

100

View full text Add to dashboard Cite

show abstract

“…Correct matches tend to form clusters with specific motions, and previous works proposed explicit geometrical checks for guaranteeing a consistent transformation of the inlier point set [20,27,61], based on local planarity or local contour invariance. More recently, datadriven strategies for selecting consistent observations have been proposed; for example, in [71] the authors rely on a one-class SVM to select a reliable candidate inlier set, and in [28] a motion model based on bilateral functions is used. However, all these approaches which rely on higher-level perceptual information in order to validate the inlier set coherent motion are not effective in complex urban environments with scarce candidates, abrupt and frequent depth variations of the scene and inconsistent edge detections due to significant viewpoint changes (see, for example, Fig.…”

Section: Related Workmentioning

confidence: 99%

Wide baseline pose estimation from video with a density-based uncertainty model

Pellicanò

Aldea

Hégarat‐Mascle

2019

Machine Vision and Applications

View full text Add to dashboard Cite

Robust wide baseline pose estimation is an essential step in the deployment of smart camera networks. In this work, we highlight some current limitations of conventional strategies for relative pose estimation in difficult urban scenes. Then, we propose a solution which relies on an adaptive search of corresponding interest points in synchronized video streams which allows us to converge robustly toward a high-quality solution. The core idea of our algorithm is to build across the image space a nonstationary mapping of the local pose estimation uncertainty, based on the spatial distribution of interest points. Subsequently, the mapping guides the selection of new observations from the video stream in order to prioritize the coverage of areas of high uncertainty. With an additional step in the initial stage, the proposed algorithm may also be used for refining an existing pose estimation based on the video data; this mode allows for performing a data-driven self-calibration task for stereo rigs for which accuracy is critical, such as onboard medical or vehicular systems. We validate our method on three different datasets which cover typical scenarios in pose estimation. The results show a fast and robust convergence of the solution, with a significant improvement, compared to single image-based alternatives, of the RMSE of ground-truth matches, and of the maximum absolute error.

show abstract

“…Although, the existing feature tracking methods, such as ROML [58], MODS [59] and RepMatch [60], have already obtained excellent performance on the small or middle scale surroundings, their performance including both matching speed and matching precision still needs to improve in large scale scenes with repeated structures. For example, Zhou et al [61] hold that the ability of the existing feature tracking approaches is still essentially limited by the abrupt scale changes in images.…”

Section: A Feature Trackingmentioning

confidence: 99%

Parallel K Nearest Neighbor Matching for 3D Reconstruction

Cao

Xie

et al. 2019

IEEE Access

View full text Add to dashboard Cite

In recent years, a 3D reconstruction based on structure from motion (SFM) has attracted much attention from the communities of computer vision and graphics. It is well known that the speed and quality of SFM systems largely depend on the technique of feature tracking. If a big volume of image data is inputted for SFM, the speed of this SFM system would become very slow. And, this problem becomes severer for largescale scenes, which typically needs to capture several thousands of images to recover the point-cloud model of the scene. However, none of the existing methods fully addresses the problem of fast feature tracking. Brute force matching is capable of producing correspondences for small-scale scenes but often getting stuck in repeated features. Hashing matching can only deal with middle-scale scenes and is not capable of largescale scenes. In this paper, we propose a new feature tacking method working in a parallel manner rather than in a single thread scheme. Our method consists of steps of keypoint detection, descriptor computing, descriptor matching by parallel k-nearest neighbor (Parallel-KNN) search, and outlier rejecting. This method is able to rapidly match a big volume of keypoints and avoids to consume high computation time, then yielding a set of correct correspondences. We demonstrate and evaluate the proposed method on several challenging benchmark datasets, including those with highly repeated features, and compare to the state-ofthe-art methods. The experimental results indicate that our method outperforms the compared methods in both efficiency and effectiveness.

show abstract

RepMatch: Robust Feature Matching and Pose for Reconstructing Modern Cities

Cited by 32 publications

References 40 publications

Quasi-Homography Warps in Image Stitching

Quasi-Homography Warps in Image Stitching

Wide baseline pose estimation from video with a density-based uncertainty model

Parallel K Nearest Neighbor Matching for 3D Reconstruction

Contact Info

Product

Resources

About