Image Alignment for Panorama Stitching in Sparsely Structured Environments

Meneghetti, Giulia; Danelljan, Martin; Felsberg, Michael; Nordberg, Klas

doi:10.1007/978-3-319-19665-7_36

Cited by 38 publications

(24 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use the PASSTA dataset to test QUASAR in challenging panorama stitching applications [41]. To merge two images together, we first use SURF [5] feature descriptors to match and establish putative feature correspondences.…”

Section: Image Stitchingmentioning

confidence: 99%

“…Since we added more constraints in (20) compared to the naive relaxation (19), the optimal cost of (20) always achieves a higher objective than (19), and since they are both relaxations, their objectives provide a lower bound to the original non-convex problem (18 Table A2. Image stitching statistics (mean and standard deviation (SD)) of QUASAR on the Lunch Room dataset [41].…”

Section: F Proof Of Propositionmentioning

confidence: 99%

See 1 more Smart Citation

A Quaternion-Based Certifiably Optimal Solution to the Wahba Problem With Outliers

Yang

Carlone

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

The Wahba problem, also known as rotation search, seeks to find the best rotation to align two sets of vector observations given putative correspondences, and is a fundamental routine in many computer vision and robotics applications. This work proposes the first polynomial-time certifiably optimal approach for solving the Wahba problem when a large number of vector observations are outliers. Our first contribution is to formulate the Wahba problem using a Truncated Least Squares (TLS) cost that is insensitive to a large fraction of spurious correspondences. The second contribution is to rewrite the problem using unit quaternions and show that the TLS cost can be framed as a Quadratically-Constrained Quadratic Program (QCQP). Since the resulting optimization is still highly non-convex and hard to solve globally, our third contribution is to develop a convex Semidefinite Programming (SDP) relaxation. We show that while a naive relaxation performs poorly in general, our relaxation is tight even in the presence of large noise and outliers. We validate the proposed algorithm, named QUASAR (QUAternion-based Semidefinite relAxation for Robust alignment), in both synthetic and real datasets showing that the algorithm outperforms RANSAC, robust local optimization techniques, global outlier-removal procedures, and Branch-and-Bound methods. QUASAR is able to compute certifiably optimal solutions (i.e. the relaxation is exact) even in the case when 95% of the correspondences are outliers. arXiv:1905.12536v4 [math.OC] 22 Sep 2019 Wahba problem with outliersIn computer vision applications, the vector-to-vector correspondences are typically established through descriptor matching, which may lead to spurious correspondences and outliers [44,15]. This observation triggered research into outlier-robust variants of the Wahba problem.Local Methods. The most widely used method for handling outliers is RANSAC, which is efficient and accurate in the low-noise and low-outlier regime [24,40]. However,

show abstract

Section: Image Stitchingmentioning

confidence: 99%

Section: F Proof Of Propositionmentioning

confidence: 99%

A Quaternion-Based Certifiably Optimal Solution to the Wahba Problem With Outliers

Yang

Carlone

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…The influence of the error function ρ on the model estimation is only determined by its variations, i.e., its derivative ρ through the weighting by ρ ( DI(x) 2 ) in (13) and (14). In theory, any increasing and derivable function can be chosen as the error function but in the following we only consider the L2 error function, for which the computations are simplified, and the robust error functions, for which the model estimation is robust to outliers.…”

Section: Error Functionmentioning

confidence: 99%

“…The error function originally considered in [2] was the identity function ρ(s) = s, which results in an L2 error in (2). It has the advantage of having a constant derivative ρ = 1 so that the Hessian H, defined in (13), and its inverse can be precomputed before the incremental refinement. Another theoretical advantage is that in Section 2.1 only one first order Taylor expansion is necessary and E 2 = E 3 .…”

Section: Error Functionmentioning

confidence: 99%

Improvements of the Inverse Compositional Algorithm for Parametric Motion Estimation

Briand¹,

Facciolo²,

Sánchez³

2018

Image Processing on Line

View full text Add to dashboard Cite

In this work, we propose several improvements of the inverse compositional algorithm for parametric registration. We propose an improved handling of boundary pixels, a different color handling and gradient estimation, and the possibility to skip scales in the multiscale coarseto-fine scheme. In an experimental part, we analyze the influence of the modifications. The estimation accuracy is at least improved by a factor 1.3 while the computation time is at least reduced by a factor 2.2 for color images. Source Code The C++ source code, the code documentation, and the online demo are accessible at the web page of this article 1. Compilation and usage instruction are included in the README.txt file of the archive.

show abstract

“…Color names have successfully been applied in object recognition [22], action recognition [21] and image stitching [26] to capture color information. On the other hand, channel coded intensity features have been used in visual tracking [31,8] to capture the image intensity statistics.…”

Section: Channel Coded Color Representationsmentioning

confidence: 99%

Coloring Channel Representations for Visual Tracking

et al. 2015

Self Cite

View full text Add to dashboard Cite

Abstract. Visual object tracking is a classical, but still open research problem in computer vision, with many real world applications. The problem is challenging due to several factors, such as illumination variation, occlusions, camera motion and appearance changes. Such problems can be alleviated by constructing robust, discriminative and computationally efficient visual features. Recently, biologically-inspired channel representations [9] have shown to provide promising results in many applications ranging from autonomous driving to visual tracking. This paper investigates the problem of coloring channel representations for visual tracking. We evaluate two strategies, channel concatenation and channel product, to construct channel coded color representations. The proposed channel coded color representations are generic and can be used beyond tracking. Experiments are performed on 41 challenging benchmark videos. Our experiments clearly suggest that a careful selection of color feature together with an optimal fusion strategy, significantly outperforms the standard luminance based channel representation. Finally, we show promising results compared to state-of-the-art tracking methods in the literature.

show abstract

Image Alignment for Panorama Stitching in Sparsely Structured Environments

Cited by 38 publications

References 22 publications

A Quaternion-Based Certifiably Optimal Solution to the Wahba Problem With Outliers

A Quaternion-Based Certifiably Optimal Solution to the Wahba Problem With Outliers

Improvements of the Inverse Compositional Algorithm for Parametric Motion Estimation

Coloring Channel Representations for Visual Tracking

Contact Info

Product

Resources

About