Line meets as-projective-as-possible image stitching with moving DLT

Joo, Kyungdon; Kim, Namil; Oh, Tae-Hyun; Kweon, In So

doi:10.1109/icip.2015.7350985

Cited by 44 publications

(23 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To provide an objective evaluation of panoramic images, a matching error metric has been used to measure the misalignment in the overlap area [10][11][12]29]. The matching error metric determines a corresponding point between two input images, and averages the Euclidean distance of the corresponding points.…”

Section: Quality Assessment Of Stitched Imagesmentioning

confidence: 99%

Quantitative Assessment Method of Image Stitching Performance Based on Estimation of Planar Parallax

Jung

Hong

2021

IEEE Access

View full text Add to dashboard Cite

While parallax-tolerant image stitching is a relatively mature field, the performances of image stitching methods have been assessed subjectively and qualitatively. These methods primarily provide the stitched image itself to demonstrate the performance, rather than quantitative data. Although several objective assessment methods have been proposed for quantifying the quality of stitched images, only the stitched output images have been analyzed, without considering the parallax level in each input image. We propose a method for quantifying the parallax level of the input images and clustering them accordingly. This facilitates a quantitative assessment of the various stitching methods for each parallax level. The parallax levels of the images are grouped based on the magnitude and variation in the planar parallax, as estimated with the proposed metric using matching errors and patch similarity. The existing image stitching methods are compared experimentally in terms of the residual misalignment errors, based on 73 pairs of different levels of parallax images originally classified in this study. Among the existing methods, the elastic local alignment method exhibits the least error. The shape-preserving half-projective method produces a larger misalignment error, but creates a natural panorama with less geometric distortion. We introduce a quantitative assessment method for considering the parallax of input images in image stitching methods. It can aid in specifying their performances, and in finding an appropriate method depending on the parallax level of the input images.INDEX TERMS Image alignment, image stitching, planar parallax, plane + parallax, quantitative assessment.

show abstract

Section: Quality Assessment Of Stitched Imagesmentioning

confidence: 99%

Quantitative Assessment Method of Image Stitching Performance Based on Estimation of Planar Parallax

Jung

Hong

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, the Gaussian weight for estimating local homographies often fracture linear structures, resulting in wavy artifacts. Joo et al [10] extended the APAP approach by adding line features in addition to original SIFT features. However, since local homographies are calculated using the spatial distance, they still yield traditional wavy artifacts.…”

Section: Related Workmentioning

confidence: 99%

“…In this paper, we mainly attempt to overcome the wavy artifacts that commonly occur in locally adaptive warp methods [5,10,12,14,22] with the help of recognizing grid-like structures of urban scenes. Instead of using a simple distance-based weight between arbitrary pixels and feature points, we newly take into account planar perspective guidance in urban scenes, which are obtained from joint probability maps of vanishing points.…”

Section: Related Workmentioning

confidence: 99%

“…As shown in Figure 2(a), a single global homography is insufficient to represent the geometric variety of every surface in the real world. Therefore, the use of locally adaptive homographies has been proposed by previous works [5,10,14,22]. Zaragoza et al [22] proposed using a spatial weight to build locally varying homographies instead of using a single global homography.…”

Section: Combining Global and Local Warpmentioning

confidence: 99%

See 1 more Smart Citation

Urban Image Stitching using Planar Perspective Guidance

Lee

Baek

Kim

2017

Procedings of the British Machine Vision Conference 2017

View full text Add to dashboard Cite

Image stitching methods with spatially-varying homographies have been proposed to overcome partial misalignments caused by global perspective projection; however, local warp operators often fracture the coherence of linear structures, resulting in an inconsistent perspective. In this paper, we propose an image stitching method that warps a source image to a target image by local projective warps using planar perspective guidance. We first detect line structures that converge into three vanishing points, yielding line-cluster probability functions for each vanishing point. Then we estimate local homographies that account for planar perspective guidance from the joint probability of planar guidance, in addition to spatial coherence. This allows us to enhance linear perspective structures while warping multiple urban images with grid-like structures. Our results validate the effectiveness of our method over state-of-the-art projective warp methods in terms of planar perspective.

show abstract

“…Therefore, a lot of methods [8,9,10,11,12,13,14] proposed to impose more constraints by line features. Joo et al [8] proposed the line guided moving DLT (L-mDLT) method, which estimated a spatiallyvarying homography model with line correspondences. Similarly, Li et al [11] proposed a mesh-based model by considering both point and line correspondences.…”

Section: Introductionmentioning

confidence: 99%

Multiple Combined Constraints for Image Stitching

Chen

Xiang

et al. 2018

2018 25th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Several approaches to image stitching use different constraints to estimate the motion model between image pairs. These constraints can be roughly divided into two categories: geometric constraints and photometric constraints. In this paper, geometric and photometric constraints are combined to improve the alignment quality, which is based on the observation that these two kinds of constraints are complementary. On the one hand, geometric constraints (e.g., point and line correspondences) are usually spatially biased and are insufficient in some extreme scenes, while photometric constraints are always evenly and densely distributed. On the other hand, photometric constraints are sensitive to displacements and are not suitable for images with large parallaxes, while geometric constraints are usually imposed by feature matching and are more robust to handle parallaxes. The proposed method therefore combines them together in an efficient mesh-based image warping framework. It achieves better alignment quality than methods only with geometric constraints, and can handle larger parallax than photometric-constraintbased method. Experimental results on various images illustrate that the proposed method outperforms representative state-of-the-art image stitching methods reported in the literature.

show abstract

Line meets as-projective-as-possible image stitching with moving DLT

Cited by 44 publications

References 15 publications

Quantitative Assessment Method of Image Stitching Performance Based on Estimation of Planar Parallax

Quantitative Assessment Method of Image Stitching Performance Based on Estimation of Planar Parallax

Urban Image Stitching using Planar Perspective Guidance

Multiple Combined Constraints for Image Stitching

Contact Info

Product

Resources

About