Efficient Seamline Network Generation for Large-Scale Orthoimage Mosaicking

Yang, Junxing; Liu, Lulu; Yan, Qingsong; Huang, He; Wang, Jian; Deng, Fei

doi:10.1109/lgrs.2022.3166347

Cited by 1 publication

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, semantic segmentation without auxiliary data implies the need for well-developed semantic segmentation algorithms and great algorithmic efficiency allocated to the process of semantic segmentation. Yang et al [25] proposed to triangulate the overlapping region into a mesh, thus assembling the original pixels into a series of triangle; this can better combine auxiliary methods or other data. On the other hand, many methods are based on auxiliary data.…”

Section: Introductionmentioning

confidence: 99%

An Upscaling–Downscaling Optimal Seamline Detection Algorithm for Very Large Remote Sensing Image Mosaicking

et al. 2022

View full text Add to dashboard Cite

For the mosaicking of multiple remote sensing images, obtaining the optimal stitching line in the overlapping region is a key step in creating a seamless mosaic image. However, for very large remote sensing images, the computation of finding seamlines involves a huge amount of image pixels. To handle this issue, we propose a stepwise strategy to obtain pixel-level optimal stitching lines for large remote sensing images via an upscaling–downscaling image sampling procedure. First, the resolution of the image is reduced and the graph cut algorithm is applied to find an energy-optimal seamline in the reduced image. Then, a stripe along the preliminary seamline is identified from the overlap area to remove the other inefficient nodes. Finally, the graph cut algorithm is applied nested within the identified stripe to seek the pixel-level optimal seamline of the original image. Compared to the existing algorithms, the proposed method produces fewer spectral differences between stitching lines and less-crossed features in the experiments. For a wide range of remote sensing images involving large data, the new method uses less than 10 percent of the time needed by the SLIC+ graph cut method.

show abstract

Section: Introductionmentioning

confidence: 99%