Scholarlink

<p>Fisheye cameras have been widely used in the field of panoramic imaging. However, most image stitching research has focused on pinhole camera images, with only a few studies addressing fisheye images. Moreover, in these studies, the distortion of fisheye images is frequently corrected to transform them into planar images prior to carrying out the subsequent stitching process. This paper proposes a novel inlier filtering algorithm, RANSAC Based on Rotation (RANSAC-R). Based on the principle of light incidence, we convert traditional matched points into matched light rays and then screen these matched light rays, which directly performs precise inlier matching on equidistant fisheye images. In the experimental evaluation, we demonstrate that the proposed RANSAC-R algorithm significantly improves matching performance. Specifically, the recall rate is increased from approximately <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(50\%\)</EquationSource> </InlineEquation> to <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(100\%\)</EquationSource> </InlineEquation>, while maintaining <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(100\%\)</EquationSource> </InlineEquation> matching precision. Furthermore, in experiments conducted with 140-degree and 180-degree fisheye cameras, the inlier rate is improved by approximately 2.5 times and 4 times, respectively. When capturing images, it poses a significant challenge to ensure the precise alignment of the camera’s optical centers, resulting in parallax that introduces artifacts into the stitched images. To eliminate artifacts, this paper presents a new stitching method, the multi-rotation motion projection method (MRM), which is capable of producing high-quality stitching results for multiple fisheye or pinhole images without introducing noticeable distortion. The experimental results indicate that both methods substantially enhance stitching accuracy, effectively reduce geometric distortion, and yield panoramas of practical quality.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Fisheye image stitching by RANSAC-R and MRM

  • 期刊论文

  • 发表日期：

    2026年8月3日

查看全文
  • Yuan Jia,
  • Cailin Wu,
  • Rui Song,
  • Bin Song

摘要

Fisheye cameras have been widely used in the field of panoramic imaging. However, most image stitching research has focused on pinhole camera images, with only a few studies addressing fisheye images. Moreover, in these studies, the distortion of fisheye images is frequently corrected to transform them into planar images prior to carrying out the subsequent stitching process. This paper proposes a novel inlier filtering algorithm, RANSAC Based on Rotation (RANSAC-R). Based on the principle of light incidence, we convert traditional matched points into matched light rays and then screen these matched light rays, which directly performs precise inlier matching on equidistant fisheye images. In the experimental evaluation, we demonstrate that the proposed RANSAC-R algorithm significantly improves matching performance. Specifically, the recall rate is increased from approximately \(50\%\) to \(100\%\) , while maintaining \(100\%\) matching precision. Furthermore, in experiments conducted with 140-degree and 180-degree fisheye cameras, the inlier rate is improved by approximately 2.5 times and 4 times, respectively. When capturing images, it poses a significant challenge to ensure the precise alignment of the camera’s optical centers, resulting in parallax that introduces artifacts into the stitched images. To eliminate artifacts, this paper presents a new stitching method, the multi-rotation motion projection method (MRM), which is capable of producing high-quality stitching results for multiple fisheye or pinhole images without introducing noticeable distortion. The experimental results indicate that both methods substantially enhance stitching accuracy, effectively reduce geometric distortion, and yield panoramas of practical quality.