江滔, 马泳, 黄珺, 王贺松, 樊凡. 基于赋权连接图的增量式运动恢复结构算法[J]. 应用光学, 2022, 43(5): 921-928, 1014. DOI: 10.5768/JAO202243.0502006
引用本文: 江滔, 马泳, 黄珺, 王贺松, 樊凡. 基于赋权连接图的增量式运动恢复结构算法[J]. 应用光学, 2022, 43(5): 921-928, 1014. DOI: 10.5768/JAO202243.0502006
JIANG Tao, MA Yong, HUANG Jun, WANG Hesong, FAN Fan. Incremental structure from motion algorithm based on weighted scene graph[J]. Journal of Applied Optics, 2022, 43(5): 921-928, 1014. DOI: 10.5768/JAO202243.0502006
Citation: JIANG Tao, MA Yong, HUANG Jun, WANG Hesong, FAN Fan. Incremental structure from motion algorithm based on weighted scene graph[J]. Journal of Applied Optics, 2022, 43(5): 921-928, 1014. DOI: 10.5768/JAO202243.0502006

基于赋权连接图的增量式运动恢复结构算法

Incremental structure from motion algorithm based on weighted scene graph

  • 摘要: 运动恢复结构算法(structure from motion, SfM)是一种通过计算图像匹配关系,恢复出相机位姿和目标三维结构的重建算法。提出一种基于赋权视角连接图的增量式运动恢复结构算法。首先建立基于图像对立体匹配质量的赋权连接图,量化了图像两两之间的匹配关系;其次在赋权连接图中边的权重的基础上,搜索度数感知的最佳初始种子对;最后根据已重建顶点的连通性构建下一张最佳图像候选集,设计了基于顶点度数与特征点分布的下一张最佳图像评价算法。在公开数据集上实验结果显示,本文算法在重建质量、相机校准率和点云生成数量的表现优于现有先进的运动恢复结构算法,相比基准对比算法,本文算法在不同数据集上平均重建耗时至少降低了19%,点云生成速率至少提升了21%。

     

    Abstract: The structure from motion (SfM) is a reconstruction algorithm that recovers the pose of cameras and three-dimensional structure of the target by calculating the image matching relationship. An incremental SfM algorithm based on weighted scene graph was proposed. Firstly, a weighted scene graph was established, which quantified the matching relationship between image pairs. Secondly, an optimal initial seed pair of degree perception was searched based on the edge weights of the weighted scene graph. Finally, the next optimal image candidate set was constructed according to the connectivity of the reconstructed vertices, and an evaluation algorithm based on the vertex degree and feature point distribution was designed to search for the next optimal image in the candidate set. The experimental results on multiple public datasets show that the proposed algorithm outperforms existing advanced structure from motion algorithms in terms of reconstruction quality, camera calibration rate and point cloud generation quantity. Compared with the benchmark comparison algorithms, the average reconstruction time on different datasets is reduced by at least 19%, and the point cloud generation rate is increased by at least 21%.

     

/

返回文章
返回