• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 图形与图像 • 上一篇    下一篇

基于Kinect相机的深度图像空洞修复及超像素分割算法

刘国华1,2,段建春1   

  1. (1.天津工业大学机械工程学院,天津300387;2.天津市现代机电装备技术重点实验室,天津300387)
  • 收稿日期:2019-09-11 修回日期:2020-01-18 出版日期:2020-05-25 发布日期:2020-05-25
  • 基金资助:

    天津市科技计划项目(18JCTPJC62700)

A deep image hole repairing method and a superpixel
segmentation algorithm based on Kinect camera
 

LIU Guo-hua1,2,DUAN Jian-chun1   

  1. (1.School of Mechanical Engineering,Tiangong University,Tianjin 300387;
    2.Advanced Mechatronics Equipment Technology Tianjin Major Laboratory,Tianjin 300387,China)

     
  • Received:2019-09-11 Revised:2020-01-18 Online:2020-05-25 Published:2020-05-25

摘要:

针对Kinect相机原始深度图像存在空洞的问题,提出了一种结合彩色图像局部边缘信息的深度图像空洞修复算法。首先,通过双边滤波修复较小空洞;其次,根据彩色图像局部边缘信息将较大空洞分为无边缘和有边缘2类;最后,对第1类无边缘空洞进行均值填充修复,对第2类有边缘空洞先根据彩色图像局部边缘特征分割空洞,再分别由外而内逐步修复,从而完成所有的空洞修复。空洞修复完成后,融合深度信息重新建立了线性谱聚类核函数,并基于此提出一种融合深度信息的线性谱聚类超像素分割算法(LSC-D)。实验结果表明,与其他方法相比,提出的深度图像空洞修复算法具有更高的修复准确度,提出的LSC-D超像素分割算法具有更低的欠分割错误率和更高的边界召回率。

 

关键词: Kinect相机, 深度图像, 空洞修复, 超像素

Abstract:

Aiming at the problem that there is a hole in the original depth image of Kinect camera, a deep image hole repairing algorithm combining local edge information of color image is proposed. Firs- tly, the smaller holes are repaired by bilateral filtering. Secondly, according to the local edge information of the color image, the larger holes are divided into two types: edgeless and edged. Finally, the average type fill-in repairing is performed on the first type of edgeless holes, and the second type of
ed- ged holes are segmented based on the local edge features of the color image and then gradually repaired from the outside to the end, so as to complete all hole repairing. After the hole repairing is completed, the fusion depth is fused to re-establish the linear spectral clustering kernel function. Based on this, a linear spectral clustering superpixel segmentation algorithm  (LSC-D) is proposed. The experimental results show that, compared with other methods, the proposed deep image hole repairing algorithm  has higher repairing accuracy, and the proposed superpixel segmentation algorithm  has lower under-segmentation error rate and higher boundary recall rate.
 

Key words: Kinect camera, depth image, hole repair, superpixel