| 摘要: |
| 深度图像在采集过程中由于受到设备本身和采集环境的影响，使采集得到的图像中存在大量的空洞，以致很难提取到准确的深度信息；提出了一种形态学滤波与双边滤波相结合的方法来解决深度图像中的空洞现象，算法根据形态学算法简单、易于分析的特点，首先利用膨胀、腐蚀、开运算、闭运算等基本算法对空洞部分进行填充，然后通过双边滤波使图像平滑； 实验结果表明方法对深度图像中所存在的空洞问题能够起到有效的填补，修复后的图像相比于原始深度图像，更加清晰，易于提取出可靠的信息。 |
| 关键词: 深度图像 空洞 形态学 双边滤波 |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Study on an Improved Depth Image Restoration Algorithm |
|
PENG Cheng, SUN Xin zhu
|
| Abstract: |
| In depth image acquisition process due to the impact of the device itself and acquisition environment, the image obtained has a large number of empty,it is difficult to extract accurate depth information to solve the problem,a new method is proposed to solve the void in the depth image,which is simple and easy to be analyzed.First, expansion,corrosion,opening and closing operations and other basic algorithm are used to fill the empty part,and then through the bilateral filtering to make the image smooth.Experimental results show that the proposed method can effectively fill the holes in the depth image,and it is more clear and easy to extract reliable information than the original image. |
| Key words: depth image cavity morphology bilateral filtering |
