[1]陈国军,张清伟,李开悦,等.基于RGB—D树状结构物体三维重建[J].计算机技术与发展,2018,28(12):142-146.[doi:10．3969／j．issn．1673—629X．2018．12．030]
　CHENGuo-jan,ZHANG Qing-wei,LI Kaiyue,et al.3D Reconstruction of Tree Structure Based on RGB—D[J].,2018,28(12):142-146.[doi:10．3969／j．issn．1673—629X．2018．12．030]
点击复制

基于RGB—D树状结构物体三维重建()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年12期
页码:
142-146
栏目:
应用开发研究
出版日期:
2018-12-10

文章信息/Info

Title:
3D Reconstruction of Tree Structure Based on RGB—D
文章编号:
1673—629X(2018)12—0142—05
作者:
陈国军; 张清伟; 李开悦; 曹岳
中国石油大学(华东)计算机与通信工程学院，山东青岛266000)
Author(s):
CHENGuo-jan; ZHANG Qing-wei; LI Kai—yue; CAO Yue
School of Computer&Communication Engineering，China University of Petroleum，Qingdao 266000，China)
关键词:
Kinect; 三维重建; 法向量; 曲率; 最小二乘法; ICP
Keywords:
inect; three-dimensional reconstruction; normal; cul’vature; least squares method; ICP
分类号:
TP391.9
DOI:
10．3969／j．issn．1673—629X．2018．12．030
摘要:
由于设备采集树状物体数据精度差，导致树状物体枝干连接部位数据丢失，重建出来的树状物体枝干不连续。树状结构物体颜色单调统一，各枝叶形状相似，导致特征点提取困难，配准精度低。通过对深度数据的分析，彩色图像与深度数据相比拥有更完整的信息，使用深度数据与彩色数据相结合的方法，根据彩色图像与深度数据的坐标映射关系，使用彩色图像修复缺失的深度数据。边界轮廓同样能够体现物体的形状特征，使用目标边界点作为特征点，应用边界点的曲率属性进行特征点的匹配。实验结果表明，使用彩色深度数据结合的优化方法相比较于直接用深度图优化深度数据的方法，能够解决枝干间断的问题，同时使边缘数据更加完整。使用边界特征配准方法能够为1CP精确配准提供良好的初始位置，从而提高精确配准时的精度。
Abstract:
The poor acquisition accuracy of data collected by the equipment for the fine objects makes the data of the branch connecting parts lost and the reconstructed tree branches discontinuous．The color of tree structure of the object is monotonous and uniform，and the shape of the branches and leavesis similar．bo山resulting in difficulty in feature point extraction and low registration accuracy．Through the depth of data analysis，the color image has more complete information than the depth data，the method of combining depth data with color data to repair the missing depth data using color images according to the coordinate mapping relationship between color image and depth data．The boundary profile call also reflect the shape featIl他s of the object。with the target boundary point as the feature point，alrplying the curvature attribute of the boundary point to match the feature points，and then making the rough match for thematching pair．The experiment shows that the method proposed Can solve the problem of branch discontinuity and improve the edge data more closely than the method of optimizing the depth data directly with depth map．The method of boundary feature registration proposed Can provide a great initial position for accurate ICP registration，thus improving the accuracy of precise registration．

相似文献/References:

[1]王建文 王敏.基于双目立体视觉的鞋楦三维建模[J].计算机技术与发展,2009,(04):224.
　WANG Jian-wen,WANG Min.3D Reconstruction of Shoe- last Based on Binocular Stereo Vision[J].,2009,(12):224.
[2]于勇 张晖 林茂松.基于双目立体视觉三维重建系统的研究与设计[J].计算机技术与发展,2009,(06):127.
　YU Yong,ZHANG Hui,LIN Mao-song.Research and Design of the 3D Reconstruction System Based on Binocular Stereo Vision[J].,2009,(12):127.
[3]印勇 林纯颖.基于对应点匹配的眼球切片图像插值算法[J].计算机技术与发展,2007,(10):102.
　YIN Yong,LIN Chun-ying.An Interpolation Algorithm of Eye Slice Images Based on Matching Corresponding Points[J].,2007,(12):102.
[4]王玫 张月东 尚宪刚 张兆臣.虚拟脊柱手术系统的设计[J].计算机技术与发展,2011,(07):179.
　WANG Mei,ZHANG Yue-dong,SHANG Xian-gang,et al.The Design of Virtual Spinal Surgery System[J].,2011,(12):179.
[5]张宁,杨磊.基于 Phong 模型的多幅图像 SFS 算法研究[J].计算机技术与发展,2013,(01):9.
　ZHANG Ning,YANG Lei.Research on Algorithm of SFS for Multi-images Based on Phong Model[J].,2013,(12):9.
[6]黄露丹,严利民.基于Kinect深度数据的人物检测[J].计算机技术与发展,2013,(04):119.
　HUANG Lu-dan,YAN Li-min.Human Detection Based on Depth Data Acquired by Kinect[J].,2013,(12):119.
[7]谢亮,廖宏建,杨玉宝.基于Kinect的姿势识别与应用研究[J].计算机技术与发展,2013,(05):258.
　XIE Liang,LIAO Hong-jian,YANG Yu-bao.Recognition and Application Research of Kinect-based Gesture[J].,2013,(12):258.
[8]肖秦琨,罗丹,肖秦汉.基于多视角视频的运动重建[J].计算机技术与发展,2014,24(02):84.
　XIAO Qin-kun[],LUO Dan[],XIAO Qin-han[].Motion Reconstruction Based on Multi-view Video[J].,2014,24(12):84.
[9]林晓雷. 医学影像仿真扫描工作站的设计与实现[J].计算机技术与发展,2015,25(01):187.
　LIN Xiao-lei. Design and Implementation of Medical Imaging Simulation Scanning Workstation[J].,2015,25(12):187.
[10]李孟,周波,孟正大,等. 三目立体相机的标定研究[J].计算机技术与发展,2015,25(02):69.
　LI Meng,ZHOU Bo,MENG Zheng-da,et al. Study on Trinocular Stereo Camera Calibration[J].,2015,25(12):69.

更新日期/Last Update: 2018-12-10