欢迎访问《中国农学通报》,

中国农学通报 ›› 2011, Vol. 27 ›› Issue (33): 266-272.

• 工程 机械 水利 装备 • 上一篇    下一篇

基于数码相机的农田景物三维重建

王传宇 赵春江 郭新宇 温维亮 苗腾   

  • 收稿日期:2011-05-04 修回日期:2011-08-22 出版日期:2011-12-25 发布日期:2011-12-25
  • 基金资助:

    国家农业科技成果转化资金项目;北京市自然科学基金重点项目

3D Reconstruction of Virtual Agricultural Field Scene Based on Digital Camera

  • Received:2011-05-04 Revised:2011-08-22 Online:2011-12-25 Published:2011-12-25

摘要:

为提出一种基于图像的农田景物三维重建方法。首先从图像文件中提取包含相机焦距等参数的EXIF信息,用以计算相机内参矩阵。根据两幅对应图像的匹配关系,求解本征矩阵并对其SVD分解获得相机外参矩阵,合并相机内外参数构成投影矩阵。其次,以SIFT匹配点的视差作为搜索范围初始限制条件,按像素邻域的SSD值匹配两幅图像中的像素,获得致密的视差图并以三维点云形式重建田块景观,最后,使用“集束调整”算法对最初三维重建结果求精,并将2维图像像素RGB值映射到三维点云上,获得最终结果。从重建效果看,方法真实再现性好,重建过程简洁,具有较高的自动化程度。

关键词: 武夷菌素, 武夷菌素, Plackett-Burman, 响应面法, 优化

Abstract:

In this paper, we present a new approach for 3D reconstruction of agricultural field scene using a hand-hold digital camera. Firstly, EXIF information such as focal length was abstracted from image in JEPG format, camera intrinsic matrix could be solved based on these parameters. Camera extrinsic matrix was acquired from SVD decomposition of essential matrix which stand for matching relationship between two images, with intrinsic and extrinsic matrix camera projection matrix was available. Secondly, in order to generate dense 3D points cloud of field scene, each pixel was matched up according to SSD value, under the searching threshold from the differences of SIFT matching points in two images. Finally, the initial 3D model was refined with bundle adjustment, map the RGB value to correspondence 3D point, we got the final agricultural field scene. From the 3D reconstruction result, we can draw the conclusion that, our method has a good reflection of real world, and has the advantage of concision, and highly automated.

中图分类号: