基于3DSOM的植株三维重建方法研究

Study on the 3D Reconstruction Method of Plants Based on 3DSOM

三维重建技术在智慧农业研究领域有着广阔的应用前景。本研究以抽穗期小麦和树木枝干为研究对象,在搭建了植株序列图像获取平台的基础上,探究了3DSOM软件在不同数量序列图像下的植株三维重建效率和精度。对于小麦植株,分别对比了32、48、64幅序列图像下重建模型的效果和精度;试验表明:3DSOM对于小麦的重建效果一般。对于树木枝干,分别对比了40、60、80幅序列图像下的重建模型,试验表明重建效果较好。为了验证3DSOM软件对植株的重建精度,对小麦3个截段的测量进行了对比。对比结果表明:其重建误差不高于3.18%,最低为0.39%,平均精度为2.16%。对枝干的8个截段的测量对比结果表明:其重建误差不高于2.66%,最低为0.4 3%,平均精度为1.4 0%。因此,将3DSOM应用于植株的三维重建可以取得高精度的效果。

3D reconstruction technology has a very broad application prospects in smart agriculture fields. In this re- search, the wheat during heading stage and branches were selected as the research objects, and the image sequence cap- turing platform was set first and and the 3DSOM software was used to test its efficiency and accuracy of three-dimensional reconstruction. For wheat, 32, 48 and 64 images were compared, the results show 3DSOM could be used for the recon- struction of small plants. For branches, 40, 60 and 80 sequence images were compared and the experiments show that reconstruction is better for larger plants. 3 markers for wheat were selected and compared, the results show that the re- construction error is not more than 3.18% , the lowest of 0.39% , with an average accuracy of 2.16%. 8 markers were selected for branches, the results show that the reconstruction error of not more than 2.66% , the lowest of only 0.43% , with an average accuracy of 1.40%. All the results show that 3DSOM software could be applied to the high accuracy 3D reconstruction of plants.