Three-Dimensional Reconstruction of Soybean Canopy Based on Multivision Technology for Calculation of Phenotypic Traits
Round 1
Reviewer 1 Report
Based on multi-visual vision, this research provides a technique for 3D reconstruction of the soybean canopy and estimation of plant characteristics. To gather all-round point cloud data of soybean, a multi-vision acquisition system based on the Kinect sensor was built. Random Sample Consensus and Iterative Closest Point were used to match and fuse the point clouds. Finally, based on the reconstruction of the morphological structure of live soybean, the plant height, leafstalk angle, and crown width of soybean were estimated.
For me is difficult to understand the novelty in the research. The 3D point cloud reconstruction, presented here is already presented in Guan, H., Liu, M., Ma, X., & Yu, S. (2018). Three-dimensional reconstruction of the soybean canopies using multisource imaging for phenotyping analysis. Remote Sensing, 10(8), 1206, where the current paper's title is "Three-dimensional reconstruction of soybean canopy based on multi-vision technology...". Probably to be changed with "Soybean parameter estimation..."? They are used well known methods for 3D point cloud processing. According to calculation of plant parameters (leafstalk angle), the idea (and realisation) is already presented in Zhu, K., Ma, X., Guan, H., Feng, J., Zhang, Z., & Yu, S. (2021). A method of calculating the leafstalk angle of the soybean canopy based on 3D point clouds. International Journal of Remote Sensing, 42(7), 2463-2484.
Overall, the article is well written. There are formulas and letters, which are with different style and size.
Author Response
Dear reviewer,
Thank you for your comments and suggestions, we have revised the manuscript according to your comment, the response file has been attached here.
Regards,
Xiaodan Ma
Author Response File: 
Author Response.pdf
Reviewer 2 Report
In this work, the authors present a three-dimensional reconstruction of soybean canopy based on multi-vision technology for phenotyping analysis. Here some minor issues that encourage the authors to address:
- Section 0 has to be section 1.
- I can understand that in general the proposed algorithm is based in 3D registration methods using depth images. however, I think that aLiDAR sensing mechanism could provide more accurate reconstructions and therefore more accurate performance by using the proposed approach. Can the authors discuss about this?
- There are a little grammatical/style error. In my opinion, a grammar/style revision has to be carried out.
Author Response
Dear reviewer,
Thank you for your comments and suggestions, we have revised the manuscript according to your comment, the response file has been attached here.
Regards,
Xiaodan Ma
Author Response File: Author Response.pdf
