Surface feature based classification of plant organs from 3D laserscanned point clouds for plant phenotyping.
Bottom Line:
We introduced an approach using surface feature histograms for automated plant organ parameterization.Highly reliable classification results of about 96% for the separation of grapevine and wheat organs have been obtained.This approach was found to be independent of the point to point distance and applicable to multiple plant species.
Affiliation: Institute of Geodesy and Geoinformation - Professorship of Geodesy, University of Bonn, Nussallee 17, 53115 Bonn, Germany. paulus@igg.uni-bonn.de
ABSTRACT
Show MeSH
Background: Laserscanning recently has become a powerful and common method for plant parameterization and plant growth observation on nearly every scale range. However, 3D measurements with high accuracy, spatial resolution and speed result in a multitude of points that require processing and analysis. The primary objective of this research has been to establish a reliable and fast technique for high throughput phenotyping using differentiation, segmentation and classification of single plants by a fully automated system. In this report, we introduce a technique for automated classification of point clouds of plants and present the applicability for plant parameterization. Results: A surface feature histogram based approach from the field of robotics was adapted to close-up laserscans of plants. Local geometric point features describe class characteristics, which were used to distinguish among different plant organs. This approach has been proven and tested on several plant species. Grapevine stems and leaves were classified with an accuracy of up to 98%. The proposed method was successfully transferred to 3D-laserscans of wheat plants for yield estimation. Wheat ears were separated with an accuracy of 96% from other plant organs. Subsequently, the ear volume was calculated and correlated to the ear weight, the kernel weights and the number of kernels. Furthermore the impact of the data resolution was evaluated considering point to point distances between 0.3 and 4.0 mm with respect to the classification accuracy. Conclusion: We introduced an approach using surface feature histograms for automated plant organ parameterization. Highly reliable classification results of about 96% for the separation of grapevine and wheat organs have been obtained. This approach was found to be independent of the point to point distance and applicable to multiple plant species. Its reliability, flexibility and its high order of automation make this method well suited for the demands of high throughput phenotyping. Highlights: • Automatic classification of plant organs using geometrical surface information• Transfer of analysis methods for low resolution point clouds to close-up laser measurements of plants• Analysis of 3D-data requirements for automated plant organ classification. Related in: MedlinePlus |
![]() Related In:
Results -
Collection
License getmorefigures.php?uid=PMC3750309&req=5
Figure 8: Point clouds of geometrical standard shapes like plane (A), cone (B), sphere (C) and cylinder (D) show unique histograms due to their differing surface properties. Mentions: 3D laserscanned point clouds were analysed by surface feature histograms. They were developed by [15,16] for the demands of robotics and adjusted for classification of geometrical primitives in low resolved point clouds. The surface feature histograms are well suited for real time processing of laser data. Furthermore they provide a density and pose invariant description of the surface using properties of differential geometry. They can be used for point cloud segmentation and separation of different surface areas showing different surface properties. Histograms descriptions for primitives like plane, cube, sphere, cylinder and cone are shown in Figure 8. The characteristic of a histogram to a single point depends, beside the properties of the surface, on the radius for normal calculation rN and the radius for the histogram calculation rH. Both parameters represent the number of neighbor points that were used for calculation. The histogram implementation follows an adapted approach using a special distance weight explained below. |
View Article: PubMed Central - HTML - PubMed
Affiliation: Institute of Geodesy and Geoinformation - Professorship of Geodesy, University of Bonn, Nussallee 17, 53115 Bonn, Germany. paulus@igg.uni-bonn.de
Background: Laserscanning recently has become a powerful and common method for plant parameterization and plant growth observation on nearly every scale range. However, 3D measurements with high accuracy, spatial resolution and speed result in a multitude of points that require processing and analysis. The primary objective of this research has been to establish a reliable and fast technique for high throughput phenotyping using differentiation, segmentation and classification of single plants by a fully automated system. In this report, we introduce a technique for automated classification of point clouds of plants and present the applicability for plant parameterization.
Results: A surface feature histogram based approach from the field of robotics was adapted to close-up laserscans of plants. Local geometric point features describe class characteristics, which were used to distinguish among different plant organs. This approach has been proven and tested on several plant species. Grapevine stems and leaves were classified with an accuracy of up to 98%. The proposed method was successfully transferred to 3D-laserscans of wheat plants for yield estimation. Wheat ears were separated with an accuracy of 96% from other plant organs. Subsequently, the ear volume was calculated and correlated to the ear weight, the kernel weights and the number of kernels. Furthermore the impact of the data resolution was evaluated considering point to point distances between 0.3 and 4.0 mm with respect to the classification accuracy.
Conclusion: We introduced an approach using surface feature histograms for automated plant organ parameterization. Highly reliable classification results of about 96% for the separation of grapevine and wheat organs have been obtained. This approach was found to be independent of the point to point distance and applicable to multiple plant species. Its reliability, flexibility and its high order of automation make this method well suited for the demands of high throughput phenotyping.
Highlights: • Automatic classification of plant organs using geometrical surface information• Transfer of analysis methods for low resolution point clouds to close-up laser measurements of plants• Analysis of 3D-data requirements for automated plant organ classification.