Crop biometrics detection

1. A system for detecting crop biometrics, the system comprising:

a crop modeling device communicatively coupled to an imaging device, wherein the crop modeling device comprises processing circuitry configured to:

receive, from the imaging device, a plurality of images of a crop of a plurality of plants in a field, wherein the plurality of plants in the field include at least one of overlapping or occluding leaves,

generate, based on the plurality of images, a three-dimensional (3D) model of the plurality of plants, wherein the 3D model defines locations and orientations of leaves and stems of respective plants of the plurality of plants, and

determine, based on the 3D model, at least one of a plant height, a leaf count, a leaf angle, or an inter-nodal distance of a respective plant of the plurality of plants in the field, the respective plant including the at least one of the overlapping or the occluding leaves,

wherein the processor is configured to generate the 3D model of the plurality of plants by at least:

generating an initial point cloud reconstruction of the plurality of plants in the field based on the plurality of images,

simulating respective routes of a plurality of randomly selected points of the initial point cloud by:

identifying a ground plane within a 3D space of the initial point cloud reconstruction,

simulating, for each of a plurality of randomly selected points within the initial point cloud, point-by-point movement from an initial position of the selected point within the initial point cloud reconstruction towards the identified ground plane based on a height of respective points within the initial point cloud, and

determining the respective routes of the plurality of randomly selected points based on the simulated point by point movement,

detecting respective stems of the plurality of plants based on the simulated respective routes, and

following the detection of the respective stems of the plurality of plants, separating the at least one of overlapping or occluding leaves of the plurality of plants in the field by segmenting the leaves connected to the respective stems using the initial point cloud reconstruction.

2. The system of claim 1 , further comprising an unmanned aerial vehicle including the at least one imaging device.

3. The system of claim 1 , wherein the processor is configured to determine the at least one of the plant height, the leaf count, the leaf angle, or the inter-nodal distance of the respective plant including the at least one of the overlapping or the occluding leaves by at least:

locating, following the separation of the at least one of overlapping or occluding leaves, a respective stem and a respective uppermost leaf of each respective plant,

determining a separation between the base of the respective stem and the respective uppermost leaf, and

determining, based on the separation between the base of the respective stem and the respective uppermost leaf, the plant height of the respective plant.

4. The system of claim 3 , wherein the processor is configured to determine the separation between the base of the respective stem and the respective uppermost leaf by at least determining an average lowest point for a predetermined plurality of plants adjacent to and comprising the respective plant.

5. The system of claim 1 , wherein the processor is configured to determine the at least one of the plant height, the leaf count, the leaf angle, or the inter-nodal distance of the respective plant including the at least one of the overlapping or the occluding leaves by at least:

locating, following the separation of the at least one of overlapping or occluding leaves, a respective stem and a respective uppermost leaf of each respective plant,

determining, based on the segmentation, a plurality of leaf-stem nodes of each respective plant, and

determining, based on the leaf-stem nodes, at least one of the leaf count, the leaf angle, or the inter-nodal distance of each respective plant.

6. The system of claim 5 , wherein the processor generates the initial point cloud reconstruction of the plurality of plants in the field based on the plurality of images by at least:

generating a reduced point cloud reconstruction by reduce the number of points in the initial point cloud reconstruction by k-means clustering.

7. The system of claim 1 , wherein the processor is configured to:

receive, from the imaging device, a plurality of images of a leaf of a plant in a field,

generate, based on the plurality of images, a point cloud model of the leaf,

generate, based on the point cloud model, a self-organized map representing a surface of the leaf, and

determine, based on the self-organized map, a total surface area of the leaf.

8. The system of claim 7 , wherein the plurality of images includes images taken at different locations and different orientations about the leaf.

9. The system of claim 7 , wherein the self-organized map is defined by four-sided polygons.

10. A method for detecting crop biometrics, the method comprising:

receiving, by processing circuitry and from an imaging device, a plurality of images of a crop of a plurality of plants in a field, wherein the plurality of plants in the field include at least one of overlapping or occluding leaves;

generating, by the processing circuitry, based on the plurality of images, a three-dimensional (3D) model of the plurality of plants, wherein the 3D model defines locations and orientations of leaves and stems of respective plants of the plurality of plants; and

determining, by the processing circuitry and based on the 3D model, at least one of a plant height, a leaf count, a leaf angle, or an inter-nodal distance of a respective plant of the plurality of plants in the field, the respective plant including the at least one of the overlapping or the occluding leaves,

wherein generating the 3D model of the plurality plants comprises:

generating an initial point cloud reconstruction of the plurality of plants in the field based on the plurality of images,

simulating respective routes of a plurality of randomly selected points of the initial point cloud by:

identifying a ground plane within a 3D space of the initial point cloud reconstruction,

simulating, for each of a plurality of randomly selected points within the initial point cloud, point-by-point movement from an initial position of the selected point within the initial point cloud reconstruction towards the identified ground plane based on a height of respective points within the initial point cloud, and

determining the respective routes of the plurality of randomly selected points based on the simulated point by point movement,

detecting respective stems of the plurality of plants based on the simulated respective routes, and

following the detection of the respective stems of the plurality of plants, separating the at least one of overlapping or occluding leaves of the plurality of plants in the field by segmenting the leaves connected to the respective stems using the initial point cloud reconstruction.

11. The method of claim 10 , wherein the imaging device is part of an unmanned vehicle, and wherein the unmanned vehicle comprises an unmanned aerial vehicle.

12. The method of claim 10 , wherein determining, based on the 3D model, the at least one of the plant height, the leaf count, the leaf angle, or the inter-nodal distance of the respective plant including the at least one of the overlapping or the occluding leaves comprises:

locating, following the separation of the at least one of overlapping or occluding leaves, by the processor, a respective stem and a respective uppermost leaf of each respective plant,

determining a separation between the base of the respective stem and the respective uppermost leaf, and

determining, based on the separation between the base of the respective stem and the respective uppermost leaf, the plant height of the respective plant.

13. The method of claim 12 , wherein determining the separation between the base of the respective stem and the respective uppermost leaf comprises determining an average lowest point for a predetermined plurality of plants adjacent to and comprising the respective plant.

14. The method of claim 10 , wherein determining, based on the 3D model, the at least one biometric parameter of the crop of plants in the field comprises:

locating, following the separation of the at least one of overlapping or occluding leaves, a respective stem and a respective plurality of leaves of each respective plant,

determining, based on the segmentation, a plurality of leaf-stem nodes of each respective plant, and

determining, based on the leaf-stem nodes, at least one of the leaf count, the leaf angle, or the inter-nodal distance of each respective plant.

15. The system of claim 14 , wherein generating the initial point cloud reconstruction of the plurality of plants in the field based on the plurality of images comprises

generating a reduced point cloud reconstruction by reduce the number of points in the initial point cloud reconstruction by k-means clustering.

16. The method of claim 1 , further comprising:

receiving, from the imaging device, a plurality of images of a leaf of a plant in a field,

generating, based on the plurality of images, a point cloud model of the leaf,

generating, based on the point cloud model, a self-organized map representing a surface of the leaf, and

determining, based on the self-organized map, a total surface area of the leaf.

17. The method of claim 16 , wherein the plurality of images includes images taken at different locations and different orientations about the leaf.

18. The method of claim 16 , wherein the self-organized map is defined by four-sided polygons.

19. The system of claim 1 , wherein the processing circuitry is configured to detect the respective stems based on common simulated routes of the randomly selected points.

20. The system of claim 1 , wherein the processing circuitry is configured to apply a skeleton Kalman filtering process to separate the at least one of the overlapping or the occluding leaves of the plurality of plants.