Methods for agronomic and agricultural monitoring using unmanned aerial systems

1. A method for agronomic and agricultural monitoring, the method comprising:

monitoring, by a first central processing unit (CPU) at a base station, an unmanned aerial vehicle (UAV) as the UAV flies along a flight path above an area and as the UAV performs:

capturing, by a second CPU of the UAV as the UAV flies along the flight path, a plurality of initial images of the area and capturing one or more additional different images of one or more target areas suspected of having one or more anomalies;

orthorectifying and stitching the plurality of initial images into a first single continuous area image;

orthorectifying and stitching the one or more additional different images into a second single continuous area image;

superimposing the first single continuous area image onto the second single continuous area image to generate a superimposed image;

partitioning the superimposed image into one or more areas, each area corresponding to one plant of a plurality of plants;

identifying, in the one or more areas, one or more structures, each structure corresponding to part of at least one plant of a plurality of plants depicted in the superimposed image;

for each area of one or more areas:

determining, based on the one or more structures, whether at least one anomaly, of the one or more anomalies, is present in an area; and

in response to determining, based on the one or more structures, that at least one anomaly, of the one or more anomalies, is present in the area, generating one or more agronomic recommendations for addressing the at least one anomaly, of the one or more anomalies, in the area.

2. The method of claim 1 , wherein the one or more anomalies include one or more of: white spaces determined based on a greenness density and that do not represent any desired plant from a planted population.

3. The method of claim 1 , wherein the one or more anomalies include one or more of non-crop matters such as weeds, pests, or stalks affected by diseases.

4. The method of claim 1 , wherein the one or more anomalies include a weed anomaly which is identified by determining a weed pressure value for a structure from the one or more structures by dividing a size of the structure by a size of the area.

5. The method of claim 1 , wherein a plant disease anomaly is identified by comparing a reflectivity of a crop plant identified in a structure of the one or more structures to a threshold value or to an average reflectivity value of the crop plant.

6. The method of claim 1 , wherein a pest anomaly is identified by comparing a reflectivity of a crop plant identified in a structure of the one or more structures to a threshold value or to an average reflectivity value of the crop plant.

7. The method of claim 1 , wherein a pest anomaly is identified by collecting one or more high-resolution images for one or more high-resolution structures and comparing a reflectivity of a crop plant identified in a high-resolution structure of the one or more high-resolution structures to a threshold value or to an average reflectivity value of the crop plant.

8. The method of claim 1 , further comprising:

based on at least the one or more anomalies, generating a report indicating one or more regions having certain characteristics comprising one or more of: low nitrogen levels, low crop maturity levels, or high crop shadow levels;

using the UAV, sending the report to a computing device;

receiving, from the computing device, instructions to acquire one or more new images of one or more new target areas;

receiving, from the computing device, the one or more new images of the one or more new target areas; and

identifying the one or more anomalies based on, at least in part, the one or more new images.

9. The method of claim 1 , further comprising: based on the plurality of initial images and the one or more additional different images, determining a greenness density map for the area, wherein the greenness density map has an expected greenness density area depicted in a first color and other areas depicted in a second color.

10. The method of claim 1 , further comprising: processing, using the base station or a cloud computer, the plurality of initial images and the one or more additional different images by performing one or more of:

based on the plurality of initial images and the one or more additional different images, generating at least one of a normalized difference vegetation index map, or an application map for the area;

based on the plurality of initial images and the one or more additional different images, determining an emergence map for the area;

based on the plurality of initial images and the one or more additional different images, generating at least one of a normalized difference vegetation index map, or an application map;

based on the plurality of initial images and the one or more additional different images, generating one or more agronomic recommendations for the area; and

wherein the processing of the plurality of initial images and the one or more different images is performed at one or more of: the base station, or a cloud system.

11. A system for agronomic and agricultural monitoring, the system comprising:

one or more processors, one or more memory units, one or more non-transitory computer-readable storage media storing one or more computer instructions which, when executed by the one or more processors, cause the one or more processors to perform:

monitoring, by a first central processing unit (CPU) at a base station, an unmanned aerial vehicle (UAV) as the UAV flies along a flight path above an area and as the UAV performs:

capturing, by a second CPU of the UAV as the UAV flies along the flight path, a plurality of initial images of the area and capturing one or more additional different images of one or more target areas suspected of having one or more anomalies;

orthorectifying and stitching the plurality of initial images into a first single continuous area image;

orthorectifying and stitching the one or more additional different images into a second single continuous area image;

superimposing the first single continuous area image onto the second single continuous area image to generate a superimposed image;

partitioning the superimposed image into one or more areas, each area corresponding to one plant of a plurality of plants;

identifying, in the one or more areas, one or more structures, each structure corresponding to part of at least one plant of a plurality of plants depicted in the superimposed image;

for each area of one or more areas:

determining, based on the one or more structures, whether at least one anomaly, of the one or more anomalies, is present in an area; and

in response to determining, based on the one or more structures, that at least one anomaly, of the one or more anomalies, is present in the area, generating one or more agronomic recommendations for addressing the at least one anomaly, of the one or more anomalies, in the area.

12. The system of claim 11 , wherein the one or more anomalies include one or more of: white spaces determined based on a greenness density and that do not represent any desired plant from a planted population.

13. The system of claim 11 , wherein the one or more anomalies include one or more of non-crop matters such as weeds, pests, or stalks affected by diseases.

14. The system of claim 11 , wherein a weed anomaly is identified by determining a weed pressure value for a structure from the one or more structures by dividing a size of the structure by a size of the area.

15. The system of claim 11 , wherein a plant disease anomaly is identified by comparing a reflectivity of a crop plant identified in a structure of the one or more structures to a threshold value or to an average reflectivity value of the crop plant.

16. The system of claim 11 , wherein a pest anomaly is identified by comparing a reflectivity of a crop plant identified in a structure of the one or more structures to a threshold value or to an average reflectivity value of the crop plant.

17. The system of claim 11 , wherein a pest anomaly is identified by collecting one or more high-resolution images for one or more high-resolution structures and comparing a reflectivity of a crop plant identified in a high-resolution structure of the one or more high-resolution structures to a threshold value or to an average reflectivity value of the crop plant.

18. The system of claim 11 , wherein the one or more non-transitory computer-readable storage media store additional instructions which, when executed by the one or more processors, cause the one or more processors to perform:

based on at least the one or more anomalies, generating a report indicating one or more regions having certain characteristics comprising one or more of: low nitrogen levels, low crop maturity levels, or high crop shadow levels;

using the UAV, sending the report to a computing device;

receiving, from the computing device, instructions to acquire one or more new images of one or more new target areas;

receiving, from the computing device, the one or more new images of one or more new target areas; and

identifying the one or more anomalies based on, at least in part, the one or more new images.

19. The system of claim 11 , wherein the one or more non-transitory computer-readable storage media store additional instructions which, when executed by the one or more processors, cause the one or more processors to perform: based on the plurality of initial images and the one or more additional different images, determining a greenness density map for the area, wherein the greenness density map has an expected greenness density area depicted in a first color and other areas depicted in a second color.

20. The system of claim 11 , wherein the one or more non-transitory computer-readable storage media store additional instructions which, when executed by the one or more processors, cause the one or more processors to perform:

processing, using the base station or a cloud computer, the plurality of initial images and the one or more additional different images by performing one or more of:

based on the plurality of initial images and the one or more additional different images, generating at least one of a normalized difference vegetation index map, or an application map for the area;

based on the plurality of initial images and the one or more additional different images, determining an emergence map for the area;

based on the plurality of initial images and the one or more additional different images, generating at least one of a normalized difference vegetation index map, or an application map;

based on the plurality of initial images and the one or more additional different images, generating one or more agronomic recommendations for the area; and

wherein the processing of the plurality of initial images and the one or more different images is performed at one or more of: the base station, or a cloud system.