Systems and methods for monitoring agricultural products

• US 10,520,482 B2
• Filed: 05/11/2018
• Issued: 12/31/2019
• Est. Priority Date: 06/01/2012
• Status: Active Grant

• Current Assignee: AGERpoint, Inc.
• Original Assignee: AGERpoint, Inc.
• Inventors: McPeek, K. Thomas
• Primary Examiner(s): Ishizuka, Yoshihisa
• Application Number:
  US15/977,771
• Publication Number:
  US 20180259496A1
• Time in Patent Office: 599 Days
• CPC Class Codes: G01B 11/24 for measuring contours or curvatures
• CPC Class Codes: G01B 5/0035 Measuring of dimensions of trees
• CPC Class Codes: G01N 2021/1797 in landscape, e.g. crops
• CPC Class Codes: G01N 2021/8466 Investigation of vegetal material, e.g. leaves, plants, fruits
• CPC Class Codes: G01N 21/251 Colorimeters; Construction thereof
• CPC Class Codes: G01N 21/31 Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry G01N21/72 takes precedence
• CPC Class Codes: G01N 21/359 using near infrared light
• CPC Class Codes: G01N 2201/0216 Vehicle borne
• CPC Class Codes: G01N 33/0098 Plants or trees wood G01N33/46
• CPC Class Codes: G01N 33/025 Fruits or vegetables

Abstract

The present invention relates to systems and methods for monitoring agricultural products. In particular, the present invention relates to monitoring fruit production, plant growth, and plant vitality. According to embodiments of the invention, a plant analysis system is configured determine a spectral signature of a plant based on spectral data, and plant color based on photographic data. The spectral signatures and plant color are associated with assembled point cloud data. Morphological data of the plant can be generated based on the assembled point cloud data. A record of the plant can be created that associates the plant with the spectral signature, plant color, spectral data, assembled point cloud data, and morphological data, and stored in a library.

Claims

1. A plant analysis system, comprising:

a) a data acquisition component comprising a 3D laser scanner, a camera, a spectral sensor, and a survey grade global positioning satellite (GPS) receiver, said survey grade GPS receiver configured to measure location with a sub centimeter level of accuracy, said 3D laser scanner configured to measure properties of a plant utilizing waveform light detection and ranging (LiDAR) and assemble point cloud data, said assembled point cloud data comprising a plurality of three dimensional vertices each of which represents the external surface of an object on said plant, said camera configured to collect photographic data of said plant, said spectral sensor for gathering spectral data for said plant, and said GPS receiver for geo-registering the point cloud data and photographic data, wherein each three dimensional vertex of said assembled point cloud data is associated with GPS data, said photographic data, and said spectral data;

b) a transport vehicle coupled to said data acquisition component and configured to collect said data on said plant; and

c) a processor configured to;

determine a spectral signature of said plant based on said spectral data,

determine plant color based on said photographic data and associate said assembled point cloud data with said plant color,

generate morphological data of said plant based on said assembled point cloud data, said morphological data comprising plant stem diameter, plant height, plant volume, and plant leaf density, and

create a record of said plant in a library, wherein the record of said plant associates said plant with said spectral signature, said plant color, said spectral data, said assembled point cloud data, and said morphological data.

2. The plant analysis system of claim 1, wherein the processor generates said morphological data by segmenting said assembled point cloud data to identify boundaries of said plant.

3. The plant analysis system of claim 2, wherein the processor classifies said morphological data to identify a plant feature, said plant feature comprising a branching structure, trunk, biomass, canopy, fruit, blossom, fruit cluster, or blossom cluster.

4. The plant analysis system of claim 1, wherein the processor utilizes said assembled point cloud data and said plant color to discriminate a fruit, blossom, fruit cluster, or blossom cluster from a shadow, said discrimination based on analyzing a pixel-by-pixel variation of said plant color and a geometric shape defined by the vertices of said assembled point cloud data.

5. The plant analysis system of claim 1, wherein said data acquisition component further comprising atmospheric sensors for measuring atmospheric conditions, and wherein said processor determines a phenotype of a plant based on said spectral signatures, said morphological data, and said atmospheric conditions.

6. The plant analysis system of claim 1, wherein said processor is further configured to determine a vegetation index of one or more plants based on said spectral data.

7. The plant analysis system of claim 1, wherein said processor is further configured to determine a number and a size of fruits or blossoms on a plant, wherein the number and size of fruits or blossoms on a plant is based on a fusion of said assembled point cloud data and plant color data.

8. The plant analysis system of claim 7, wherein said number and size of fruits or blossoms on a plant is determined by clustering said assembled point cloud data and plant color data.

9. The plant analysis system of claim 8, wherein a crop yield is estimate based on said number and size of fruits or blossoms on a plant.

10. The plant analysis system of claim 1, wherein said processor is further configured to compare a spectral signature of a plant with a spectral signature from said library of plant records based on the spectral information divergence of said spectral signatures.

11. The plant analysis system of claim 10, wherein said processor is further configured to detect the presence of a plant disease based on said comparison of spectral signatures.

12. The plant analysis system of claim 11, wherein said processor is further configured to detect the presence of wilt or leaf drop caused by environmental stressors based on said comparison of spectral signatures.

13. The plant analysis system of claim 12, wherein said processor is further configured to identify a pest, including a disease vector, and predict said pest'"'"'s trajectory.

14. The plant analysis system of claim 1, wherein said spectral sensor is an active hyperspectral sensor.

15. The plant analysis system of claim 1, wherein said library of plant records is further configured to store historical data associated with a plant, said historical data comprising one or more of date of planting, root stock, grating record, nutritional treatment, health treatment, yield, surrounding soil conditions, surrounding atmospheric conditions, and surrounding topography.

16. The plant analysis system of claim 1, further comprising an asset management dashboard for accessing, viewing, analyzing and controlling said library of plant records.

17. The plant analysis system of claim 16, wherein said asset management dashboard integrates spatial information of a subset of said plant records in a configurable display, said subset of said plant records correspond to a plot on an orchard, and wherein said asset management dashboard allows users to generate precise counting and statistical reports about said plant records.

18. The plant analysis system of claim 17, wherein said asset management dashboard is configured to filter said plant records for viewing according to their location and health.

19. The plant analysis system of claim 17, wherein said asset management dashboard is configured to visualize a plurality of layers of sensor data over a map of three-dimensional point clouds.

20. The plant analysis system of claim 1, further comprising a post-processing server configured to receive data collected by said data acquisition component, and an asset management dashboard coupled to said post-processing server, wherein said record of said plant is created at the post-processing server and transmitted to said asset management dashboard.