Per-plant aerial image data analytics method and devices

Patent metadata

Field	Value
Publication number	US-11915366-B2
Application number	US-202117241531-A
Country	US
Kind code	B2
Filing date	Apr 27, 2021
Priority date	Apr 27, 2021
Publication date	Feb 27, 2024
Grant date	Feb 27, 2024

Abstract

The embodiments disclose a method comprising creating 3D models of an orchard with multiple plants in the form of a densified point cloud using oblique aerial RGB imaging and photogrammetry, identifying and segmenting individual plants of the orchard from the 3D models, simulating sunlight radiation in the 3D models, determining a shading effect of branches and neighboring plants on each individual plant at any time of the day, determining canopy light interception of each plant, analyzing canopy geometry of each plant in the 3D models, forecasting potential yield of each plant based on the measured canopy light interception and calculating nitrogen and water requirements of each plant based on the potential yield and other predetermined field, environmental and climate factors and validating the yield forecasting model using the canopy light interception data by measuring the actual yield for each plant.

First claim

What is claimed is:

1. A method, comprising:
creating 3D models of an orchard with multiple plants in the form of a densified point cloud using oblique aerial RGB imaging and photogrammetry;
identifying and segmenting individual plants of the orchard from the 3D models;
simulating sunlight radiation of each plant in the 3D models;
determining a shading effect of branches and neighboring plants on each individual plant at any time of the day;
determining canopy light interception of each plant;
extracting and analyzing canopy profile features of each plant in the 3D models;
forecasting potential yield of each plant based on the measured canopy light interception;
calculating nitrogen and water requirements of each plant based on the potential yield and other predetermined field, environmental and climate factors; and
providing a measured actual yield for each plant to validate yield forecasting by canopy light interception data.

2. The method of claim 1 , further comprising creating 3D models of an orchard with multiple plants in the form of a densified point cloud using a digital surface model (DSM) generated by Light Detection and Ranging (LiDAR) sensors, wherein LiDAR has much higher pixel resolutions.

3. The method of claim 1 , further comprising identifying and segmenting individual plants of the orchard from the 3D models by extracting canopy profile features per-plant by segmenting pixels with a predefined minimum elevation above the ground in a normalized DSM.

4. The method of claim 1 , further comprising simulating sunlight radiation of each plant in the 3D models over a growing season during the solar noon (also known as the incoming Fractional PAR (fPAR)) by measuring the percentage of sunlight intercepted by a tree canopy.

5. The method of claim 1 , further comprising determining a shading effect of branches and neighboring plants on each individual plant at any time of the day will consider the sun angle and irradiance variation during the day.

6. The method of claim 1 , further comprising determining canopy light interception of each plant analyses shadow conditions at different times of a day (from 7 AM to 8 PM) in mid-June for providing an indication of canopy light interception variation over time for each tree and its impact on surrounding trees.

7. The method of claim 1 , further comprising analyzing canopy geometry of each plant in the 3D models utilizing sun angle and irradiance variation during the day and each trees corresponding shadow angles affecting canopy light interception variation over time.

8. The method of claim 1 , further comprising forecasting potential yield of each plant based on the measured canopy light interception uses real-size 3D models of the orchard to simulate sunlight and measure mid-day (solar noon) canopy light interception per tree including the shading effect of branches and neighboring trees.

9. The method of claim 1 , further comprising calculating nitrogen and water requirements of each plant based on the potential yield and other predetermined field, environmental and climate factors includes spectral reflectance to determine a tree nitrogen status.

10. The method of claim 1 , further comprising validating the yield forecasting model using canopy light interception data by measuring the actual yield for each plant and comparing to the canopy light interception of the corresponding plant.

11. An apparatus, comprising:
at least one device configured for creating 3D models of an orchard with multiple plants in the form of a densified point cloud using oblique aerial RGB imaging and photogrammetry;
at least one device configured for identifying and segmenting individual plants of the orchard from the 3D models;
at least one device configured for simulating sunlight radiation of each plant in the 3D models;
at least one device configured for determining a shading effect of branches and neighboring plants on each individual plant at any time of the day;
at least one device configured for determining canopy light interception of each plant;
at least one device configured for analyzing canopy geometry of each plant in the 3D models;
at least one device configured for forecasting potential yield of each plant based on the measured canopy light interception;
at least one device configured for calculating nitrogen and water requirements of each plant based on the potential yield and other predetermined field, environmental and climate factors; and
at least one device configured for validating the yield forecasting model using canopy light interception data by measuring the actual yield for each plant.

12. The apparatus of claim 11 , further comprising at least one device configured for processing aerial imagery to create 3D models of plants and configured to include extracting canopy profile features per-plant.

13. The apparatus of claim 11 , further comprising at least one device configured for calculating nitrogen and water requirements of each plant based on potential yield forecasted by the virtual orchard (VO) method, and field, environmental and climate factors as well as spectral reflectance to determine a tree nitrogen status.

14. The apparatus of claim 11 , further comprising at least one device configured for determining canopy light interception of each plant based on measured canopy light interception using real-size 3D models of the orchard to simulate sunlight and measure mid-day canopy light interception per tree including the shading effect of branches and neighboring trees.

15. The apparatus of claim 11 , further comprising at least one device configured for identifying and segmenting individual plants of the orchard from the 3D models by extracting canopy profile features per-plant by segmenting pixels with a predefined minimum elevation above the ground in a normalized DSM.

16. An apparatus, comprising:
at least one device configured for collecting per plant canopy profile features using 3D models created by aerial imagery in an orchard;
at least one device configured for identifying and segmenting individual plants of the orchard from the 3D models;
at least one device configured for creating real-size 3D images of each plant to simulate sunlight and measure mid-day canopy light interception per tree;
at least one device configured for simulating sunlight radiation of each plant in the real-size 3D models;
at least one device configured for determining a shading effect of branches and neighboring plants on each individual plant at any time of the day;
at least one device configured for measuring canopy light interception for each plant over a growing season; and
at least one device configured for forecasting potential yield of each plant based on the measured canopy light interception.

17. The apparatus of claim 16 , further comprising at least one device configured for collecting per plant canopy profile features using 3D models created by at least one Light Detection and Ranging (LiDAR) sensor.

18. The apparatus of claim 16 , further comprising at least one device configured for extracting canopy profile features per-plant by segmenting pixels of the real-size 3D models with a predefined minimum elevation above the ground.

19. The apparatus of claim 16 , further comprising at least one device configured for calculating nitrogen and water requirements of each plant based on potential yield forecasted by the virtual orchard (VO) method, and field, environmental and climate factors as well as spectral reflectance to determine a tree nitrogen status for

Assignees

• Univ California

Inventors

• Pourreza Alireza

Classifications

• G06T17/00 Primary

  Three-dimensional [3D] modelling for computer graphics · CPC title

• G01S17/89

  for mapping or imaging · CPC title

• G06T15/80

  Shading · CPC title

• G06V10/26

  Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion · CPC title

• G06V10/751

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title