Back to results
US 12,716,879 B2Granted
Systems and methods for crop health monitoring, assessment and prediction
AssigneeViscon Group Holding B.V.
InventorsSaber Miresmailli, Maryam Antikchi
Life of this patent
Estimating the term…
Abstract
Systems and methods for monitoring and assessing crop health and performance can provide rapid screening of individual plants. The systems and methods have an automated component, and rely primarily on the detection and interpretation of plant-based signals to provide information about crop health. In some cases knowledge from human experts is captured and integrated into the automated crop monitoring systems and methods. Predictive models can also be developed and used to predict future health of plants in a crop.
Claims20
A method comprising:
- in a training phase:
- receiving a human expert assessment of a state of each plant of a first plurality of plants based on visual inspection of the first plurality of plants by at least one human expert;
- receiving training sensor data captured for each plant of the first plurality of plants;
- and
- correlating the human expert assessment with the training sensor data using machine learning to generate a model;
- and
- in an assessment phase:
- receiving assessment sensor data captured for each plant of a second plurality of plants;
- classifying a state of each plant of the second plurality of plants by applying the model to the assessment sensor data;
- and
- transmitting information relating to the state of each plant of the second plurality of plants to at least one end-user device;
- wherein the training sensor data captured for the first plurality of plants includes sensor data captured for plants that are healthy and sensor data captured for plants that are unhealthy as identified by the at least one human expert.
9 more elements
A system comprising:
- at least one interface configured to:
- receive a human expert assessment of a state of each plant of a first plurality of plants based on visual inspection of the first plurality of plants by at least one human expert;
- receive training sensor data captured for each plant of the first plurality of plants;
- and
- receive assessment sensor data captured for each plant of a second plurality of plants;
- and
- at least one processor configured to:
- correlate the human expert assessment with the training sensor data using machine learning to generate a model;
- classify a state of each plant of the second plurality of plants by applying the model to the assessment sensor data;
- and
- initiate transmission of information relating to the state of each plant of the second plurality of plants to at least one end-user device;
- wherein the training sensor data captured for the first plurality of plants includes sensor data captured for plants that are healthy and sensor data captured for plants that are unhealthy as identified by the at least one human expert.
9 more elements
Dependencies are inferred from the claim text.