US 2026/0182491 A1 · IDENTIFICATION, COUNTING, AND DISEASE DETECTION USING ARTIFICIAL INTELLIGENCE FOR AUTOMATED FOOD PRODUCT HARVESTING

Abstract

A machine for harvesting root crops integrates imaging devices, machine learning, and automated sorting capabilities to enable real-time crop identification, counting, disease detection, and data collection during harvesting operations. The machine captures images of individual root crops as they are extracted from soil and processes the images using a trained machine learning model to identify individual crops, generate accurate counts, and detect disease conditions based on visual characteristics. A global positioning system determines geographic locations for each identified crop, while weight sensors measure individual crop weights. A controller automatically activates a sorting mechanism to physically separate diseased crops from healthy crops based on disease detection results. The system generates comprehensive crop data records associating each harvested crop with count data, weight data, disease status, and GPS coordinates, creating spatially-referenced maps that correlate crop characteristics with field locations to enable precision agricultural analysis and targeted interventions.

Claims21

Dependent claims

A method of harvesting sugar beets, the method comprising:

operating a sugar beet harvesting machine configured to pull sugar beets from the ground and transport the sugar beets along a conveyor system;
capturing image data of the sugar beets on the conveyor system;
processing the image data using a pre-trained machine learning model to identify individual sugar beets in the image data;
generating a count of harvested sugar beets based on the identified individual sugar beets;
receiving a first signal from a load sensor associated with the conveyor system, wherein the first signal indicates a total weight of sugar beets on a first portion of the conveyor system;
determining a predicted weight for each individual sugar beet based on the count of harvested sugar beets and the first signal from the load sensor;
obtaining GPS data indicating a precise location where each individual sugar beet was pulled from the ground;
and
creating a data record for each individual sugar beet, wherein each data record includes the predicted weight of the individual sugar beet and the GPS data indicating the precise location where the individual sugar beet was pulled from the ground.

6 more elements

A machine for harvesting root crops, the machine comprising:

a harvesting mechanism configured to extract root crops from soil;
one or more imaging devices mounted on the machine and configured to capture a plurality of images of individual root crops as the root crops are being harvested from the soil;
a processor operatively coupled to the one or more imaging devices and configured with a trained machine learning model to process the captured images to:
(i) identify and differentiate individual root crops within the captured images,
(ii) generate a count of the individual root crops, and
(iii) detect presence of disease conditions in the individual root crops based on visual characteristics;
a global positioning system operatively coupled to the processor and configured to determine, for each identified root crop, a geographic location using positioning data;
a data generation module operatively coupled to the processor and configured to generate, in real-time during the harvesting operations, crop data records that associate each identified root crop with its corresponding count data, disease detection data, and geographic location data;
a sorting mechanism integrated into the machine and configured to physically separate diseased root crops from healthy root crops;
a controller operatively coupled to the processor and the sorting mechanism, the controller configured to automatically control the sorting mechanism to separate the diseased root crops from the healthy root crops based on the disease detection data;
and
a storage system operatively coupled to the data generation module and configured to store the crop data records in a database to create a spatially-referenced map correlating crop health status with geographic locations across a harvested field;
wherein the processor, the global positioning system, the data generation module, and the controller are configured to operate substantially contemporaneously with the extraction of the root crops from the soil by the harvesting mechanism.

10 more elements

Dependencies are inferred from the claim text.

Identification, counting, and disease detection using artificial intelligence for automated food product harvesting

Life of this patent

Identification, counting, and disease detection using artificial intelligence for automated food product harvesting

Life of this patent

Abstract

Claims21