Harvester Multi-Camera Imaging for Real-Time Crop State Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current agricultural harvesting equipment lacks the ability to acquire and process real-time state information about the harvesting operation, requiring manual intervention and lacking in intelligent unmanned operations, leading to inefficiencies and high production costs.

Innovation Solution

An image acquisition device and processing method that captures and processes images of the harvesting operation area, including positions of crops to be harvested, harvested, and the state of harvesting, enabling real-time feedback and control for unmanned operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If multiple cameras are used to capture surrounding images for comprehensive harvesting operation information, then the completeness of state information is improved, but the device complexity and cost increase

Engineering Contradiction:
Improvecompleteness of harvesting state informationVSAvoidnumber of cameras and image processing system
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The image acquisition system is segmented into multiple cameras positioned at different locations (front, rear, left, right sides of the harvesting machine) to capture different aspects of the harvesting operation. Each camera focuses on specific areas (crops to be harvested, crops being harvested, crops already harvested) to collectively provide comprehensive state information without requiring a single complex all-seeing system

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The image processing system is designed to extract multiple types of harvesting state information (positions of crops to be harvested, positions of harvested crops, and state of crops being harvested) from the combined images captured by the camera system, making the system multi-functional in terms of information extraction while using a unified processing architecture

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If real-time image processing algorithms are implemented to extract harvesting operation state information, then the accuracy of state information is improved, but the processing time and computational cost increase

Engineering Contradiction:
Improveaccuracy of harvesting state informationVSAvoidimage processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by capturing images from multiple predetermined camera positions that are strategically placed to cover all necessary harvesting areas. The image processing algorithm is pre-configured to extract specific harvesting state information (crop positions, harvesting state) from these standardized image formats, enabling faster processing compared to analyzing arbitrary images from unknown angles

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system extracts only the specific harvesting state information that is necessary for operation control (positions of crops to be harvested, positions of harvested crops, and state of crops being harvested) from the captured images, rather than performing comprehensive image analysis. This partial extraction approach provides sufficient information for harvesting decisions without the computational overhead of complete scene understanding

Inventive Principle:
Principle #16Partial or excessive action

3Area of stationary object

If long-distance scene images are captured to monitor large harvesting areas, then the coverage area is improved, but the image quality and usefulness for specific harvesting decisions deteriorate

Engineering Contradiction:
Improvemonitoring coverage areaVSAvoidusefulness of images for harvesting decisions
Core Design Contradiction:
Area of stationary objectVSMeasurement precision

Solution Approach 1:

Instead of using a single long-distance camera to monitor the entire harvesting area, the system employs multiple cameras positioned at different locations around the harvesting machine, each capturing images of specific local areas (front, rear, left, right sides). This provides detailed, high-quality images of locally relevant harvesting states (crops to be harvested, crops being harvested) that are immediately useful for harvesting decisions

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3954190B1Image acquisition device and processing method for agricultural harvesting operation machine
Publication Date: 2025.07.09 FJ DYNAMICS TECH CO LTD
  • EP3954190B1 patent drawingFigure 1
  • EP3954190B1 patent drawingFigure 2
  • EP3954190B1 patent drawingFigure 3~4

AI summary

An image acquisition device and image processing method for an agricultural harvesting operation machine. The agricultural harvesting operation machine comprises a body and an image acquisition device; the image acquisition device comprises an image capturing component and a communication machine; the image acquisition device is mounted on the body; the communication machine is communicatably connected to the image capturing component so as to obtain acquired image information from the image capturing component, thereby assisting in adjusting the working position and operation speed of the body. Also provided is an image processing method. Information required by harvesting operation is taken into full consideration, images of the position of an agricultural harvesting operation machine are acquired, and multiple acquired images are efficiently processed.